Add latest code

fashion-mnist-with-pytorch-93-accuracy.ipynb

@@ -19,7 +19,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 1,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -53,7 +53,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 2,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -219,22 +219,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 4,
    "metadata": {
     "colab": {},
     "colab_type": "code",
     "id": "zM618_wYGM0n"
    },
-   "outputs": [
+   "outputs": [],
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/ta180m/git/PyTorch/.venv/lib/python3.9/site-packages/torchvision/datasets/mnist.py:498: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at  /pytorch/torch/csrc/utils/tensor_numpy.cpp:180.)\n",
-      "  return torch.from_numpy(parsed.astype(m[2], copy=False)).view(*s)\n"
-     ]
-    }
-   ],
    "source": [
     "\n",
     "train_set = torchvision.datasets.FashionMNIST(\"./data\", download=True, transform=\n",
@@ -246,7 +237,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 5,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -279,7 +270,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 6,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -415,7 +406,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 7,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -427,11 +418,10 @@
    },
    "outputs": [
     {
-     "name": "stdout",
      "output_type": "stream",
+     "name": "stdout",
      "text": [
-      "<class 'torch.Tensor'> <class 'torch.Tensor'>\n",
+      "<class 'torch.Tensor'> <class 'torch.Tensor'>\ntorch.Size([10, 1, 28, 28]) torch.Size([10])\n"
-      "torch.Size([10, 1, 28, 28]) torch.Size([10])\n"
      ]
     }
    ],
@@ -525,7 +515,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 8,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -998,9 +988,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.6"
+   "version": "3.9.6-final"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}

nn_tutorial.ipynb

@@ -67,7 +67,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "metadata": {
     "collapsed": false,
     "jupyter": {
@@ -103,7 +103,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 6,
    "metadata": {
     "collapsed": false,
     "jupyter": {
@@ -119,6 +119,23 @@
     "        ((x_train, y_train), (x_valid, y_valid), _) = pickle.load(f, encoding=\"latin-1\")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "[[0. 0. 0. ... 0. 0. 0.]\n [0. 0. 0. ... 0. 0. 0.]\n [0. 0. 0. ... 0. 0. 0.]\n ...\n [0. 0. 0. ... 0. 0. 0.]\n [0. 0. 0. ... 0. 0. 0.]\n [0. 0. 0. ... 0. 0. 0.]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(x_valid)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -1920,9 +1937,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.6"
+   "version": "3.9.6-final"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}

quickstart_tutorial.ipynb

@@ -45,7 +45,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "metadata": {
     "collapsed": false,
     "jupyter": {
@@ -79,23 +79,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "metadata": {
     "collapsed": false,
     "jupyter": {
      "outputs_hidden": false
     }
    },
-   "outputs": [
+   "outputs": [],
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/ta180m/git/PyTorch/.venv/lib/python3.9/site-packages/torchvision/datasets/mnist.py:498: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at  /pytorch/torch/csrc/utils/tensor_numpy.cpp:180.)\n",
-      "  return torch.from_numpy(parsed.astype(m[2], copy=False)).view(*s)\n"
-     ]
-    }
-   ],
    "source": [
     "# Download training data from open datasets.\n",
     "training_data = datasets.FashionMNIST(\n",
@@ -124,6 +115,26 @@
     "\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "torchvision.datasets.mnist.FashionMNIST"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 6
+    }
+   ],
+   "source": [
+    "type(training_data)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 23,
@@ -770,9 +781,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.6"
+   "version": "3.9.6-final"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}