initial TF2 changes

Author: kashif

1-fashion-mnist-with-keras.ipynb

@@ -9,12 +9,14 @@
    "source": [
     "# Fashion-MNIST with tf.keras\n",
     "\n",
-    "Welcome! In this lab, you'll learn how to train an image classifier train on the [Fashion-MNIST dataset](https://github.com/zalandoresearch/fashion-mnist). You'll go through all the steps, including loading the data, building and training a model, calculating the accuracy, and making predictions. Our focus here is on the code."
+    "Welcome! In this lab, you'll learn how to train an image classifier train on the [Fashion-MNIST dataset](https://github.com/zalandoresearch/fashion-mnist) using TensorFlow 2. You'll go through all the steps, including loading the data, building and training a model, calculating the accuracy, and making predictions. Our focus here is on the code.\n",
+    "\n",
+    "The biggest change to TensorFlow is that it runs with eager execution by default."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {
     "colab": {
      "autoexec": {
@@ -32,6 +34,26 @@
     "import numpy as np"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'2.0.0-preview'"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tf.__version__"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -46,7 +68,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {
     "colab": {
      "autoexec": {
@@ -75,7 +97,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {
     "colab": {
      "autoexec": {
@@ -86,7 +108,37 @@
     "colab_type": "code",
     "id": "AwxNOsCMNNGd"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Label: 6\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.image.AxesImage at 0x7fab2545ad68>"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "%matplotlib inline\n",
     "import random\n",
@@ -132,7 +184,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {
     "colab": {
      "autoexec": {
@@ -143,7 +195,16 @@
     "colab_type": "code",
     "id": "TTj2ZWMBN24i"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(60000, 28, 28)\n",
+      "(60000,)\n"
+     ]
+    }
+   ],
    "source": [
     "print(train_images.shape)\n",
     "print(train_labels.shape)"
@@ -165,7 +226,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {
     "colab": {
      "autoexec": {
@@ -208,7 +269,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {
     "colab": {
      "autoexec": {
@@ -219,7 +280,16 @@
     "colab_type": "code",
     "id": "E9yrkEENQ9Vz"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Before 9\n",
+      "After [0. 0. 0. 0. 0. 0. 0. 0. 0. 1.]\n"
+     ]
+    }
+   ],
    "source": [
     "NUM_CAT = 10\n",
     "\n",
@@ -252,7 +322,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "metadata": {
     "colab": {
      "autoexec": {
@@ -263,7 +333,26 @@
     "colab_type": "code",
     "id": "mNscbvHkUrMc"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"sequential_1\"\n",
+      "_________________________________________________________________\n",
+      "Layer (type)                 Output Shape              Param #   \n",
+      "=================================================================\n",
+      "dense_2 (Dense)              (None, 512)               401920    \n",
+      "_________________________________________________________________\n",
+      "dense_3 (Dense)              (None, 10)                5130      \n",
+      "=================================================================\n",
+      "Total params: 407,050\n",
+      "Trainable params: 407,050\n",
+      "Non-trainable params: 0\n",
+      "_________________________________________________________________\n"
+     ]
+    }
+   ],
    "source": [
     "model = tf.keras.Sequential()\n",
     "model.add(tf.keras.layers.Dense(512, activation=tf.nn.relu, input_shape=(784,)))\n",
@@ -291,7 +380,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "metadata": {
     "colab": {
      "autoexec": {
@@ -302,7 +391,34 @@
     "colab_type": "code",
     "id": "gBs0LwqcVXx6"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/5\n",
+      "60000/60000==============================] - 5s 75us/sample - loss: 0.4949 - acc: 0.8230\n",
+      "Epoch 2/5\n",
+      "60000/60000==============================] - 4s 69us/sample - loss: 0.3785 - acc: 0.8664\n",
+      "Epoch 3/5\n",
+      "60000/60000==============================] - 4s 68us/sample - loss: 0.3547 - acc: 0.8759\n",
+      "Epoch 4/5\n",
+      "60000/60000==============================] - 4s 69us/sample - loss: 0.3424 - acc: 0.8841\n",
+      "Epoch 5/5\n",
+      "60000/60000==============================] - 4s 68us/sample - loss: 0.3352 - acc: 0.8880\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<tensorflow.python.keras.callbacks.History at 0x7fab27af79b0>"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "model.fit(train_images, train_labels, epochs=5)"
    ]
@@ -320,7 +436,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "metadata": {
     "colab": {
      "autoexec": {
@@ -331,7 +447,16 @@
     "colab_type": "code",
     "id": "iuqDe4NiWBpU"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "10000/10000==============================] - 0s 44us/sample - loss: 0.4367 - acc: 0.8591\n",
+      "Test accuracy: 0.86\n"
+     ]
+    }
+   ],
    "source": [
     "loss, accuracy = model.evaluate(test_images, test_labels)\n",
     "print('Test accuracy: %.2f' % (accuracy))"
@@ -380,7 +505,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.0"
+   "version": "3.6.7"
   }
  },
  "nbformat": 4,