TensorFlow/classification.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "MhoQ0WE77laV"
   },
   "source": [
    "##### Copyright 2018 The TensorFlow Authors."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "cellView": "form",
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:48.690538Z",
     "iopub.status.busy": "2020-10-15T01:28:48.689438Z",
     "iopub.status.idle": "2020-10-15T01:28:48.692375Z",
     "shell.execute_reply": "2020-10-15T01:28:48.691811Z"
    },
    "id": "_ckMIh7O7s6D"
   },
   "outputs": [],
   "source": [
    "#@title Licensed under the Apache License, Version 2.0 (the \"License\");\n",
    "# you may not use this file except in compliance with the License.\n",
    "# You may obtain a copy of the License at\n",
    "#\n",
    "# https://www.apache.org/licenses/LICENSE-2.0\n",
    "#\n",
    "# Unless required by applicable law or agreed to in writing, software\n",
    "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
    "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
    "# See the License for the specific language governing permissions and\n",
    "# limitations under the License."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "cellView": "form",
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:48.696906Z",
     "iopub.status.busy": "2020-10-15T01:28:48.695809Z",
     "iopub.status.idle": "2020-10-15T01:28:48.698639Z",
     "shell.execute_reply": "2020-10-15T01:28:48.697957Z"
    },
    "id": "vasWnqRgy1H4"
   },
   "outputs": [],
   "source": [
    "#@title MIT License\n",
    "#\n",
    "# Copyright (c) 2017 François Chollet\n",
    "#\n",
    "# Permission is hereby granted, free of charge, to any person obtaining a\n",
    "# copy of this software and associated documentation files (the \"Software\"),\n",
    "# to deal in the Software without restriction, including without limitation\n",
    "# the rights to use, copy, modify, merge, publish, distribute, sublicense,\n",
    "# and/or sell copies of the Software, and to permit persons to whom the\n",
    "# Software is furnished to do so, subject to the following conditions:\n",
    "#\n",
    "# The above copyright notice and this permission notice shall be included in\n",
    "# all copies or substantial portions of the Software.\n",
    "#\n",
    "# THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\n",
    "# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\n",
    "# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL\n",
    "# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\n",
    "# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING\n",
    "# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER\n",
    "# DEALINGS IN THE SOFTWARE."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "jYysdyb-CaWM"
   },
   "source": [
    "# Basic classification: Classify images of clothing"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "S5Uhzt6vVIB2"
   },
   "source": [
    "<table class=\"tfo-notebook-buttons\" align=\"left\">\n",
    "  <td>\n",
    "    <a target=\"_blank\" href=\"https://www.tensorflow.org/tutorials/keras/classification\"><img src=\"https://www.tensorflow.org/images/tf_logo_32px.png\" />View on TensorFlow.org</a>\n",
    "  </td>\n",
    "  <td>\n",
    "    <a target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/keras/classification.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
    "  </td>\n",
    "  <td>\n",
    "    <a target=\"_blank\" href=\"https://github.com/tensorflow/docs/blob/master/site/en/tutorials/keras/classification.ipynb\"><img src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" />View source on GitHub</a>\n",
    "  </td>\n",
    "  <td>\n",
    "    <a href=\"https://storage.googleapis.com/tensorflow_docs/docs/site/en/tutorials/keras/classification.ipynb\"><img src=\"https://www.tensorflow.org/images/download_logo_32px.png\" />Download notebook</a>\n",
    "  </td>\n",
    "</table>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "FbVhjPpzn6BM"
   },
   "source": [
    "This guide trains a neural network model to classify images of clothing, like sneakers and shirts. It's okay if you don't understand all the details; this is a fast-paced overview of a complete TensorFlow program with the details explained as you go.\n",
    "\n",
    "This guide uses [tf.keras](https://www.tensorflow.org/guide/keras), a high-level API to build and train models in TensorFlow."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:48.704610Z",
     "iopub.status.busy": "2020-10-15T01:28:48.703507Z",
     "iopub.status.idle": "2020-10-15T01:28:54.941102Z",
     "shell.execute_reply": "2020-10-15T01:28:54.941516Z"
    },
    "id": "dzLKpmZICaWN"
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stderr",
     "text": [
      "WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.\n",
      "WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.\n",
      "WARNING:root:Limited tf.compat.v2.summary API due to missing TensorBoard installation.\n",
      "WARNING:root:Limited tf.summary API due to missing TensorBoard installation.\n",
      "2.4.1\n"
     ]
    }
   ],
   "source": [
    "# TensorFlow and tf.keras\n",
    "import tensorflow as tf\n",
    "\n",
    "# Helper libraries\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "print(tf.__version__)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "yR0EdgrLCaWR"
   },
   "source": [
    "## Import the Fashion MNIST dataset"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "DLdCchMdCaWQ"
   },
   "source": [
    "This guide uses the [Fashion MNIST](https://github.com/zalandoresearch/fashion-mnist) dataset which contains 70,000 grayscale images in 10 categories. The images show individual articles of clothing at low resolution (28 by 28 pixels), as seen here:\n",
    "\n",
    "<table>\n",
    "  <tr><td>\n",
    "    <img src=\"https://tensorflow.org/images/fashion-mnist-sprite.png\"\n",
    "         alt=\"Fashion MNIST sprite\"  width=\"600\">\n",
    "  </td></tr>\n",
    "  <tr><td align=\"center\">\n",
    "    <b>Figure 1.</b> <a href=\"https://github.com/zalandoresearch/fashion-mnist\">Fashion-MNIST samples</a> (by Zalando, MIT License).<br/>&nbsp;\n",
    "  </td></tr>\n",
    "</table>\n",
    "\n",
    "Fashion MNIST is intended as a drop-in replacement for the classic [MNIST](http://yann.lecun.com/exdb/mnist/) dataset—often used as the \"Hello, World\" of machine learning programs for computer vision. The MNIST dataset contains images of handwritten digits (0, 1, 2, etc.) in a format identical to that of the articles of clothing you'll use here.\n",
    "\n",
    "This guide uses Fashion MNIST for variety, and because it's a slightly more challenging problem than regular MNIST. Both datasets are relatively small and are used to verify that an algorithm works as expected. They're good starting points to test and debug code.\n",
    "\n",
    "Here, 60,000 images are used to train the network and 10,000 images to evaluate how accurately the network learned to classify images. You can access the Fashion MNIST directly from TensorFlow. Import and load the Fashion MNIST data directly from TensorFlow:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:54.947431Z",
     "iopub.status.busy": "2020-10-15T01:28:54.945758Z",
     "iopub.status.idle": "2020-10-15T01:28:55.921866Z",
     "shell.execute_reply": "2020-10-15T01:28:55.920987Z"
    },
    "id": "7MqDQO0KCaWS"
   },
   "outputs": [],
   "source": [
    "fashion_mnist = tf.keras.datasets.fashion_mnist\n",
    "\n",
    "(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "t9FDsUlxCaWW"
   },
   "source": [
    "Loading the dataset returns four NumPy arrays:\n",
    "\n",
    "* The `train_images` and `train_labels` arrays are the *training set*—the data the model uses to learn.\n",
    "* The model is tested against the *test set*, the `test_images`, and `test_labels` arrays.\n",
    "\n",
    "The images are 28x28 NumPy arrays, with pixel values ranging from 0 to 255. The *labels* are an array of integers, ranging from 0 to 9. These correspond to the *class* of clothing the image represents:\n",
    "\n",
    "<table>\n",
    "  <tr>\n",
    "    <th>Label</th>\n",
    "    <th>Class</th>\n",
    "  </tr>\n",
    "  <tr>\n",
    "    <td>0</td>\n",
    "    <td>T-shirt/top</td>\n",
    "  </tr>\n",
    "  <tr>\n",
    "    <td>1</td>\n",
    "    <td>Trouser</td>\n",
    "  </tr>\n",
    "    <tr>\n",
    "    <td>2</td>\n",
    "    <td>Pullover</td>\n",
    "  </tr>\n",
    "    <tr>\n",
    "    <td>3</td>\n",
    "    <td>Dress</td>\n",
    "  </tr>\n",
    "    <tr>\n",
    "    <td>4</td>\n",
    "    <td>Coat</td>\n",
    "  </tr>\n",
    "    <tr>\n",
    "    <td>5</td>\n",
    "    <td>Sandal</td>\n",
    "  </tr>\n",
    "    <tr>\n",
    "    <td>6</td>\n",
    "    <td>Shirt</td>\n",
    "  </tr>\n",
    "    <tr>\n",
    "    <td>7</td>\n",
    "    <td>Sneaker</td>\n",
    "  </tr>\n",
    "    <tr>\n",
    "    <td>8</td>\n",
    "    <td>Bag</td>\n",
    "  </tr>\n",
    "    <tr>\n",
    "    <td>9</td>\n",
    "    <td>Ankle boot</td>\n",
    "  </tr>\n",
    "</table>\n",
    "\n",
    "Each image is mapped to a single label. Since the *class names* are not included with the dataset, store them here to use later when plotting the images:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:55.927038Z",
     "iopub.status.busy": "2020-10-15T01:28:55.926055Z",
     "iopub.status.idle": "2020-10-15T01:28:55.928759Z",
     "shell.execute_reply": "2020-10-15T01:28:55.928121Z"
    },
    "id": "IjnLH5S2CaWx"
   },
   "outputs": [],
   "source": [
    "class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',\n",
    "               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Brm0b_KACaWX"
   },
   "source": [
    "## Explore the data\n",
    "\n",
    "Let's explore the format of the dataset before training the model. The following shows there are 60,000 images in the training set, with each image represented as 28 x 28 pixels:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:55.934510Z",
     "iopub.status.busy": "2020-10-15T01:28:55.933579Z",
     "iopub.status.idle": "2020-10-15T01:28:55.937673Z",
     "shell.execute_reply": "2020-10-15T01:28:55.938105Z"
    },
    "id": "zW5k_xz1CaWX"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "(60000, 28, 28)"
      ]
     },
     "metadata": {},
     "execution_count": 9
    }
   ],
   "source": [
    "train_images.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "cIAcvQqMCaWf"
   },
   "source": [
    "Likewise, there are 60,000 labels in the training set:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:55.942785Z",
     "iopub.status.busy": "2020-10-15T01:28:55.941935Z",
     "iopub.status.idle": "2020-10-15T01:28:55.945134Z",
     "shell.execute_reply": "2020-10-15T01:28:55.945674Z"
    },
    "id": "TRFYHB2mCaWb"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "60000"
      ]
     },
     "metadata": {},
     "execution_count": 10
    }
   ],
   "source": [
    "len(train_labels)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "YSlYxFuRCaWk"
   },
   "source": [
    "Each label is an integer between 0 and 9:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:55.950046Z",
     "iopub.status.busy": "2020-10-15T01:28:55.949289Z",
     "iopub.status.idle": "2020-10-15T01:28:55.952794Z",
     "shell.execute_reply": "2020-10-15T01:28:55.952207Z"
    },
    "id": "XKnCTHz4CaWg"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "array([9, 0, 0, ..., 3, 0, 5], dtype=uint8)"
      ]
     },
     "metadata": {},
     "execution_count": 11
    }
   ],
   "source": [
    "train_labels"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "TMPI88iZpO2T"
   },
   "source": [
    "There are 10,000 images in the test set. Again, each image is represented as 28 x 28 pixels:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:55.957082Z",
     "iopub.status.busy": "2020-10-15T01:28:55.956303Z",
     "iopub.status.idle": "2020-10-15T01:28:55.959375Z",
     "shell.execute_reply": "2020-10-15T01:28:55.959771Z"
    },
    "id": "2KFnYlcwCaWl"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "(10000, 28, 28)"
      ]
     },
     "metadata": {},
     "execution_count": 12
    }
   ],
   "source": [
    "test_images.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "rd0A0Iu0CaWq"
   },
   "source": [
    "And the test set contains 10,000 images labels:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:55.963873Z",
     "iopub.status.busy": "2020-10-15T01:28:55.963023Z",
     "iopub.status.idle": "2020-10-15T01:28:55.966085Z",
     "shell.execute_reply": "2020-10-15T01:28:55.966508Z"
    },
    "id": "iJmPr5-ACaWn"
   },
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": [
       "10000"
      ]
     },
     "metadata": {},
     "execution_count": 13
    }
   ],
   "source": [
    "len(test_labels)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ES6uQoLKCaWr"
   },
   "source": [
    "## Preprocess the data\n",
    "\n",
    "The data must be preprocessed before training the network. If you inspect the first image in the training set, you will see that the pixel values fall in the range of 0 to 255:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:55.984523Z",
     "iopub.status.busy": "2020-10-15T01:28:55.983443Z",
     "iopub.status.idle": "2020-10-15T01:28:56.147713Z",
     "shell.execute_reply": "2020-10-15T01:28:56.147090Z"
    },
    "id": "m4VEw8Ud9Quh"
   },
   "outputs": [
    {
     "output_type": "display_data",
     "data": {
      "text/plain": "<Figure size 432x288 with 2 Axes>",
      "image/png": "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\n"
     },
     "metadata": {
      "needs_background": "light"
     }
    }
   ],
   "source": [
    "plt.figure()\n",
    "plt.imshow(train_images[0])\n",
    "plt.colorbar()\n",
    "plt.grid(False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Wz7l27Lz9S1P"
   },
   "source": [
    "Scale these values to a range of 0 to 1 before feeding them to the neural network model. To do so, divide the values by 255. It's important that the *training set* and the *testing set* be preprocessed in the same way:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:56.152920Z",
     "iopub.status.busy": "2020-10-15T01:28:56.151644Z",
     "iopub.status.idle": "2020-10-15T01:28:56.309548Z",
     "shell.execute_reply": "2020-10-15T01:28:56.310021Z"
    },
    "id": "bW5WzIPlCaWv"
   },
   "outputs": [],
   "source": [
    "train_images = train_images / 255.0\n",
    "\n",
    "test_images = test_images / 255.0"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Ee638AlnCaWz"
   },
   "source": [
    "To verify that the data is in the correct format and that you're ready to build and train the network, let's display the first 25 images from the *training set* and display the class name below each image."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:56.350855Z",
     "iopub.status.busy": "2020-10-15T01:28:56.327945Z",
     "iopub.status.idle": "2020-10-15T01:28:57.224132Z",
     "shell.execute_reply": "2020-10-15T01:28:57.224604Z"
    },
    "id": "oZTImqg_CaW1"
   },
   "outputs": [
    {
     "output_type": "display_data",
     "data": {
      "text/plain": "<Figure size 720x720 with 25 Axes>",
      "image/png": "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\n"
     },
     "metadata": {}
    }
   ],
   "source": [
    "plt.figure(figsize=(10,10))\n",
    "for i in range(25):\n",
    "    plt.subplot(5,5,i+1)\n",
    "    plt.xticks([])\n",
    "    plt.yticks([])\n",
    "    plt.grid(False)\n",
    "    plt.imshow(train_images[i], cmap=plt.cm.binary)\n",
    "    plt.xlabel(class_names[train_labels[i]])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "59veuiEZCaW4"
   },
   "source": [
    "## Build the model\n",
    "\n",
    "Building the neural network requires configuring the layers of the model, then compiling the model."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Gxg1XGm0eOBy"
   },
   "source": [
    "### Set up the layers\n",
    "\n",
    "The basic building block of a neural network is the *layer*. Layers extract representations from the data fed into them. Hopefully, these representations are meaningful for the problem at hand.\n",
    "\n",
    "Most of deep learning consists of chaining together simple layers. Most layers, such as `tf.keras.layers.Dense`, have parameters that are learned during training."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:57.230757Z",
     "iopub.status.busy": "2020-10-15T01:28:57.229590Z",
     "iopub.status.idle": "2020-10-15T01:28:58.945316Z",
     "shell.execute_reply": "2020-10-15T01:28:58.944694Z"
    },
    "id": "9ODch-OFCaW4"
   },
   "outputs": [],
   "source": [
    "model = tf.keras.Sequential([\n",
    "    tf.keras.layers.Flatten(input_shape=(28, 28)),\n",
    "    tf.keras.layers.Dense(128, activation='relu'),\n",
    "    tf.keras.layers.Dense(10)\n",
    "])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "gut8A_7rCaW6"
   },
   "source": [
    "The first layer in this network, `tf.keras.layers.Flatten`, transforms the format of the images from a two-dimensional array (of 28 by 28 pixels) to a one-dimensional array (of 28 * 28 = 784 pixels). Think of this layer as unstacking rows of pixels in the image and lining them up. This layer has no parameters to learn; it only reformats the data.\n",
    "\n",
    "After the pixels are flattened, the network consists of a sequence of two `tf.keras.layers.Dense` layers. These are densely connected, or fully connected, neural layers. The first `Dense` layer has 128 nodes (or neurons). The second (and last) layer returns a logits array with length of 10. Each node contains a score that indicates the current image belongs to one of the 10 classes.\n",
    "\n",
    "### Compile the model\n",
    "\n",
    "Before the model is ready for training, it needs a few more settings. These are added during the model's *compile* step:\n",
    "\n",
    "* *Loss function* —This measures how accurate the model is during training. You want to minimize this function to \"steer\" the model in the right direction.\n",
    "* *Optimizer* —This is how the model is updated based on the data it sees and its loss function.\n",
    "* *Metrics* —Used to monitor the training and testing steps. The following example uses *accuracy*, the fraction of the images that are correctly classified."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:58.958392Z",
     "iopub.status.busy": "2020-10-15T01:28:58.957188Z",
     "iopub.status.idle": "2020-10-15T01:28:58.965695Z",
     "shell.execute_reply": "2020-10-15T01:28:58.966131Z"
    },
    "id": "Lhan11blCaW7"
   },
   "outputs": [
    {
     "output_type": "error",
     "ename": "NameError",
     "evalue": "name 'model' is not defined",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-1-180c3339d833>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m model.compile(optimizer='adam',\n\u001b[0m\u001b[1;32m      2\u001b[0m               \u001b[0mloss\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlosses\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mSparseCategoricalCrossentropy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfrom_logits\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m               metrics=['accuracy'])\n",
      "\u001b[0;31mNameError\u001b[0m: name 'model' is not defined"
     ]
    }
   ],
   "source": [
    "model.compile(optimizer='adam',\n",
    "              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
    "              metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "qKF6uW-BCaW-"
   },
   "source": [
    "## Train the model\n",
    "\n",
    "Training the neural network model requires the following steps:\n",
    "\n",
    "1. Feed the training data to the model. In this example, the training data is in the `train_images` and `train_labels` arrays.\n",
    "2. The model learns to associate images and labels.\n",
    "3. You ask the model to make predictions about a test set—in this example, the `test_images` array.\n",
    "4. Verify that the predictions match the labels from the `test_labels` array.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Z4P4zIV7E28Z"
   },
   "source": [
    "### Feed the model\n",
    "\n",
    "To start training,  call the `model.fit` method—so called because it \"fits\" the model to the training data:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:28:58.972129Z",
     "iopub.status.busy": "2020-10-15T01:28:58.971103Z",
     "iopub.status.idle": "2020-10-15T01:29:28.207307Z",
     "shell.execute_reply": "2020-10-15T01:29:28.206660Z"
    },
    "id": "xvwvpA64CaW_"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "   1/1875 [..............................] - ETA: 1s - loss: 2.4084 - accuracy: 0.0938"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  35/1875 [..............................] - ETA: 2s - loss: 1.2894 - accuracy: 0.5857"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  70/1875 [>.............................] - ETA: 2s - loss: 1.0295 - accuracy: 0.6567"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 105/1875 [>.............................] - ETA: 2s - loss: 0.9114 - accuracy: 0.6923"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 139/1875 [=>............................] - ETA: 2s - loss: 0.8543 - accuracy: 0.7100"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 172/1875 [=>............................] - ETA: 2s - loss: 0.8011 - accuracy: 0.7271"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 206/1875 [==>...........................] - ETA: 2s - loss: 0.7711 - accuracy: 0.7363"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 241/1875 [==>...........................] - ETA: 2s - loss: 0.7394 - accuracy: 0.7478"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 275/1875 [===>..........................] - ETA: 2s - loss: 0.7107 - accuracy: 0.7570"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 310/1875 [===>..........................] - ETA: 2s - loss: 0.6957 - accuracy: 0.7614"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 344/1875 [====>.........................] - ETA: 2s - loss: 0.6861 - accuracy: 0.7656"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 378/1875 [=====>........................] - ETA: 2s - loss: 0.6702 - accuracy: 0.7718"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 413/1875 [=====>........................] - ETA: 2s - loss: 0.6596 - accuracy: 0.7754"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 448/1875 [======>.......................] - ETA: 2s - loss: 0.6446 - accuracy: 0.7797"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 482/1875 [======>.......................] - ETA: 2s - loss: 0.6360 - accuracy: 0.7827"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 516/1875 [=======>......................] - ETA: 2s - loss: 0.6252 - accuracy: 0.7859"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 551/1875 [=======>......................] - ETA: 1s - loss: 0.6171 - accuracy: 0.7881"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 586/1875 [========>.....................] - ETA: 1s - loss: 0.6083 - accuracy: 0.7912"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 621/1875 [========>.....................] - ETA: 1s - loss: 0.5997 - accuracy: 0.7943"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 654/1875 [=========>....................] - ETA: 1s - loss: 0.5937 - accuracy: 0.7961"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 687/1875 [=========>....................] - ETA: 1s - loss: 0.5877 - accuracy: 0.7980"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 721/1875 [==========>...................] - ETA: 1s - loss: 0.5804 - accuracy: 0.8001"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 756/1875 [===========>..................] - ETA: 1s - loss: 0.5729 - accuracy: 0.8027"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 790/1875 [===========>..................] - ETA: 1s - loss: 0.5697 - accuracy: 0.8042"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 824/1875 [============>.................] - ETA: 1s - loss: 0.5658 - accuracy: 0.8052"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 858/1875 [============>.................] - ETA: 1s - loss: 0.5599 - accuracy: 0.8074"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 891/1875 [=============>................] - ETA: 1s - loss: 0.5572 - accuracy: 0.8084"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 925/1875 [=============>................] - ETA: 1s - loss: 0.5529 - accuracy: 0.8095"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 958/1875 [==============>...............] - ETA: 1s - loss: 0.5502 - accuracy: 0.8102"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 992/1875 [==============>...............] - ETA: 1s - loss: 0.5482 - accuracy: 0.8106"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1027/1875 [===============>..............] - ETA: 1s - loss: 0.5456 - accuracy: 0.8113"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1061/1875 [===============>..............] - ETA: 1s - loss: 0.5418 - accuracy: 0.8126"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1094/1875 [================>.............] - ETA: 1s - loss: 0.5385 - accuracy: 0.8138"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1127/1875 [=================>............] - ETA: 1s - loss: 0.5346 - accuracy: 0.8148"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1161/1875 [=================>............] - ETA: 1s - loss: 0.5324 - accuracy: 0.8157"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1194/1875 [==================>...........] - ETA: 1s - loss: 0.5310 - accuracy: 0.8161"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1227/1875 [==================>...........] - ETA: 0s - loss: 0.5294 - accuracy: 0.8165"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1260/1875 [===================>..........] - ETA: 0s - loss: 0.5275 - accuracy: 0.8169"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1294/1875 [===================>..........] - ETA: 0s - loss: 0.5266 - accuracy: 0.8172"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1328/1875 [====================>.........] - ETA: 0s - loss: 0.5240 - accuracy: 0.8181"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1362/1875 [====================>.........] - ETA: 0s - loss: 0.5214 - accuracy: 0.8188"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1396/1875 [=====================>........] - ETA: 0s - loss: 0.5181 - accuracy: 0.8200"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1429/1875 [=====================>........] - ETA: 0s - loss: 0.5151 - accuracy: 0.8207"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1461/1875 [======================>.......] - ETA: 0s - loss: 0.5134 - accuracy: 0.8212"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1494/1875 [======================>.......] - ETA: 0s - loss: 0.5111 - accuracy: 0.8221"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1529/1875 [=======================>......] - ETA: 0s - loss: 0.5086 - accuracy: 0.8229"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1564/1875 [========================>.....] - ETA: 0s - loss: 0.5077 - accuracy: 0.8231"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1598/1875 [========================>.....] - ETA: 0s - loss: 0.5052 - accuracy: 0.8236"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1633/1875 [=========================>....] - ETA: 0s - loss: 0.5032 - accuracy: 0.8244"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1667/1875 [=========================>....] - ETA: 0s - loss: 0.5022 - accuracy: 0.8245"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1701/1875 [==========================>...] - ETA: 0s - loss: 0.5006 - accuracy: 0.8249"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1734/1875 [==========================>...] - ETA: 0s - loss: 0.4996 - accuracy: 0.8253"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1767/1875 [===========================>..] - ETA: 0s - loss: 0.4975 - accuracy: 0.8260"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1800/1875 [===========================>..] - ETA: 0s - loss: 0.4951 - accuracy: 0.8266"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1834/1875 [============================>.] - ETA: 0s - loss: 0.4932 - accuracy: 0.8274"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1867/1875 [============================>.] - ETA: 0s - loss: 0.4920 - accuracy: 0.8276"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1875/1875 [==============================] - 3s 1ms/step - loss: 0.4917 - accuracy: 0.8277\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 2/10\n",
      "\r",
      "   1/1875 [..............................] - ETA: 0s - loss: 0.5414 - accuracy: 0.8125"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  36/1875 [..............................] - ETA: 2s - loss: 0.3838 - accuracy: 0.8594"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  71/1875 [>.............................] - ETA: 2s - loss: 0.3885 - accuracy: 0.8596"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 104/1875 [>.............................] - ETA: 2s - loss: 0.3732 - accuracy: 0.8684"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 138/1875 [=>............................] - ETA: 2s - loss: 0.3872 - accuracy: 0.8614"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 171/1875 [=>............................] - ETA: 2s - loss: 0.3838 - accuracy: 0.8635"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 204/1875 [==>...........................] - ETA: 2s - loss: 0.3863 - accuracy: 0.8620"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 237/1875 [==>...........................] - ETA: 2s - loss: 0.3938 - accuracy: 0.8602"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 270/1875 [===>..........................] - ETA: 2s - loss: 0.3939 - accuracy: 0.8593"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 304/1875 [===>..........................] - ETA: 2s - loss: 0.3981 - accuracy: 0.8567"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 338/1875 [====>.........................] - ETA: 2s - loss: 0.3977 - accuracy: 0.8570"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 373/1875 [====>.........................] - ETA: 2s - loss: 0.3968 - accuracy: 0.8569"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 407/1875 [=====>........................] - ETA: 2s - loss: 0.3931 - accuracy: 0.8585"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 442/1875 [======>.......................] - ETA: 2s - loss: 0.3932 - accuracy: 0.8589"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 476/1875 [======>.......................] - ETA: 2s - loss: 0.3898 - accuracy: 0.8612"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 510/1875 [=======>......................] - ETA: 2s - loss: 0.3881 - accuracy: 0.8612"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 543/1875 [=======>......................] - ETA: 1s - loss: 0.3860 - accuracy: 0.8619"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 578/1875 [========>.....................] - ETA: 1s - loss: 0.3861 - accuracy: 0.8620"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 613/1875 [========>.....................] - ETA: 1s - loss: 0.3884 - accuracy: 0.8610"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 647/1875 [=========>....................] - ETA: 1s - loss: 0.3884 - accuracy: 0.8618"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 682/1875 [=========>....................] - ETA: 1s - loss: 0.3866 - accuracy: 0.8631"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 717/1875 [==========>...................] - ETA: 1s - loss: 0.3859 - accuracy: 0.8628"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 752/1875 [===========>..................] - ETA: 1s - loss: 0.3865 - accuracy: 0.8623"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 786/1875 [===========>..................] - ETA: 1s - loss: 0.3855 - accuracy: 0.8631"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 820/1875 [============>.................] - ETA: 1s - loss: 0.3859 - accuracy: 0.8629"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 854/1875 [============>.................] - ETA: 1s - loss: 0.3850 - accuracy: 0.8630"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 889/1875 [=============>................] - ETA: 1s - loss: 0.3850 - accuracy: 0.8629"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 924/1875 [=============>................] - ETA: 1s - loss: 0.3838 - accuracy: 0.8634"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 959/1875 [==============>...............] - ETA: 1s - loss: 0.3829 - accuracy: 0.8636"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 994/1875 [==============>...............] - ETA: 1s - loss: 0.3830 - accuracy: 0.8640"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1027/1875 [===============>..............] - ETA: 1s - loss: 0.3818 - accuracy: 0.8643"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1061/1875 [===============>..............] - ETA: 1s - loss: 0.3808 - accuracy: 0.8646"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1095/1875 [================>.............] - ETA: 1s - loss: 0.3799 - accuracy: 0.8649"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1129/1875 [=================>............] - ETA: 1s - loss: 0.3795 - accuracy: 0.8649"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1162/1875 [=================>............] - ETA: 1s - loss: 0.3784 - accuracy: 0.8655"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1195/1875 [==================>...........] - ETA: 1s - loss: 0.3787 - accuracy: 0.8652"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1228/1875 [==================>...........] - ETA: 0s - loss: 0.3777 - accuracy: 0.8656"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1263/1875 [===================>..........] - ETA: 0s - loss: 0.3776 - accuracy: 0.8655"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1298/1875 [===================>..........] - ETA: 0s - loss: 0.3782 - accuracy: 0.8654"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1331/1875 [====================>.........] - ETA: 0s - loss: 0.3785 - accuracy: 0.8649"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1365/1875 [====================>.........] - ETA: 0s - loss: 0.3780 - accuracy: 0.8652"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1398/1875 [=====================>........] - ETA: 0s - loss: 0.3774 - accuracy: 0.8656"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1432/1875 [=====================>........] - ETA: 0s - loss: 0.3769 - accuracy: 0.8656"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1466/1875 [======================>.......] - ETA: 0s - loss: 0.3763 - accuracy: 0.8656"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1499/1875 [======================>.......] - ETA: 0s - loss: 0.3753 - accuracy: 0.8658"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1534/1875 [=======================>......] - ETA: 0s - loss: 0.3749 - accuracy: 0.8659"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1568/1875 [========================>.....] - ETA: 0s - loss: 0.3743 - accuracy: 0.8660"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1602/1875 [========================>.....] - ETA: 0s - loss: 0.3742 - accuracy: 0.8661"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1635/1875 [=========================>....] - ETA: 0s - loss: 0.3741 - accuracy: 0.8662"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1669/1875 [=========================>....] - ETA: 0s - loss: 0.3742 - accuracy: 0.8662"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1702/1875 [==========================>...] - ETA: 0s - loss: 0.3731 - accuracy: 0.8664"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1735/1875 [==========================>...] - ETA: 0s - loss: 0.3725 - accuracy: 0.8666"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1768/1875 [===========================>..] - ETA: 0s - loss: 0.3727 - accuracy: 0.8664"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1802/1875 [===========================>..] - ETA: 0s - loss: 0.3720 - accuracy: 0.8666"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1836/1875 [============================>.] - ETA: 0s - loss: 0.3709 - accuracy: 0.8670"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1871/1875 [============================>.] - ETA: 0s - loss: 0.3702 - accuracy: 0.8674"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1875/1875 [==============================] - 3s 1ms/step - loss: 0.3702 - accuracy: 0.8674\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 3/10\n",
      "\r",
      "   1/1875 [..............................] - ETA: 0s - loss: 0.2502 - accuracy: 0.8750"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  36/1875 [..............................] - ETA: 2s - loss: 0.3424 - accuracy: 0.8707"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  70/1875 [>.............................] - ETA: 2s - loss: 0.3471 - accuracy: 0.8728"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 104/1875 [>.............................] - ETA: 2s - loss: 0.3477 - accuracy: 0.8669"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 138/1875 [=>............................] - ETA: 2s - loss: 0.3407 - accuracy: 0.8712"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 171/1875 [=>............................] - ETA: 2s - loss: 0.3464 - accuracy: 0.8704"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 204/1875 [==>...........................] - ETA: 2s - loss: 0.3464 - accuracy: 0.8699"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 237/1875 [==>...........................] - ETA: 2s - loss: 0.3460 - accuracy: 0.8700"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 271/1875 [===>..........................] - ETA: 2s - loss: 0.3421 - accuracy: 0.8717"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 305/1875 [===>..........................] - ETA: 2s - loss: 0.3433 - accuracy: 0.8717"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 338/1875 [====>.........................] - ETA: 2s - loss: 0.3423 - accuracy: 0.8726"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 371/1875 [====>.........................] - ETA: 2s - loss: 0.3406 - accuracy: 0.8749"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 406/1875 [=====>........................] - ETA: 2s - loss: 0.3423 - accuracy: 0.8740"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 440/1875 [======>.......................] - ETA: 2s - loss: 0.3410 - accuracy: 0.8746"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 473/1875 [======>.......................] - ETA: 2s - loss: 0.3407 - accuracy: 0.8747"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 507/1875 [=======>......................] - ETA: 2s - loss: 0.3417 - accuracy: 0.8743"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 540/1875 [=======>......................] - ETA: 2s - loss: 0.3430 - accuracy: 0.8737"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 573/1875 [========>.....................] - ETA: 1s - loss: 0.3439 - accuracy: 0.8741"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 606/1875 [========>.....................] - ETA: 1s - loss: 0.3424 - accuracy: 0.8748"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 639/1875 [=========>....................] - ETA: 1s - loss: 0.3438 - accuracy: 0.8737"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 673/1875 [=========>....................] - ETA: 1s - loss: 0.3416 - accuracy: 0.8742"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 708/1875 [==========>...................] - ETA: 1s - loss: 0.3425 - accuracy: 0.8739"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 743/1875 [==========>...................] - ETA: 1s - loss: 0.3424 - accuracy: 0.8746"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 777/1875 [===========>..................] - ETA: 1s - loss: 0.3423 - accuracy: 0.8754"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 811/1875 [===========>..................] - ETA: 1s - loss: 0.3419 - accuracy: 0.8760"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 845/1875 [============>.................] - ETA: 1s - loss: 0.3403 - accuracy: 0.8763"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 879/1875 [=============>................] - ETA: 1s - loss: 0.3401 - accuracy: 0.8764"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 913/1875 [=============>................] - ETA: 1s - loss: 0.3407 - accuracy: 0.8762"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 947/1875 [==============>...............] - ETA: 1s - loss: 0.3408 - accuracy: 0.8760"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 981/1875 [==============>...............] - ETA: 1s - loss: 0.3408 - accuracy: 0.8757"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1014/1875 [===============>..............] - ETA: 1s - loss: 0.3402 - accuracy: 0.8754"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1048/1875 [===============>..............] - ETA: 1s - loss: 0.3402 - accuracy: 0.8754"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1081/1875 [================>.............] - ETA: 1s - loss: 0.3405 - accuracy: 0.8755"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1115/1875 [================>.............] - ETA: 1s - loss: 0.3401 - accuracy: 0.8757"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1149/1875 [=================>............] - ETA: 1s - loss: 0.3395 - accuracy: 0.8761"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1181/1875 [=================>............] - ETA: 1s - loss: 0.3372 - accuracy: 0.8771"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1214/1875 [==================>...........] - ETA: 0s - loss: 0.3362 - accuracy: 0.8777"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1247/1875 [==================>...........] - ETA: 0s - loss: 0.3358 - accuracy: 0.8778"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1281/1875 [===================>..........] - ETA: 0s - loss: 0.3353 - accuracy: 0.8779"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1316/1875 [====================>.........] - ETA: 0s - loss: 0.3351 - accuracy: 0.8778"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1350/1875 [====================>.........] - ETA: 0s - loss: 0.3348 - accuracy: 0.8780"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1384/1875 [=====================>........] - ETA: 0s - loss: 0.3356 - accuracy: 0.8775"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1419/1875 [=====================>........] - ETA: 0s - loss: 0.3343 - accuracy: 0.8783"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1454/1875 [======================>.......] - ETA: 0s - loss: 0.3347 - accuracy: 0.8782"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1488/1875 [======================>.......] - ETA: 0s - loss: 0.3352 - accuracy: 0.8780"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1521/1875 [=======================>......] - ETA: 0s - loss: 0.3349 - accuracy: 0.8781"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1554/1875 [=======================>......] - ETA: 0s - loss: 0.3350 - accuracy: 0.8782"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1588/1875 [========================>.....] - ETA: 0s - loss: 0.3355 - accuracy: 0.8781"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1622/1875 [========================>.....] - ETA: 0s - loss: 0.3342 - accuracy: 0.8787"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1656/1875 [=========================>....] - ETA: 0s - loss: 0.3341 - accuracy: 0.8788"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1689/1875 [==========================>...] - ETA: 0s - loss: 0.3343 - accuracy: 0.8787"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1722/1875 [==========================>...] - ETA: 0s - loss: 0.3338 - accuracy: 0.8788"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1756/1875 [===========================>..] - ETA: 0s - loss: 0.3338 - accuracy: 0.8787"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1789/1875 [===========================>..] - ETA: 0s - loss: 0.3336 - accuracy: 0.8789"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1823/1875 [============================>.] - ETA: 0s - loss: 0.3334 - accuracy: 0.8790"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1856/1875 [============================>.] - ETA: 0s - loss: 0.3331 - accuracy: 0.8792"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1875/1875 [==============================] - 3s 2ms/step - loss: 0.3328 - accuracy: 0.8793\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 4/10\n",
      "\r",
      "   1/1875 [..............................] - ETA: 0s - loss: 0.3749 - accuracy: 0.8438"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  34/1875 [..............................] - ETA: 2s - loss: 0.3157 - accuracy: 0.8805"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  67/1875 [>.............................] - ETA: 2s - loss: 0.3085 - accuracy: 0.8829"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 101/1875 [>.............................] - ETA: 2s - loss: 0.3201 - accuracy: 0.8806"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 135/1875 [=>............................] - ETA: 2s - loss: 0.3114 - accuracy: 0.8840"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 169/1875 [=>............................] - ETA: 2s - loss: 0.3178 - accuracy: 0.8828"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 202/1875 [==>...........................] - ETA: 2s - loss: 0.3194 - accuracy: 0.8815"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 236/1875 [==>...........................] - ETA: 2s - loss: 0.3118 - accuracy: 0.8856"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 270/1875 [===>..........................] - ETA: 2s - loss: 0.3136 - accuracy: 0.8850"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 305/1875 [===>..........................] - ETA: 2s - loss: 0.3164 - accuracy: 0.8840"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 339/1875 [====>.........................] - ETA: 2s - loss: 0.3193 - accuracy: 0.8815"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 371/1875 [====>.........................] - ETA: 2s - loss: 0.3166 - accuracy: 0.8831"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 404/1875 [=====>........................] - ETA: 2s - loss: 0.3180 - accuracy: 0.8830"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 437/1875 [=====>........................] - ETA: 2s - loss: 0.3171 - accuracy: 0.8840"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 470/1875 [======>.......................] - ETA: 2s - loss: 0.3177 - accuracy: 0.8849"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 503/1875 [=======>......................] - ETA: 2s - loss: 0.3154 - accuracy: 0.8861"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 539/1875 [=======>......................] - ETA: 2s - loss: 0.3141 - accuracy: 0.8867"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 574/1875 [========>.....................] - ETA: 1s - loss: 0.3116 - accuracy: 0.8877"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 608/1875 [========>.....................] - ETA: 1s - loss: 0.3131 - accuracy: 0.8871"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 641/1875 [=========>....................] - ETA: 1s - loss: 0.3110 - accuracy: 0.8875"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 676/1875 [=========>....................] - ETA: 1s - loss: 0.3107 - accuracy: 0.8878"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 712/1875 [==========>...................] - ETA: 1s - loss: 0.3106 - accuracy: 0.8871"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 746/1875 [==========>...................] - ETA: 1s - loss: 0.3115 - accuracy: 0.8866"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 780/1875 [===========>..................] - ETA: 1s - loss: 0.3113 - accuracy: 0.8868"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 814/1875 [============>.................] - ETA: 1s - loss: 0.3128 - accuracy: 0.8859"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 848/1875 [============>.................] - ETA: 1s - loss: 0.3127 - accuracy: 0.8860"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 882/1875 [=============>................] - ETA: 1s - loss: 0.3120 - accuracy: 0.8859"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 916/1875 [=============>................] - ETA: 1s - loss: 0.3112 - accuracy: 0.8861"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 950/1875 [==============>...............] - ETA: 1s - loss: 0.3115 - accuracy: 0.8862"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 984/1875 [==============>...............] - ETA: 1s - loss: 0.3136 - accuracy: 0.8854"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1019/1875 [===============>..............] - ETA: 1s - loss: 0.3151 - accuracy: 0.8847"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1054/1875 [===============>..............] - ETA: 1s - loss: 0.3140 - accuracy: 0.8851"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1090/1875 [================>.............] - ETA: 1s - loss: 0.3138 - accuracy: 0.8849"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1125/1875 [=================>............] - ETA: 1s - loss: 0.3127 - accuracy: 0.8854"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1159/1875 [=================>............] - ETA: 1s - loss: 0.3125 - accuracy: 0.8857"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1194/1875 [==================>...........] - ETA: 1s - loss: 0.3115 - accuracy: 0.8858"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1227/1875 [==================>...........] - ETA: 0s - loss: 0.3113 - accuracy: 0.8859"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1262/1875 [===================>..........] - ETA: 0s - loss: 0.3122 - accuracy: 0.8856"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1298/1875 [===================>..........] - ETA: 0s - loss: 0.3121 - accuracy: 0.8857"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1332/1875 [====================>.........] - ETA: 0s - loss: 0.3129 - accuracy: 0.8856"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1366/1875 [====================>.........] - ETA: 0s - loss: 0.3127 - accuracy: 0.8855"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1401/1875 [=====================>........] - ETA: 0s - loss: 0.3114 - accuracy: 0.8860"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1436/1875 [=====================>........] - ETA: 0s - loss: 0.3112 - accuracy: 0.8862"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1471/1875 [======================>.......] - ETA: 0s - loss: 0.3119 - accuracy: 0.8858"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1506/1875 [=======================>......] - ETA: 0s - loss: 0.3122 - accuracy: 0.8858"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1541/1875 [=======================>......] - ETA: 0s - loss: 0.3121 - accuracy: 0.8858"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1576/1875 [========================>.....] - ETA: 0s - loss: 0.3119 - accuracy: 0.8858"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1611/1875 [========================>.....] - ETA: 0s - loss: 0.3116 - accuracy: 0.8858"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1645/1875 [=========================>....] - ETA: 0s - loss: 0.3112 - accuracy: 0.8859"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1679/1875 [=========================>....] - ETA: 0s - loss: 0.3113 - accuracy: 0.8857"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1713/1875 [==========================>...] - ETA: 0s - loss: 0.3102 - accuracy: 0.8859"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1748/1875 [==========================>...] - ETA: 0s - loss: 0.3095 - accuracy: 0.8863"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1782/1875 [===========================>..] - ETA: 0s - loss: 0.3104 - accuracy: 0.8857"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1816/1875 [============================>.] - ETA: 0s - loss: 0.3107 - accuracy: 0.8855"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1850/1875 [============================>.] - ETA: 0s - loss: 0.3109 - accuracy: 0.8857"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1875/1875 [==============================] - 3s 1ms/step - loss: 0.3106 - accuracy: 0.8859\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 5/10\n",
      "\r",
      "   1/1875 [..............................] - ETA: 0s - loss: 0.1569 - accuracy: 0.9375"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  35/1875 [..............................] - ETA: 2s - loss: 0.2726 - accuracy: 0.9054"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  69/1875 [>.............................] - ETA: 2s - loss: 0.2785 - accuracy: 0.8976"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 104/1875 [>.............................] - ETA: 2s - loss: 0.2844 - accuracy: 0.8957"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 139/1875 [=>............................] - ETA: 2s - loss: 0.2886 - accuracy: 0.8939"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 174/1875 [=>............................] - ETA: 2s - loss: 0.2917 - accuracy: 0.8935"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 209/1875 [==>...........................] - ETA: 2s - loss: 0.2910 - accuracy: 0.8934"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 243/1875 [==>...........................] - ETA: 2s - loss: 0.2873 - accuracy: 0.8939"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 278/1875 [===>..........................] - ETA: 2s - loss: 0.2902 - accuracy: 0.8929"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 313/1875 [====>.........................] - ETA: 2s - loss: 0.2875 - accuracy: 0.8937"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 347/1875 [====>.........................] - ETA: 2s - loss: 0.2881 - accuracy: 0.8935"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 382/1875 [=====>........................] - ETA: 2s - loss: 0.2890 - accuracy: 0.8934"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 416/1875 [=====>........................] - ETA: 2s - loss: 0.2890 - accuracy: 0.8928"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 450/1875 [======>.......................] - ETA: 2s - loss: 0.2889 - accuracy: 0.8922"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 484/1875 [======>.......................] - ETA: 2s - loss: 0.2912 - accuracy: 0.8917"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 518/1875 [=======>......................] - ETA: 1s - loss: 0.2919 - accuracy: 0.8917"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 553/1875 [=======>......................] - ETA: 1s - loss: 0.2935 - accuracy: 0.8913"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 587/1875 [========>.....................] - ETA: 1s - loss: 0.2932 - accuracy: 0.8912"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 622/1875 [========>.....................] - ETA: 1s - loss: 0.2945 - accuracy: 0.8910"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 655/1875 [=========>....................] - ETA: 1s - loss: 0.2949 - accuracy: 0.8916"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 690/1875 [==========>...................] - ETA: 1s - loss: 0.2952 - accuracy: 0.8914"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 725/1875 [==========>...................] - ETA: 1s - loss: 0.2943 - accuracy: 0.8918"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 760/1875 [===========>..................] - ETA: 1s - loss: 0.2937 - accuracy: 0.8917"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 794/1875 [===========>..................] - ETA: 1s - loss: 0.2930 - accuracy: 0.8920"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 828/1875 [============>.................] - ETA: 1s - loss: 0.2944 - accuracy: 0.8913"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 861/1875 [============>.................] - ETA: 1s - loss: 0.2922 - accuracy: 0.8921"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 896/1875 [=============>................] - ETA: 1s - loss: 0.2932 - accuracy: 0.8917"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 930/1875 [=============>................] - ETA: 1s - loss: 0.2928 - accuracy: 0.8917"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 963/1875 [==============>...............] - ETA: 1s - loss: 0.2922 - accuracy: 0.8917"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 998/1875 [==============>...............] - ETA: 1s - loss: 0.2924 - accuracy: 0.8917"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1033/1875 [===============>..............] - ETA: 1s - loss: 0.2920 - accuracy: 0.8919"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1068/1875 [================>.............] - ETA: 1s - loss: 0.2917 - accuracy: 0.8921"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1102/1875 [================>.............] - ETA: 1s - loss: 0.2929 - accuracy: 0.8916"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1136/1875 [=================>............] - ETA: 1s - loss: 0.2930 - accuracy: 0.8916"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1171/1875 [=================>............] - ETA: 1s - loss: 0.2923 - accuracy: 0.8918"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1206/1875 [==================>...........] - ETA: 0s - loss: 0.2924 - accuracy: 0.8921"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1242/1875 [==================>...........] - ETA: 0s - loss: 0.2919 - accuracy: 0.8927"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1277/1875 [===================>..........] - ETA: 0s - loss: 0.2919 - accuracy: 0.8924"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1312/1875 [===================>..........] - ETA: 0s - loss: 0.2910 - accuracy: 0.8929"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1348/1875 [====================>.........] - ETA: 0s - loss: 0.2917 - accuracy: 0.8926"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1384/1875 [=====================>........] - ETA: 0s - loss: 0.2921 - accuracy: 0.8929"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1418/1875 [=====================>........] - ETA: 0s - loss: 0.2920 - accuracy: 0.8928"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1454/1875 [======================>.......] - ETA: 0s - loss: 0.2924 - accuracy: 0.8927"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1489/1875 [======================>.......] - ETA: 0s - loss: 0.2922 - accuracy: 0.8927"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1524/1875 [=======================>......] - ETA: 0s - loss: 0.2915 - accuracy: 0.8927"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1559/1875 [=======================>......] - ETA: 0s - loss: 0.2917 - accuracy: 0.8928"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1594/1875 [========================>.....] - ETA: 0s - loss: 0.2910 - accuracy: 0.8930"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1627/1875 [=========================>....] - ETA: 0s - loss: 0.2906 - accuracy: 0.8931"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1661/1875 [=========================>....] - ETA: 0s - loss: 0.2901 - accuracy: 0.8931"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1696/1875 [==========================>...] - ETA: 0s - loss: 0.2900 - accuracy: 0.8931"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1731/1875 [==========================>...] - ETA: 0s - loss: 0.2899 - accuracy: 0.8933"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1766/1875 [===========================>..] - ETA: 0s - loss: 0.2908 - accuracy: 0.8929"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1800/1875 [===========================>..] - ETA: 0s - loss: 0.2913 - accuracy: 0.8926"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1835/1875 [============================>.] - ETA: 0s - loss: 0.2916 - accuracy: 0.8926"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1871/1875 [============================>.] - ETA: 0s - loss: 0.2916 - accuracy: 0.8926"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1875/1875 [==============================] - 3s 1ms/step - loss: 0.2915 - accuracy: 0.8927\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 6/10\n",
      "\r",
      "   1/1875 [..............................] - ETA: 0s - loss: 0.3187 - accuracy: 0.8750"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  37/1875 [..............................] - ETA: 2s - loss: 0.2586 - accuracy: 0.8919"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  73/1875 [>.............................] - ETA: 2s - loss: 0.2510 - accuracy: 0.8951"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 109/1875 [>.............................] - ETA: 2s - loss: 0.2485 - accuracy: 0.8994"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 145/1875 [=>............................] - ETA: 2s - loss: 0.2497 - accuracy: 0.8987"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 181/1875 [=>............................] - ETA: 2s - loss: 0.2594 - accuracy: 0.8968"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 216/1875 [==>...........................] - ETA: 2s - loss: 0.2650 - accuracy: 0.8963"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 252/1875 [===>..........................] - ETA: 2s - loss: 0.2675 - accuracy: 0.8956"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 288/1875 [===>..........................] - ETA: 2s - loss: 0.2623 - accuracy: 0.8988"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 322/1875 [====>.........................] - ETA: 2s - loss: 0.2627 - accuracy: 0.8998"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 355/1875 [====>.........................] - ETA: 2s - loss: 0.2654 - accuracy: 0.8989"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 390/1875 [=====>........................] - ETA: 2s - loss: 0.2637 - accuracy: 0.8996"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 423/1875 [=====>........................] - ETA: 2s - loss: 0.2653 - accuracy: 0.8998"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 457/1875 [======>.......................] - ETA: 2s - loss: 0.2666 - accuracy: 0.9001"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 491/1875 [======>.......................] - ETA: 2s - loss: 0.2674 - accuracy: 0.9001"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 525/1875 [=======>......................] - ETA: 1s - loss: 0.2676 - accuracy: 0.8992"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 558/1875 [=======>......................] - ETA: 1s - loss: 0.2689 - accuracy: 0.8981"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 591/1875 [========>.....................] - ETA: 1s - loss: 0.2705 - accuracy: 0.8983"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 625/1875 [=========>....................] - ETA: 1s - loss: 0.2701 - accuracy: 0.8984"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 659/1875 [=========>....................] - ETA: 1s - loss: 0.2713 - accuracy: 0.8981"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 692/1875 [==========>...................] - ETA: 1s - loss: 0.2714 - accuracy: 0.8986"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 726/1875 [==========>...................] - ETA: 1s - loss: 0.2701 - accuracy: 0.8993"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 761/1875 [===========>..................] - ETA: 1s - loss: 0.2714 - accuracy: 0.8987"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 795/1875 [===========>..................] - ETA: 1s - loss: 0.2725 - accuracy: 0.8982"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 829/1875 [============>.................] - ETA: 1s - loss: 0.2730 - accuracy: 0.8978"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 864/1875 [============>.................] - ETA: 1s - loss: 0.2745 - accuracy: 0.8971"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 897/1875 [=============>................] - ETA: 1s - loss: 0.2749 - accuracy: 0.8971"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 933/1875 [=============>................] - ETA: 1s - loss: 0.2750 - accuracy: 0.8971"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 967/1875 [==============>...............] - ETA: 1s - loss: 0.2764 - accuracy: 0.8964"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1000/1875 [===============>..............] - ETA: 1s - loss: 0.2776 - accuracy: 0.8966"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1033/1875 [===============>..............] - ETA: 1s - loss: 0.2781 - accuracy: 0.8965"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1066/1875 [================>.............] - ETA: 1s - loss: 0.2785 - accuracy: 0.8962"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1100/1875 [================>.............] - ETA: 1s - loss: 0.2784 - accuracy: 0.8960"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1132/1875 [=================>............] - ETA: 1s - loss: 0.2789 - accuracy: 0.8958"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1165/1875 [=================>............] - ETA: 1s - loss: 0.2790 - accuracy: 0.8959"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1199/1875 [==================>...........] - ETA: 1s - loss: 0.2783 - accuracy: 0.8963"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1233/1875 [==================>...........] - ETA: 0s - loss: 0.2781 - accuracy: 0.8965"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1267/1875 [===================>..........] - ETA: 0s - loss: 0.2777 - accuracy: 0.8966"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1301/1875 [===================>..........] - ETA: 0s - loss: 0.2782 - accuracy: 0.8963"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1334/1875 [====================>.........] - ETA: 0s - loss: 0.2772 - accuracy: 0.8965"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1368/1875 [====================>.........] - ETA: 0s - loss: 0.2770 - accuracy: 0.8965"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1401/1875 [=====================>........] - ETA: 0s - loss: 0.2774 - accuracy: 0.8964"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1435/1875 [=====================>........] - ETA: 0s - loss: 0.2776 - accuracy: 0.8961"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1469/1875 [======================>.......] - ETA: 0s - loss: 0.2774 - accuracy: 0.8962"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1502/1875 [=======================>......] - ETA: 0s - loss: 0.2769 - accuracy: 0.8965"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1536/1875 [=======================>......] - ETA: 0s - loss: 0.2774 - accuracy: 0.8964"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1570/1875 [========================>.....] - ETA: 0s - loss: 0.2773 - accuracy: 0.8964"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1605/1875 [========================>.....] - ETA: 0s - loss: 0.2776 - accuracy: 0.8964"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1641/1875 [=========================>....] - ETA: 0s - loss: 0.2770 - accuracy: 0.8965"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1677/1875 [=========================>....] - ETA: 0s - loss: 0.2770 - accuracy: 0.8966"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1711/1875 [==========================>...] - ETA: 0s - loss: 0.2771 - accuracy: 0.8965"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1744/1875 [==========================>...] - ETA: 0s - loss: 0.2770 - accuracy: 0.8967"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1777/1875 [===========================>..] - ETA: 0s - loss: 0.2772 - accuracy: 0.8968"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1810/1875 [===========================>..] - ETA: 0s - loss: 0.2772 - accuracy: 0.8966"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1844/1875 [============================>.] - ETA: 0s - loss: 0.2771 - accuracy: 0.8967"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1875/1875 [==============================] - 3s 1ms/step - loss: 0.2771 - accuracy: 0.8968\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 7/10\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\r",
      "   1/1875 [..............................] - ETA: 0s - loss: 0.3847 - accuracy: 0.8125"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  35/1875 [..............................] - ETA: 2s - loss: 0.2473 - accuracy: 0.9062"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  68/1875 [>.............................] - ETA: 2s - loss: 0.2538 - accuracy: 0.9067"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 102/1875 [>.............................] - ETA: 2s - loss: 0.2578 - accuracy: 0.9056"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 135/1875 [=>............................] - ETA: 2s - loss: 0.2717 - accuracy: 0.8993"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 169/1875 [=>............................] - ETA: 2s - loss: 0.2730 - accuracy: 0.9003"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 205/1875 [==>...........................] - ETA: 2s - loss: 0.2718 - accuracy: 0.9011"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 238/1875 [==>...........................] - ETA: 2s - loss: 0.2757 - accuracy: 0.8986"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 273/1875 [===>..........................] - ETA: 2s - loss: 0.2740 - accuracy: 0.8981"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 307/1875 [===>..........................] - ETA: 2s - loss: 0.2713 - accuracy: 0.8980"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 341/1875 [====>.........................] - ETA: 2s - loss: 0.2716 - accuracy: 0.8975"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 375/1875 [=====>........................] - ETA: 2s - loss: 0.2721 - accuracy: 0.8975"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 409/1875 [=====>........................] - ETA: 2s - loss: 0.2713 - accuracy: 0.8973"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 442/1875 [======>.......................] - ETA: 2s - loss: 0.2736 - accuracy: 0.8968"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 476/1875 [======>.......................] - ETA: 2s - loss: 0.2737 - accuracy: 0.8967"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 509/1875 [=======>......................] - ETA: 2s - loss: 0.2733 - accuracy: 0.8972"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 543/1875 [=======>......................] - ETA: 1s - loss: 0.2716 - accuracy: 0.8978"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 578/1875 [========>.....................] - ETA: 1s - loss: 0.2712 - accuracy: 0.8982"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 613/1875 [========>.....................] - ETA: 1s - loss: 0.2698 - accuracy: 0.8990"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 648/1875 [=========>....................] - ETA: 1s - loss: 0.2688 - accuracy: 0.8992"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 681/1875 [=========>....................] - ETA: 1s - loss: 0.2692 - accuracy: 0.8990"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 715/1875 [==========>...................] - ETA: 1s - loss: 0.2684 - accuracy: 0.8992"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 749/1875 [==========>...................] - ETA: 1s - loss: 0.2683 - accuracy: 0.8993"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 783/1875 [===========>..................] - ETA: 1s - loss: 0.2686 - accuracy: 0.8992"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 817/1875 [============>.................] - ETA: 1s - loss: 0.2680 - accuracy: 0.8997"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 852/1875 [============>.................] - ETA: 1s - loss: 0.2702 - accuracy: 0.8993"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 885/1875 [=============>................] - ETA: 1s - loss: 0.2709 - accuracy: 0.8993"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 920/1875 [=============>................] - ETA: 1s - loss: 0.2696 - accuracy: 0.8999"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 954/1875 [==============>...............] - ETA: 1s - loss: 0.2692 - accuracy: 0.9001"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 988/1875 [==============>...............] - ETA: 1s - loss: 0.2695 - accuracy: 0.9001"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1022/1875 [===============>..............] - ETA: 1s - loss: 0.2696 - accuracy: 0.9000"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1056/1875 [===============>..............] - ETA: 1s - loss: 0.2691 - accuracy: 0.9002"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1090/1875 [================>.............] - ETA: 1s - loss: 0.2687 - accuracy: 0.9002"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1124/1875 [================>.............] - ETA: 1s - loss: 0.2678 - accuracy: 0.9006"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1159/1875 [=================>............] - ETA: 1s - loss: 0.2672 - accuracy: 0.9008"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1193/1875 [==================>...........] - ETA: 1s - loss: 0.2671 - accuracy: 0.9006"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1227/1875 [==================>...........] - ETA: 0s - loss: 0.2664 - accuracy: 0.9007"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1261/1875 [===================>..........] - ETA: 0s - loss: 0.2669 - accuracy: 0.9003"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1296/1875 [===================>..........] - ETA: 0s - loss: 0.2666 - accuracy: 0.9006"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1330/1875 [====================>.........] - ETA: 0s - loss: 0.2664 - accuracy: 0.9006"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1364/1875 [====================>.........] - ETA: 0s - loss: 0.2671 - accuracy: 0.9006"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1398/1875 [=====================>........] - ETA: 0s - loss: 0.2670 - accuracy: 0.9006"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1432/1875 [=====================>........] - ETA: 0s - loss: 0.2672 - accuracy: 0.9004"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1466/1875 [======================>.......] - ETA: 0s - loss: 0.2674 - accuracy: 0.9002"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1500/1875 [=======================>......] - ETA: 0s - loss: 0.2671 - accuracy: 0.9003"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1534/1875 [=======================>......] - ETA: 0s - loss: 0.2673 - accuracy: 0.9002"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1568/1875 [========================>.....] - ETA: 0s - loss: 0.2670 - accuracy: 0.9003"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1603/1875 [========================>.....] - ETA: 0s - loss: 0.2670 - accuracy: 0.9002"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1636/1875 [=========================>....] - ETA: 0s - loss: 0.2666 - accuracy: 0.9003"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1670/1875 [=========================>....] - ETA: 0s - loss: 0.2668 - accuracy: 0.9005"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1704/1875 [==========================>...] - ETA: 0s - loss: 0.2662 - accuracy: 0.9006"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1738/1875 [==========================>...] - ETA: 0s - loss: 0.2673 - accuracy: 0.9002"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1773/1875 [===========================>..] - ETA: 0s - loss: 0.2673 - accuracy: 0.9005"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1808/1875 [===========================>..] - ETA: 0s - loss: 0.2675 - accuracy: 0.9004"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1842/1875 [============================>.] - ETA: 0s - loss: 0.2668 - accuracy: 0.9007"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1875/1875 [==============================] - 3s 1ms/step - loss: 0.2666 - accuracy: 0.9008\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 8/10\n",
      "\r",
      "   1/1875 [..............................] - ETA: 0s - loss: 0.2344 - accuracy: 0.9375"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  35/1875 [..............................] - ETA: 2s - loss: 0.2431 - accuracy: 0.9098"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  69/1875 [>.............................] - ETA: 2s - loss: 0.2431 - accuracy: 0.9076"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 103/1875 [>.............................] - ETA: 2s - loss: 0.2539 - accuracy: 0.9066"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 136/1875 [=>............................] - ETA: 2s - loss: 0.2493 - accuracy: 0.9079"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 170/1875 [=>............................] - ETA: 2s - loss: 0.2413 - accuracy: 0.9108"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 204/1875 [==>...........................] - ETA: 2s - loss: 0.2409 - accuracy: 0.9116"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 237/1875 [==>...........................] - ETA: 2s - loss: 0.2430 - accuracy: 0.9103"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 270/1875 [===>..........................] - ETA: 2s - loss: 0.2435 - accuracy: 0.9094"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 304/1875 [===>..........................] - ETA: 2s - loss: 0.2459 - accuracy: 0.9093"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 339/1875 [====>.........................] - ETA: 2s - loss: 0.2465 - accuracy: 0.9095"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 374/1875 [====>.........................] - ETA: 2s - loss: 0.2492 - accuracy: 0.9079"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 408/1875 [=====>........................] - ETA: 2s - loss: 0.2485 - accuracy: 0.9081"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 441/1875 [======>.......................] - ETA: 2s - loss: 0.2525 - accuracy: 0.9073"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 475/1875 [======>.......................] - ETA: 2s - loss: 0.2537 - accuracy: 0.9068"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 510/1875 [=======>......................] - ETA: 2s - loss: 0.2517 - accuracy: 0.9078"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 544/1875 [=======>......................] - ETA: 1s - loss: 0.2505 - accuracy: 0.9082"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 578/1875 [========>.....................] - ETA: 1s - loss: 0.2499 - accuracy: 0.9085"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 612/1875 [========>.....................] - ETA: 1s - loss: 0.2534 - accuracy: 0.9073"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 646/1875 [=========>....................] - ETA: 1s - loss: 0.2542 - accuracy: 0.9066"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 680/1875 [=========>....................] - ETA: 1s - loss: 0.2555 - accuracy: 0.9060"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 714/1875 [==========>...................] - ETA: 1s - loss: 0.2547 - accuracy: 0.9060"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 748/1875 [==========>...................] - ETA: 1s - loss: 0.2559 - accuracy: 0.9055"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 782/1875 [===========>..................] - ETA: 1s - loss: 0.2567 - accuracy: 0.9052"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 815/1875 [============>.................] - ETA: 1s - loss: 0.2565 - accuracy: 0.9049"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 850/1875 [============>.................] - ETA: 1s - loss: 0.2556 - accuracy: 0.9059"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 884/1875 [=============>................] - ETA: 1s - loss: 0.2550 - accuracy: 0.9061"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 917/1875 [=============>................] - ETA: 1s - loss: 0.2555 - accuracy: 0.9055"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 950/1875 [==============>...............] - ETA: 1s - loss: 0.2544 - accuracy: 0.9059"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 985/1875 [==============>...............] - ETA: 1s - loss: 0.2533 - accuracy: 0.9063"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1021/1875 [===============>..............] - ETA: 1s - loss: 0.2528 - accuracy: 0.9062"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1055/1875 [===============>..............] - ETA: 1s - loss: 0.2535 - accuracy: 0.9061"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1090/1875 [================>.............] - ETA: 1s - loss: 0.2540 - accuracy: 0.9061"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1124/1875 [================>.............] - ETA: 1s - loss: 0.2534 - accuracy: 0.9062"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1159/1875 [=================>............] - ETA: 1s - loss: 0.2533 - accuracy: 0.9062"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1194/1875 [==================>...........] - ETA: 1s - loss: 0.2536 - accuracy: 0.9060"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1228/1875 [==================>...........] - ETA: 0s - loss: 0.2529 - accuracy: 0.9061"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1261/1875 [===================>..........] - ETA: 0s - loss: 0.2537 - accuracy: 0.9059"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1295/1875 [===================>..........] - ETA: 0s - loss: 0.2534 - accuracy: 0.9060"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1329/1875 [====================>.........] - ETA: 0s - loss: 0.2536 - accuracy: 0.9059"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1363/1875 [====================>.........] - ETA: 0s - loss: 0.2533 - accuracy: 0.9063"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1398/1875 [=====================>........] - ETA: 0s - loss: 0.2540 - accuracy: 0.9060"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1431/1875 [=====================>........] - ETA: 0s - loss: 0.2547 - accuracy: 0.9059"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1466/1875 [======================>.......] - ETA: 0s - loss: 0.2539 - accuracy: 0.9064"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1500/1875 [=======================>......] - ETA: 0s - loss: 0.2540 - accuracy: 0.9064"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1534/1875 [=======================>......] - ETA: 0s - loss: 0.2546 - accuracy: 0.9060"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1567/1875 [========================>.....] - ETA: 0s - loss: 0.2550 - accuracy: 0.9058"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1600/1875 [========================>.....] - ETA: 0s - loss: 0.2549 - accuracy: 0.9057"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1634/1875 [=========================>....] - ETA: 0s - loss: 0.2544 - accuracy: 0.9059"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1668/1875 [=========================>....] - ETA: 0s - loss: 0.2545 - accuracy: 0.9059"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1702/1875 [==========================>...] - ETA: 0s - loss: 0.2547 - accuracy: 0.9058"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1735/1875 [==========================>...] - ETA: 0s - loss: 0.2553 - accuracy: 0.9054"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1768/1875 [===========================>..] - ETA: 0s - loss: 0.2555 - accuracy: 0.9053"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1802/1875 [===========================>..] - ETA: 0s - loss: 0.2552 - accuracy: 0.9055"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1836/1875 [============================>.] - ETA: 0s - loss: 0.2552 - accuracy: 0.9053"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1870/1875 [============================>.] - ETA: 0s - loss: 0.2549 - accuracy: 0.9054"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1875/1875 [==============================] - 3s 1ms/step - loss: 0.2547 - accuracy: 0.9055\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 9/10\n",
      "\r",
      "   1/1875 [..............................] - ETA: 0s - loss: 0.2343 - accuracy: 0.9062"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  35/1875 [..............................] - ETA: 2s - loss: 0.2327 - accuracy: 0.9062"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  69/1875 [>.............................] - ETA: 2s - loss: 0.2490 - accuracy: 0.8972"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 102/1875 [>.............................] - ETA: 2s - loss: 0.2439 - accuracy: 0.9059"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 135/1875 [=>............................] - ETA: 2s - loss: 0.2500 - accuracy: 0.9039"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 169/1875 [=>............................] - ETA: 2s - loss: 0.2514 - accuracy: 0.9035"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 203/1875 [==>...........................] - ETA: 2s - loss: 0.2481 - accuracy: 0.9061"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 238/1875 [==>...........................] - ETA: 2s - loss: 0.2458 - accuracy: 0.9073"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 274/1875 [===>..........................] - ETA: 2s - loss: 0.2470 - accuracy: 0.9065"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 310/1875 [===>..........................] - ETA: 2s - loss: 0.2472 - accuracy: 0.9068"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 345/1875 [====>.........................] - ETA: 2s - loss: 0.2456 - accuracy: 0.9082"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 380/1875 [=====>........................] - ETA: 2s - loss: 0.2485 - accuracy: 0.9076"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 415/1875 [=====>........................] - ETA: 2s - loss: 0.2460 - accuracy: 0.9090"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 449/1875 [======>.......................] - ETA: 2s - loss: 0.2431 - accuracy: 0.9103"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 482/1875 [======>.......................] - ETA: 2s - loss: 0.2439 - accuracy: 0.9098"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 517/1875 [=======>......................] - ETA: 1s - loss: 0.2443 - accuracy: 0.9093"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 551/1875 [=======>......................] - ETA: 1s - loss: 0.2432 - accuracy: 0.9095"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 586/1875 [========>.....................] - ETA: 1s - loss: 0.2446 - accuracy: 0.9091"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 622/1875 [========>.....................] - ETA: 1s - loss: 0.2450 - accuracy: 0.9086"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 658/1875 [=========>....................] - ETA: 1s - loss: 0.2434 - accuracy: 0.9089"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 693/1875 [==========>...................] - ETA: 1s - loss: 0.2417 - accuracy: 0.9098"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 727/1875 [==========>...................] - ETA: 1s - loss: 0.2425 - accuracy: 0.9098"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 762/1875 [===========>..................] - ETA: 1s - loss: 0.2444 - accuracy: 0.9087"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 797/1875 [===========>..................] - ETA: 1s - loss: 0.2441 - accuracy: 0.9088"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 832/1875 [============>.................] - ETA: 1s - loss: 0.2439 - accuracy: 0.9089"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 867/1875 [============>.................] - ETA: 1s - loss: 0.2455 - accuracy: 0.9084"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 901/1875 [=============>................] - ETA: 1s - loss: 0.2461 - accuracy: 0.9081"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 934/1875 [=============>................] - ETA: 1s - loss: 0.2468 - accuracy: 0.9075"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 968/1875 [==============>...............] - ETA: 1s - loss: 0.2464 - accuracy: 0.9074"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1002/1875 [===============>..............] - ETA: 1s - loss: 0.2472 - accuracy: 0.9072"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1036/1875 [===============>..............] - ETA: 1s - loss: 0.2470 - accuracy: 0.9074"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1070/1875 [================>.............] - ETA: 1s - loss: 0.2465 - accuracy: 0.9077"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1105/1875 [================>.............] - ETA: 1s - loss: 0.2463 - accuracy: 0.9080"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1139/1875 [=================>............] - ETA: 1s - loss: 0.2454 - accuracy: 0.9085"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1172/1875 [=================>............] - ETA: 1s - loss: 0.2449 - accuracy: 0.9088"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1206/1875 [==================>...........] - ETA: 0s - loss: 0.2448 - accuracy: 0.9087"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1240/1875 [==================>...........] - ETA: 0s - loss: 0.2440 - accuracy: 0.9091"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1275/1875 [===================>..........] - ETA: 0s - loss: 0.2441 - accuracy: 0.9091"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1309/1875 [===================>..........] - ETA: 0s - loss: 0.2429 - accuracy: 0.9096"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1342/1875 [====================>.........] - ETA: 0s - loss: 0.2437 - accuracy: 0.9091"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1375/1875 [=====================>........] - ETA: 0s - loss: 0.2427 - accuracy: 0.9095"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1410/1875 [=====================>........] - ETA: 0s - loss: 0.2441 - accuracy: 0.9092"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1445/1875 [======================>.......] - ETA: 0s - loss: 0.2440 - accuracy: 0.9091"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1480/1875 [======================>.......] - ETA: 0s - loss: 0.2445 - accuracy: 0.9091"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1513/1875 [=======================>......] - ETA: 0s - loss: 0.2441 - accuracy: 0.9093"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1547/1875 [=======================>......] - ETA: 0s - loss: 0.2436 - accuracy: 0.9095"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1582/1875 [========================>.....] - ETA: 0s - loss: 0.2439 - accuracy: 0.9095"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1616/1875 [========================>.....] - ETA: 0s - loss: 0.2439 - accuracy: 0.9094"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1649/1875 [=========================>....] - ETA: 0s - loss: 0.2432 - accuracy: 0.9097"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1682/1875 [=========================>....] - ETA: 0s - loss: 0.2428 - accuracy: 0.9099"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1716/1875 [==========================>...] - ETA: 0s - loss: 0.2427 - accuracy: 0.9100"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1750/1875 [===========================>..] - ETA: 0s - loss: 0.2428 - accuracy: 0.9100"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1784/1875 [===========================>..] - ETA: 0s - loss: 0.2429 - accuracy: 0.9100"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1819/1875 [============================>.] - ETA: 0s - loss: 0.2433 - accuracy: 0.9098"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1854/1875 [============================>.] - ETA: 0s - loss: 0.2439 - accuracy: 0.9097"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1875/1875 [==============================] - 3s 1ms/step - loss: 0.2439 - accuracy: 0.9097\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 10/10\n",
      "\r",
      "   1/1875 [..............................] - ETA: 0s - loss: 0.1792 - accuracy: 0.9062"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  34/1875 [..............................] - ETA: 2s - loss: 0.2322 - accuracy: 0.9072"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "  68/1875 [>.............................] - ETA: 2s - loss: 0.2314 - accuracy: 0.9118"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 102/1875 [>.............................] - ETA: 2s - loss: 0.2238 - accuracy: 0.9139"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 136/1875 [=>............................] - ETA: 2s - loss: 0.2282 - accuracy: 0.9134"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 168/1875 [=>............................] - ETA: 2s - loss: 0.2244 - accuracy: 0.9165"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 199/1875 [==>...........................] - ETA: 2s - loss: 0.2326 - accuracy: 0.9138"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 229/1875 [==>...........................] - ETA: 2s - loss: 0.2294 - accuracy: 0.9148"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 259/1875 [===>..........................] - ETA: 2s - loss: 0.2260 - accuracy: 0.9159"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 290/1875 [===>..........................] - ETA: 2s - loss: 0.2250 - accuracy: 0.9154"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 320/1875 [====>.........................] - ETA: 2s - loss: 0.2256 - accuracy: 0.9153"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 349/1875 [====>.........................] - ETA: 2s - loss: 0.2250 - accuracy: 0.9149"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 378/1875 [=====>........................] - ETA: 2s - loss: 0.2234 - accuracy: 0.9158"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 406/1875 [=====>........................] - ETA: 2s - loss: 0.2237 - accuracy: 0.9164"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 435/1875 [=====>........................] - ETA: 2s - loss: 0.2241 - accuracy: 0.9161"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 463/1875 [======>.......................] - ETA: 2s - loss: 0.2236 - accuracy: 0.9160"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 492/1875 [======>.......................] - ETA: 2s - loss: 0.2228 - accuracy: 0.9157"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 521/1875 [=======>......................] - ETA: 2s - loss: 0.2229 - accuracy: 0.9152"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 550/1875 [=======>......................] - ETA: 2s - loss: 0.2240 - accuracy: 0.9147"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 578/1875 [========>.....................] - ETA: 2s - loss: 0.2271 - accuracy: 0.9131"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 606/1875 [========>.....................] - ETA: 2s - loss: 0.2282 - accuracy: 0.9129"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 635/1875 [=========>....................] - ETA: 2s - loss: 0.2291 - accuracy: 0.9130"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 663/1875 [=========>....................] - ETA: 2s - loss: 0.2284 - accuracy: 0.9130"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 691/1875 [==========>...................] - ETA: 1s - loss: 0.2307 - accuracy: 0.9123"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 719/1875 [==========>...................] - ETA: 1s - loss: 0.2320 - accuracy: 0.9120"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 747/1875 [==========>...................] - ETA: 1s - loss: 0.2314 - accuracy: 0.9123"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 775/1875 [===========>..................] - ETA: 1s - loss: 0.2317 - accuracy: 0.9124"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 803/1875 [===========>..................] - ETA: 1s - loss: 0.2317 - accuracy: 0.9124"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 831/1875 [============>.................] - ETA: 1s - loss: 0.2319 - accuracy: 0.9122"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 859/1875 [============>.................] - ETA: 1s - loss: 0.2322 - accuracy: 0.9121"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 888/1875 [=============>................] - ETA: 1s - loss: 0.2321 - accuracy: 0.9121"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 917/1875 [=============>................] - ETA: 1s - loss: 0.2328 - accuracy: 0.9120"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 946/1875 [==============>...............] - ETA: 1s - loss: 0.2329 - accuracy: 0.9120"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      " 974/1875 [==============>...............] - ETA: 1s - loss: 0.2321 - accuracy: 0.9123"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1002/1875 [===============>..............] - ETA: 1s - loss: 0.2337 - accuracy: 0.9122"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1030/1875 [===============>..............] - ETA: 1s - loss: 0.2341 - accuracy: 0.9118"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1059/1875 [===============>..............] - ETA: 1s - loss: 0.2337 - accuracy: 0.9119"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1087/1875 [================>.............] - ETA: 1s - loss: 0.2340 - accuracy: 0.9119"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1116/1875 [================>.............] - ETA: 1s - loss: 0.2343 - accuracy: 0.9117"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1144/1875 [=================>............] - ETA: 1s - loss: 0.2343 - accuracy: 0.9120"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1172/1875 [=================>............] - ETA: 1s - loss: 0.2345 - accuracy: 0.9119"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1200/1875 [==================>...........] - ETA: 1s - loss: 0.2348 - accuracy: 0.9117"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1229/1875 [==================>...........] - ETA: 1s - loss: 0.2350 - accuracy: 0.9117"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1257/1875 [===================>..........] - ETA: 1s - loss: 0.2355 - accuracy: 0.9115"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1285/1875 [===================>..........] - ETA: 1s - loss: 0.2359 - accuracy: 0.9115"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1313/1875 [====================>.........] - ETA: 0s - loss: 0.2359 - accuracy: 0.9115"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1341/1875 [====================>.........] - ETA: 0s - loss: 0.2361 - accuracy: 0.9114"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1369/1875 [====================>.........] - ETA: 0s - loss: 0.2359 - accuracy: 0.9113"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1397/1875 [=====================>........] - ETA: 0s - loss: 0.2361 - accuracy: 0.9114"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1425/1875 [=====================>........] - ETA: 0s - loss: 0.2360 - accuracy: 0.9113"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1452/1875 [======================>.......] - ETA: 0s - loss: 0.2360 - accuracy: 0.9114"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1479/1875 [======================>.......] - ETA: 0s - loss: 0.2354 - accuracy: 0.9116"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1507/1875 [=======================>......] - ETA: 0s - loss: 0.2351 - accuracy: 0.9118"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1535/1875 [=======================>......] - ETA: 0s - loss: 0.2351 - accuracy: 0.9119"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1562/1875 [=======================>......] - ETA: 0s - loss: 0.2349 - accuracy: 0.9119"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1590/1875 [========================>.....] - ETA: 0s - loss: 0.2344 - accuracy: 0.9121"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1617/1875 [========================>.....] - ETA: 0s - loss: 0.2347 - accuracy: 0.9121"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1646/1875 [=========================>....] - ETA: 0s - loss: 0.2352 - accuracy: 0.9120"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1674/1875 [=========================>....] - ETA: 0s - loss: 0.2352 - accuracy: 0.9120"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1703/1875 [==========================>...] - ETA: 0s - loss: 0.2358 - accuracy: 0.9118"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1731/1875 [==========================>...] - ETA: 0s - loss: 0.2361 - accuracy: 0.9117"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1760/1875 [===========================>..] - ETA: 0s - loss: 0.2363 - accuracy: 0.9118"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1788/1875 [===========================>..] - ETA: 0s - loss: 0.2370 - accuracy: 0.9115"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1816/1875 [============================>.] - ETA: 0s - loss: 0.2367 - accuracy: 0.9115"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1844/1875 [============================>.] - ETA: 0s - loss: 0.2367 - accuracy: 0.9116"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1873/1875 [============================>.] - ETA: 0s - loss: 0.2371 - accuracy: 0.9115"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r",
      "1875/1875 [==============================] - 3s 2ms/step - loss: 0.2370 - accuracy: 0.9115\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<tensorflow.python.keras.callbacks.History at 0x7fd5c7912b00>"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(train_images, train_labels, epochs=10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "W3ZVOhugCaXA"
   },
   "source": [
    "As the model trains, the loss and accuracy metrics are displayed. This model reaches an accuracy of about 0.91 (or 91%) on the training data."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "wCpr6DGyE28h"
   },
   "source": [
    "### Evaluate accuracy\n",
    "\n",
    "Next, compare how the model performs on the test dataset:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:28.212489Z",
     "iopub.status.busy": "2020-10-15T01:29:28.211852Z",
     "iopub.status.idle": "2020-10-15T01:29:28.957935Z",
     "shell.execute_reply": "2020-10-15T01:29:28.957398Z"
    },
    "id": "VflXLEeECaXC"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "313/313 - 1s - loss: 0.3637 - accuracy: 0.8693\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Test accuracy: 0.8693000078201294\n"
     ]
    }
   ],
   "source": [
    "test_loss, test_acc = model.evaluate(test_images,  test_labels, verbose=2)\n",
    "\n",
    "print('\\nTest accuracy:', test_acc)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "yWfgsmVXCaXG"
   },
   "source": [
    "It turns out that the accuracy on the test dataset is a little less than the accuracy on the training dataset. This gap between training accuracy and test accuracy represents *overfitting*. Overfitting happens when a machine learning model performs worse on new, previously unseen inputs than it does on the training data. An overfitted model \"memorizes\" the noise and details in the training dataset to a point where it negatively impacts the performance of the model on the new data. For more information, see the following:\n",
    "*   [Demonstrate overfitting](https://www.tensorflow.org/tutorials/keras/overfit_and_underfit#demonstrate_overfitting)\n",
    "*   [Strategies to prevent overfitting](https://www.tensorflow.org/tutorials/keras/overfit_and_underfit#strategies_to_prevent_overfitting)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "v-PyD1SYE28q"
   },
   "source": [
    "### Make predictions\n",
    "\n",
    "With the model trained, you can use it to make predictions about some images.\n",
    "The model's linear outputs, [logits](https://developers.google.com/machine-learning/glossary#logits). Attach a softmax layer to convert the logits to probabilities, which are easier to interpret. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:28.964739Z",
     "iopub.status.busy": "2020-10-15T01:29:28.964119Z",
     "iopub.status.idle": "2020-10-15T01:29:28.977816Z",
     "shell.execute_reply": "2020-10-15T01:29:28.977317Z"
    },
    "id": "DnfNA0CrQLSD"
   },
   "outputs": [],
   "source": [
    "probability_model = tf.keras.Sequential([model, \n",
    "                                         tf.keras.layers.Softmax()])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:28.981879Z",
     "iopub.status.busy": "2020-10-15T01:29:28.981269Z",
     "iopub.status.idle": "2020-10-15T01:29:29.358175Z",
     "shell.execute_reply": "2020-10-15T01:29:29.357478Z"
    },
    "id": "Gl91RPhdCaXI"
   },
   "outputs": [],
   "source": [
    "predictions = probability_model.predict(test_images)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "x9Kk1voUCaXJ"
   },
   "source": [
    "Here, the model has predicted the label for each image in the testing set. Let's take a look at the first prediction:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:29.363537Z",
     "iopub.status.busy": "2020-10-15T01:29:29.362894Z",
     "iopub.status.idle": "2020-10-15T01:29:29.366418Z",
     "shell.execute_reply": "2020-10-15T01:29:29.365810Z"
    },
    "id": "3DmJEUinCaXK"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([5.1698703e-07, 5.0422708e-11, 1.0513627e-06, 4.2676376e-08,\n",
       "       4.1753174e-07, 8.8213873e-04, 1.4294442e-06, 8.9591898e-02,\n",
       "       3.7699414e-07, 9.0952224e-01], dtype=float32)"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predictions[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "-hw1hgeSCaXN"
   },
   "source": [
    "A prediction is an array of 10 numbers. They represent the model's \"confidence\" that the image corresponds to each of the 10 different articles of clothing. You can see which label has the highest confidence value:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:29.370858Z",
     "iopub.status.busy": "2020-10-15T01:29:29.370189Z",
     "iopub.status.idle": "2020-10-15T01:29:29.373719Z",
     "shell.execute_reply": "2020-10-15T01:29:29.373242Z"
    },
    "id": "qsqenuPnCaXO"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.argmax(predictions[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "E51yS7iCCaXO"
   },
   "source": [
    "So, the model is most confident that this image is an ankle boot, or `class_names[9]`. Examining the test label shows that this classification is correct:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:29.377805Z",
     "iopub.status.busy": "2020-10-15T01:29:29.377134Z",
     "iopub.status.idle": "2020-10-15T01:29:29.380679Z",
     "shell.execute_reply": "2020-10-15T01:29:29.380090Z"
    },
    "id": "Sd7Pgsu6CaXP"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_labels[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ygh2yYC972ne"
   },
   "source": [
    "Graph this to look at the full set of 10 class predictions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:29.388527Z",
     "iopub.status.busy": "2020-10-15T01:29:29.387890Z",
     "iopub.status.idle": "2020-10-15T01:29:29.390338Z",
     "shell.execute_reply": "2020-10-15T01:29:29.389776Z"
    },
    "id": "DvYmmrpIy6Y1"
   },
   "outputs": [],
   "source": [
    "def plot_image(i, predictions_array, true_label, img):\n",
    "  true_label, img = true_label[i], img[i]\n",
    "  plt.grid(False)\n",
    "  plt.xticks([])\n",
    "  plt.yticks([])\n",
    "\n",
    "  plt.imshow(img, cmap=plt.cm.binary)\n",
    "\n",
    "  predicted_label = np.argmax(predictions_array)\n",
    "  if predicted_label == true_label:\n",
    "    color = 'blue'\n",
    "  else:\n",
    "    color = 'red'\n",
    "\n",
    "  plt.xlabel(\"{} {:2.0f}% ({})\".format(class_names[predicted_label],\n",
    "                                100*np.max(predictions_array),\n",
    "                                class_names[true_label]),\n",
    "                                color=color)\n",
    "\n",
    "def plot_value_array(i, predictions_array, true_label):\n",
    "  true_label = true_label[i]\n",
    "  plt.grid(False)\n",
    "  plt.xticks(range(10))\n",
    "  plt.yticks([])\n",
    "  thisplot = plt.bar(range(10), predictions_array, color=\"#777777\")\n",
    "  plt.ylim([0, 1])\n",
    "  predicted_label = np.argmax(predictions_array)\n",
    "\n",
    "  thisplot[predicted_label].set_color('red')\n",
    "  thisplot[true_label].set_color('blue')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Zh9yABaME29S"
   },
   "source": [
    "### Verify predictions\n",
    "\n",
    "With the model trained, you can use it to make predictions about some images."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "d4Ov9OFDMmOD"
   },
   "source": [
    "Let's look at the 0th image, predictions, and prediction array. Correct prediction labels are blue and incorrect prediction labels are red. The number gives the percentage (out of 100) for the predicted label."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:29.407710Z",
     "iopub.status.busy": "2020-10-15T01:29:29.407060Z",
     "iopub.status.idle": "2020-10-15T01:29:29.522612Z",
     "shell.execute_reply": "2020-10-15T01:29:29.523065Z"
    },
    "id": "HV5jw-5HwSmO"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x216 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "i = 0\n",
    "plt.figure(figsize=(6,3))\n",
    "plt.subplot(1,2,1)\n",
    "plot_image(i, predictions[i], test_labels, test_images)\n",
    "plt.subplot(1,2,2)\n",
    "plot_value_array(i, predictions[i],  test_labels)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:29.539661Z",
     "iopub.status.busy": "2020-10-15T01:29:29.538497Z",
     "iopub.status.idle": "2020-10-15T01:29:29.655736Z",
     "shell.execute_reply": "2020-10-15T01:29:29.656108Z"
    },
    "id": "Ko-uzOufSCSe"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x216 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "i = 12\n",
    "plt.figure(figsize=(6,3))\n",
    "plt.subplot(1,2,1)\n",
    "plot_image(i, predictions[i], test_labels, test_images)\n",
    "plt.subplot(1,2,2)\n",
    "plot_value_array(i, predictions[i],  test_labels)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "kgdvGD52CaXR"
   },
   "source": [
    "Let's plot several images with their predictions. Note that the model can be wrong even when very confident."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:29.679633Z",
     "iopub.status.busy": "2020-10-15T01:29:29.665430Z",
     "iopub.status.idle": "2020-10-15T01:29:31.579390Z",
     "shell.execute_reply": "2020-10-15T01:29:31.579841Z"
    },
    "id": "hQlnbqaw2Qu_"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x720 with 30 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot the first X test images, their predicted labels, and the true labels.\n",
    "# Color correct predictions in blue and incorrect predictions in red.\n",
    "num_rows = 5\n",
    "num_cols = 3\n",
    "num_images = num_rows*num_cols\n",
    "plt.figure(figsize=(2*2*num_cols, 2*num_rows))\n",
    "for i in range(num_images):\n",
    "  plt.subplot(num_rows, 2*num_cols, 2*i+1)\n",
    "  plot_image(i, predictions[i], test_labels, test_images)\n",
    "  plt.subplot(num_rows, 2*num_cols, 2*i+2)\n",
    "  plot_value_array(i, predictions[i], test_labels)\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "R32zteKHCaXT"
   },
   "source": [
    "## Use the trained model\n",
    "\n",
    "Finally, use the trained model to make a prediction about a single image."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:31.584662Z",
     "iopub.status.busy": "2020-10-15T01:29:31.583984Z",
     "iopub.status.idle": "2020-10-15T01:29:31.586277Z",
     "shell.execute_reply": "2020-10-15T01:29:31.586760Z"
    },
    "id": "yRJ7JU7JCaXT"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(28, 28)\n"
     ]
    }
   ],
   "source": [
    "# Grab an image from the test dataset.\n",
    "img = test_images[1]\n",
    "\n",
    "print(img.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "vz3bVp21CaXV"
   },
   "source": [
    "`tf.keras` models are optimized to make predictions on a *batch*, or collection, of examples at once. Accordingly, even though you're using a single image, you need to add it to a list:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:31.591301Z",
     "iopub.status.busy": "2020-10-15T01:29:31.590656Z",
     "iopub.status.idle": "2020-10-15T01:29:31.592794Z",
     "shell.execute_reply": "2020-10-15T01:29:31.593208Z"
    },
    "id": "lDFh5yF_CaXW"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1, 28, 28)\n"
     ]
    }
   ],
   "source": [
    "# Add the image to a batch where it's the only member.\n",
    "img = (np.expand_dims(img,0))\n",
    "\n",
    "print(img.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "EQ5wLTkcCaXY"
   },
   "source": [
    "Now predict the correct label for this image:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:31.597886Z",
     "iopub.status.busy": "2020-10-15T01:29:31.597206Z",
     "iopub.status.idle": "2020-10-15T01:29:31.633314Z",
     "shell.execute_reply": "2020-10-15T01:29:31.632699Z"
    },
    "id": "o_rzNSdrCaXY"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[1.2673076e-05 1.9937504e-13 9.9978513e-01 1.8617269e-11 1.3060638e-04\n",
      "  2.2522463e-12 7.1663781e-05 1.4157123e-21 3.1792444e-11 1.6293697e-13]]\n"
     ]
    }
   ],
   "source": [
    "predictions_single = probability_model.predict(img)\n",
    "\n",
    "print(predictions_single)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:31.665435Z",
     "iopub.status.busy": "2020-10-15T01:29:31.657875Z",
     "iopub.status.idle": "2020-10-15T01:29:31.739346Z",
     "shell.execute_reply": "2020-10-15T01:29:31.738715Z"
    },
    "id": "6Ai-cpLjO-3A"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWAAAAEbCAYAAADkhF5OAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAAAdhUlEQVR4nO3debglVXnv8e/b3TTdoM2MIIgt0DSDAoIEEVBkEBAUZUYJKIKMVxnU5jqBBgiQmERwwgGVNkQEFBQVEYMKDlFQUSNOOMThRkGjJuCErPzxrs0pzj0Nfc4e1uHw/TwPT++Js6pqV/1qTVU7SilIkkZvVusFkKSHKwNYkhoxgCWpEQNYkhoxgCWpEQNYkhqZM5kPr7nmmmXhwoVDWpSZ6dZb4Z57hlvGnDmw1VbDLUPS1N1yyy13llLWGv/6pAJ44cKF3HzzzYNbqoeBiOGXcc894NciTV8R8eOJXrcLQpIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaMYAlqREDWJIaiVLK8n844g7gx8NbnPtZE7hzRGVZ9vQo37Ite6aW/dhSylrjX5xUAI9SRNxcSnmSZT98yrdsy344lN1lF4QkNWIAS1Ij0zmA327ZD7vyLduyHw5l32fa9gFL0kw3nWvAkjSjGcCS1IgBPAUREa2XQaMREY/w+xZARMyq/w5sfzCAJykiotSO84jYMyLWa7EMM7GsWt7qnceLR1n2BMuyCFgKbD2i8uaMopzJ6H7/ETF3FOVMRxGxGrCgPt16UH93xgRw7wuMiPkRsdKwyumE79OB1wL/PayyJjLuBPDsiFh1RGXtGhGbD6usWsYsYNeIuCAijgOWRMSCB/v/hqWU8j3gh8DpEbHlMMuKiFWA7erjPYa9rZfHuO//hcBhvVrgoP5+/XcRcMQwA34Adib3x9cBSwfWMiqlzJj/gOcA1wGfB/4aWHlI5RwA/Bx4dn0+t8G67gP8G7DmCMo6Gfgy8LgRrdtXgV8Dj6nPVxjxtg1gVuf5ucCVwJZDLHMTYAlwNfDtYe27U1y2HYBrgUcOchvXf3cBPgh8CTgYWLH1+j7AMn8K+A3w1EH9zZlUA94MOBV4DXA2GcDPr+/1daaa4P//MPAr4CUApZQ/RcTsfsqY5PLsCLwL+NtSyp0RseIQy9qV3I47lVJ+GBFPjIjdB1xGt5m7Irmj3wT8bUTMKaX8eZDlPdiylHRvRKwBUEo5HfgW8LpB14R7615K+S6wHvBXwAeAPw6ynKmKiG2Ai4BfAHcN6u+WUkpE7Ay8DbgYuBV4KnDIdKkJT3DcX0B+N4dHxKYDKaMm+0NaRGwMnAPMLqUcUF/bAbgMOKyU8rk+/vb9+nyBvwDfBO4AvgZ8pZRyZH1/dinlL/2sy4MtQ32+Mrlu65ZSth1k2ROUtQg4nTzz/4VsJv8euKSU8v5BlldPor8rpfysPv8XYE4p5aCI2IWsHX2i3zKXc7lOArYHfgK8q5Rye0ScCWxBnvi+MoAyuuv+IuDp5MlnEdkCuLSU8vOIWBP4VRnBwTr++6+vHQMcSVZwvjyo5YiIV5A1/TPqifdFwHOBdwIfHOWJd4Jl6343BwBzgLtKKddExN8B6wKnAPsDfyilvHcq5Txka8Djzk4/Iputq9b+s5VKKV8A/oW869GUdb6El5FBtBc5MLMI2AZ4fERcVT871PCNiN0jYl9gNeBw4NaIuLoXvv3WwseVdXxE7A/cTYbCo4EryG6ez5I7ZN865Z1C1rQuiYiLal/ji4HZEfEV4B+B7w+izAdTA+dg4P/Wf8+JiJ1LKWeS+9op/bY6ImJBZ913AvYDTiilvJvsWlofODAiXkmONQytldPVWaajI+I1db9fClxOti6fNMB+4O8AT46IzUspfyylvAWYDewEDKSGOVWd7fAS4BXAVsBREfGeUsrLgV+S++TLyeyZckEPuf8Yq7nvBBzGWF/sy8hLDE8H9gB+Sjad+y1vY+BD9fHZZD/divX5CsCNZEDFENf5NOAzwJuAT5P9co8A3lGfzxpgWSeRfb4bT/De8+sOt+kAyzscuLE+Pods6l7cef9AYOEQt+12ZACuWLfp3wHrkF1M15N9wNcBO9fP99XvDmxEhvs8YFXgKuAW4Mmdz+xDBt4XGGLf8zKW76V1vXcFvg6cWl9fUvf1babwN3vH7LbAbsAGdXufA7yK7HpZXPflq4BXj3Kdl7HM84AP9Y4DYC7wz8CS+nxTYO2+ymi9kn1snD2Bb9RA/BTZZKEeNF+uwbRXfW1S4TQ+SIHHApcAbwSu6YTv/oMMvgdYnk0667cE+DjZeplFTo15M3XAagBlrVkPvi1qGB1KNrV2IZvknwKe0GcZ47fvlvWAPJE8ua0C3E4Ozgx9AA54HjkItE99PreG5Cc6n7m9hsVKAyjvcTV4tyZP7r3961Rgo87nZjGCwTjuP+A4i6zZBVmh+WgNytn1/ZMmu691wndv4LvAq8k+5SeRrcglwBfJmv9m5An3/F6Zo/pvgv1yJbLSs0/ntb2BfxhYmaNcwUHuMGSz6JDOa9cCb6mPzwAuBJ4y2QO4+yUAh9QdYi5Z8/wKsH5972iy1tLXGXA5lmct4JHkAMDFwMd660SeABaM33H63Onm1HW9jBz5fydwKXliWwFYtc/16W7fVYAFne/0EmDv+vxv6kG51jD3o87js8mBv4Pq8w3I2QhPBp5JnnjXG+C6P7KW+S5gIVn7W0qe7BYNc596gOXbkzwxXEGehK+gzvABjgP26ONvb0G2nDaq5fyibt/dOvv5avW9bwGPH/G6d7+bHchKzwKyy/F24Cn1vWPISsK8fo67+8pq8UVPYePMBRbXxwuBtWvAHtz5zGOB99bHKwD/QJ5Fp1RjIWtj3wA2rM/3IJuiN5A1oW8CWwx5vbcGzgNWJwP4RmoNCXgh2TxcZ0A73X5kd87iWu6B1GlnwLH1YJwzwHV7GdnU/BrZrbE+2Z/2ZuD1NfAGUqtfjmU5iaxtX0p2Wz23vn4c8DnyxNtXIEx0sAKPIZvfb6v79SZ1m5w4yG39AMu0DWPdKo8Evlgf71ZDp3cyOhK4rXcsLOff3oisIOzXeW0TYEfg5vp8CfAnYNf6fAE5DjDU4+pBlvv/kC3o95LdIc8gT8A/A95Cnhw2H1h5rVZ0EhtkDXJ6yjE1jL4GrExOM/t/vS+LHEG+iVpjImtyy117GhdGTyBrt+vV508j+8N6fYUH0mkqDnHdt6sH/2JyEOAisk/qzcC/D2pHBY4n504fC/wZ2LG3TYAXkCeivnY6su/vr8ga1q5kk38BOch1US1ne7L/8SP9Bt4klmuj+l1vUJ8fVg/AA+vztem3n68TXOSc6neTA2uPIrt8Xlu/0w3JLolHj2C959Tv/V8733fvO5lX9/EfAO+p22e59zUyaL8JvKHuV8d13juasZbqLmTIdfu+Rzrne9xyL6rrug7Z/bB7Pf4W1WNwcwZcKWiyopPYIHPJ2sABZLP4j8AZnfdfSp6ZLyDPTL0+vL76ZcmAv5CsmbyN7Ae6kk6Ne8jrvW5vHeoBe1k9YDasO8VB9HFRBPc/2axNhvoqwFFkH+/sznt/T//hu1cNtSPImu4hwNLO+8+gU8Ma5kHI/9/lMpecLbMTY107rwP+hzqG0Gd5a5Cj/a8mT0A3koOO55HzydetnzmXbLUNveY7btleTJ7wdiOn19H5/heRg8vLfQKqIfVV4Fn1+eFk0G9dn+9MzqV9I9mCe/JE38uI1n9Wt+x6fH103GfOBI4e2jKMeqWnsJFOJEeDF5NN/7PJgaHewbIj8Hjgif1+kWT/02fq42eRfclb1udnAOcNe2cha4HvIGdzLKiBdR4DqnGPC9/nkTWuJbXMazvb9TSyhtZXIJCth+8B23Ve25ps4m3fee1i6oyVYW3fceu+kLEWzvl1H+t1uexXQ2n9Psvbt27bXcmW2yeAfet7a9WD+yryAozVGc1VjeNPQAuAE8ja771kP/ynyNH+tzHJgTDyRHZv5/nXyUHjr9XveDZZiTiD2t/f6r9O8G7AWF/3VdSuzPr8bOCsoS1Dyw2wvBupfoHH1+cvBf6J7JfZieynm1KNd4KdcRbZwX75uNefx4CnXk20DGTf9TzyhPIGcurTCeRVQm8acLkHkV02G9cD7ZuMDYgdVA+chQMo51TgpfXxnPrvKuTJ9FyyL/gFZJ9jX4E3ie18KtmF85Fa/nyyqf0+srVxKxNMwZtkefvWv9PrylgPuBl4R+cza5BT3t4/2aAbwDbYjay8PKo+P57sDjiKPOkvZIonfXKmwA/IgbzX1tfmkjMgTlvWMo3qv7ruu9fHp9Tv6X31mFuVbO1+gjwp30odfxrKsox65Zdj48yjXnPOWL/cxmQtcG3yjH0K8FZyMvQ+AyhzE+p0H/IMfRnwsfp8s/q8r6lXy7EMx9ed4B3A0+pru5J93d8ju1hWG1BZ25FN4RPr87XrwfKeGgY3M6BBJ7Ir56zea4w1+1YDXknOAngXIxp4IVsY7yOngm1K9vn15nU+sW7vvlobZB/iDdRaf2ff2pm8uc9Jnc+OpOY7bvlOImu8r6n7Vu84O67uFzsOoIzdgHu4/0yTF40P4Bb/kf3895Ize95ej/HH1/3wErIidiw50D3wStf9lqX1xphg4+xN1nKPIPsF1yIHKs5hrF9pJbJ53JsZMaWzaN3Qj60H4QupMybIk8AXgGvq86HOxSQvv/wG9TJX8kx8eOf9xfTX57uInE61K1n7XLfueDcAW9XPrEK2KPboHZADWrdda7hv29nmvZrwSeTJb+g3M6rhvxVZs7+YsX7Ox9YweuMAy1qNbL08oe5LZ5K1y8vIqwh/Arxu2Ou8jGXbnZzZsTJ5hdd/kJeZ9/rfj2Fwc8qfCXy/Pt6YnHb2jBbr3d0P6r+9qzyX1ucrkJW7K+h0lw19eVpujGVsoFk1GP6b2nyrr+9CDuRsO4gvYNxrO5H9XkcwVlt5VT1o+pr7uYxleCqd/q96ILyqPp5NNsk/yGAm/e9DjuR+CPgk8GPybL8+Odh0IUOccVAP9DPJftZtO68fWpdraFPNlvFdH1ND8L454mRt+AbypN7/3M4M+9PIZuxPyZbF0WSTv9ftct+MnWH+N359yBr3uuTUsuvra0vJ6WAD/y7IAdi7yS6fvgc1B/Td9EL4ALIm/LTO+5dSpyGOZHlab5DxOwlZaziCvALnbLKG0jtQDiQ77/uukZI13ncAZ5FXYj2hhvBp5DzUjw/rACH7WO9g7Eq9fcgR8S07n7mO/q8424u8mKG7g51J3s9gM7Lr4YwaEMPr58r+z9eSs0neULf5t4cZ/OPKP5Ac7d+qPj+2bt/uzIeBzj4gryLcgXG3WCSbuHsMIuiXYxm6x9ViYLPO81cz1gV1TD3e+ur3foDl2G2UobY826UTws8np16+qgbybYzwQpjmG2PchtmEsRu/zCKbbBeQtainkdfPX8gk50l2Nnbv32PIfs5DyP7kb9SDZXPyPhKXMoTr78m5sE+rj/cnByr2IifBn0V2PzyLHIX/Sj8nALKmcy9jo+7zOu+9juz7m0+efF5OHxd0LOfyzK+Bd2YNwE2GWNZKnccnk/2aZ5C13GPr60eTl77uMML9+yCyu2soQfcA5Z5aj6trySlgqzPW/3kh2bJcdwTL0WLAbcIya7708uCgeqy8mwF2vy3X8o16g4zbCOuQA0KzyD6iHwH/2Hn/EXWHeSd5A/Q96dTmJlHOwnF/82TgmZ3XnkPOfuh1Pwzl/g71QLiJsauPDiJH/59KjjofR9a8L6fW1vosb596clmjPu/WxD7N2NS9aXsT7Cmu8z+Rte7tgcvq6y+rJ7W3d0L4iFEccGST/2SyGT7qS2z3YGxA+Szq/S1qCB9GdokMdYC54b7QbQHsTbZGFgPze+93QnhvhtgKXOYyNt5AR4/bIGeRTYANOp+ZT/bXbd3dqMt7NiWnA32XvKHICWQt8yLgqs5nHkXWelcdwY5wItkX+9T6/OAawr1r4uczgL7fcTve7dQZFIw1ua9mxHfZGsH+1Jv69ZzOtlyvhvKnyYtZziSn3B07wuWaX5dhpDXfWvY25NSys8g+6d73P7Kaf4N1Ht/vfSrZ738u2erZvfvZ5c2SoSzrNNhYa5Oj0k+vz8+rG2nCbobJbCzGbuyxuB6I13UC/NNkk2M2OSD0OYZ/Y53eT+wcNy6EDyBHoocyQjxBCB9Rt/FQ13fE+9H4qV/z60l3fbL2+8r6+lFkLXjGrHtnG4wPniC7mL5E3sSpt+8fTbbEVmsZPkPcDmvWf3st6/fX5yeT3TCzyFkPzdd95L/C2vkJllL//WVE/JT8wb8/l1KWRMQ5wCcj4hml/jpCT+//W45ynkEOeNxEDuQdT05f24wM5X3JmQGXkF/Si0opvxzEOi5jebYEXhERV5RS3la3w2si4vWllCsj4s9kn/DAlVI+Xn/h4bMR8RZyrutQ17eBP5KDKX+IiHnkFWg7kXNRVydvJL4x2d2z7wxbd+B+NxF/KRm8PyLHUC4gT/onRMSjyC63w0op/9VmSYejHlNrAT+MiMNKKR+OiF8Dd0TEpeQJZ9+SPzd1MHnC/kXDRR5tAEfEiqWUP9bHTyE31hdKKa+td94/qv4owysjYgWyX/Rny/6LyyxnN/LeEaeQNaNtyKbp44DtI+J3pZSfAnvUn/eZXUr53QBWsVf+/U4y9fHXI+KrwJ4RcW8p5a0RUYA3RMTJpZQPD6r8idQQnk1Ob3tiKeXfh1leA78hm9h/T86nvp68qOQ2cj7qe8jpUOeUUkbyyxqjUn8B5u76eCdy1sdFZAi/h2zx/JKcfjibnN753TZLO1y1QncU8O6IeEEp5SMRcRd5kc2LSyn3RMSRZKvoxqYLywh/Ey7y59Ovol46TE67+j45EfyaerY6lRyUe2sp5bN9lLUd2df1+fo7Y4eSv2O2Knn5503Ap0spP57yCj1w+XNKKffUx3uSzd2l9flLyHshfKCUcm3dWa4vpfzHMJZlgmW772CdaSLiEeR0wscAV3dO9u8FPlxKubLl8g1DROxDDrSdT9buTwDOL/nbZWuRt1d8PHDyqPax6SAi9iIH8PcjT8Jnkt2Qd5CDswdPh0rISH+UMyKWMHabuzNKKd+OiGPJg+a6GsKvAK4tpXx9AOXNqs2NxeT9HO4ir/jaiDwBXFYG/DtuEbEH2c94Kzn4Bznt7eJSyuX1MxeTtZPXlFI+PsjydX8RcRA5tfDgUsrtrZdnkOrvA55N3m/h6oh4DDmf9/OllOPqZ9Ygu2MeRx4Dfyml3NtqmYehd5zXx4eR40dviIgDyfGlZ5ZSbqqt7jWAW6fLyWgkXRC9H3sspZwXEXeScw/fS07GvxwowH71xyXPH1S5vS+llPKd2gd0CNlPeBtwwxDCdy/yIo6l5ODiXuSljRcDf123wwfIe7DOI+eEaggiYl3y+z6G/OWUmRa+65AXDR1dSvlyRKxcSvlJRJwALI2Ik0opbyql/CoiziWnVjb7leFhiYitgHMj4sBSyl1kLfdOgFLKFRFxL3B1RBxdSvlQy2WdyNADuBe+tW/qt6WUd0X+zPZ5EfGLUsotEXEF2Tc1tH6pGsJXAM8m70j1q0H+/YhYnRxp3q/2O21ANgtXJEMY4PURsR95T4LnzsSBoGnkN+TFJvvNtD7favyg48sjYhdyUOknwJKIWKuUckYp5dftFnO4Sim3RsQ9wGUR8VxyoO3OzvsfrGMyF0TEJ4G7p1MLYCRdEBGxN3nH/yNLKTfW104gm+onllL+rdtvOuRlWWFYNYHaH3c+OcfydxHxz8BnSykX1fe3IO+Idf0MDQWNSA2VU8mb2fcGHW8iW3fPIkPoOeSJ/o5Gizk0df1n9VqxEXEleT+L2+u/t5EnKcgppneXUn7fYlkfyNADOCLWI2uGx5RSvlSbDAvI2sn+5KDBU4D/mU5npqmqJ5sLyBH5RwPPL6X8vtcSaLt0mkkeYNDxErIb7PqZuM91j6WIWK83VTUiLiK7nC4iZ7wsIOeDv3K69PmON/AAjojNyUsbL6vPVyHvO3o3Oe1sY/K668tLKe+MiMeVUn440IVoLCJ2Jy/6WKdOi5lXSvlD6+XSzNcZdDxkJrayxoXvSeTNdG4hf2fuWxHxZvKCp2fXz8wtpfyp3RI/sFmD/GMRsQn5UyYr914rpfyWvPBhLnn57x7kXNRt6/szKnwBSinXk5ee3hARaxu+GraIWDciTianWx05E8MX7nexyXPIe02fRF7xd2xE7FBKORGYFRG9vt+hd2v2Y2CDcHWq1zXAFaWUi+tr82u/y1Lyd6L+EhHbk1elnT6osqejeuHDXODaiHhSvjTzmoOaNn7DzB50vE9EbErONrq0DuL/gPwRh0PrTKp9I+LR9Xib1sfcQGrAtdvhfeSlj7+NiB0Bat/nhuR9d9eJvBz3ZHLe4rX1DDVjlVKuJu/3cK/hq2Eqpfy+lPLRmRi+kZdPd/2ObEU/v9Z6/4u8z/SfgGfXLr+fj3o5p6LvPuCImE8Osr2TrAGfRu1uIO+5ezU5Mfzs+vl1Sin/6aCUpAdTa7vfIn/G/rZSytvr6/PIq2p3Iy8v/0IdlJxXSrlzmX9wmhnIIFwvVOvjxWTH+BwygL9bSvlm92oVSVoeEbE+eU+Pj5Bh+wvyEuN/LaXcFREnkhfcvKKU8sV2Szo1A+mC6ITvrFLKd8g+33vICw5WrZ8xfCVNSsmbZn2JvKHWM8lLrY8BPlbHVm4lb7w16Zt2TQcDnQXRufT3e2QIzyP7ZFYbZDmSZr7OGNHp5GDamsB/kjcX+jb5O26Hkr/y8ZMmC9mnoV6IERGL4L5AlqRJqSG8AnktwYbk9NXTSylX1Wmvd5SH8H2NR3o3NEmaijq29BngzaWUv2m9PIMy0C4ISRqGOrZ0OjA7IlZqvTyDYgBLeqj4IjkYN2PYBSHpISNm2C+6GMCS1IhdEJLUiAEsSY0YwJLUiAEsSY0YwJLUiAEsSY38L43UgwIIdBNZAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_value_array(1, predictions_single[0], test_labels)\n",
    "_ = plt.xticks(range(10), class_names, rotation=45)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "cU1Y2OAMCaXb"
   },
   "source": [
    "`tf.keras.Model.predict` returns a list of lists—one list for each image in the batch of data. Grab the predictions for our (only) image in the batch:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-15T01:29:31.744362Z",
     "iopub.status.busy": "2020-10-15T01:29:31.743639Z",
     "iopub.status.idle": "2020-10-15T01:29:31.747116Z",
     "shell.execute_reply": "2020-10-15T01:29:31.746537Z"
    },
    "id": "2tRmdq_8CaXb"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.argmax(predictions_single[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "YFc2HbEVCaXd"
   },
   "source": [
    "And the model predicts a label as expected."
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "classification.ipynb",
   "toc_visible": true
  },
  "kernelspec": {
   "name": "python39264bit97e5c9179d77459788f16ab326f5feac",
   "display_name": "Python 3.9.2 64-bit"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.2-final"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}