{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "\n",
    "from tensorflow.keras.layers import Dense, Flatten, Conv2D\n",
    "from tensorflow.keras import Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "outputs": [],
   "source": [
    "mnist = tf.keras.datasets.mnist\n",
    "\n",
    "(x_train, y_train), (x_test, y_test) = mnist.load_data()\n",
    "x_train, x_test = x_train / 255.0, x_test / 255.0\n",
    "\n",
    "x_train = x_train[..., tf.newaxis].astype(\"float32\")\n",
    "x_test = x_test[..., tf.newaxis].astype(\"float32\")"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "outputs": [],
   "source": [
    "train_ds = tf.data.Dataset.from_tensor_slices((x_train, y_train)).shuffle(10000).batch(32)\n",
    "test_ds = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "outputs": [],
   "source": [
    "class MyModel(Model):\n",
    "    def __init__(self):\n",
    "        super(MyModel, self).__init__()\n",
    "        self.conv1 = Conv2D(32, 3, activation='relu')\n",
    "        self.flatten = Flatten()\n",
    "        self.d1 = Dense(128, activation='relu')\n",
    "        self.d2 = Dense(10)\n",
    "\n",
    "    def call(self, x):\n",
    "        x = self.conv1(x)\n",
    "        x = self.flatten(x)\n",
    "        x = self.d1(x)\n",
    "\n",
    "        return self.d2(x)\n",
    "\n",
    "model = MyModel()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "outputs": [],
   "source": [
    "loss_object = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)\n",
    "optimizer = tf.keras.optimizers.Adam()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "outputs": [],
   "source": [
    "train_loss = tf.keras.metrics.Mean(name='train_loss')\n",
    "train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')\n",
    "\n",
    "test_loss = tf.keras.metrics.Mean(name='test_loss')\n",
    "test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy')"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "outputs": [],
   "source": [
    "@tf.function\n",
    "def train_step(images, labels):\n",
    "    with tf.GradientTape() as tape:\n",
    "        predictions = model(images, training=True)\n",
    "        loss = loss_object(labels, predictions)\n",
    "\n",
    "    gradients = tape.gradient(loss, model.trainable_variables)\n",
    "    optimizer.apply_gradients(zip(gradients, model.trainable_variables))\n",
    "\n",
    "    train_loss(loss)\n",
    "    train_accuracy(labels, predictions)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "outputs": [],
   "source": [
    "@tf.function\n",
    "def test_step(images, labels):\n",
    "    predictions = model(images, training=False)\n",
    "    t_loss = loss_object(labels, predictions)\n",
    "\n",
    "    test_loss(t_loss)\n",
    "    test_accuracy(labels, predictions)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1, Loss: 0.1362500935792923, Accuracy: 95.75833129882812, Test Loss: 0.06010208651423454, Test Accuracy: 98.07999420166016\n",
      "Epoch 2, Loss: 0.04352438822388649, Accuracy: 98.65333557128906, Test Loss: 0.05184892565011978, Test Accuracy: 98.22999572753906\n",
      "Epoch 3, Loss: 0.021888718008995056, Accuracy: 99.29500579833984, Test Loss: 0.05651076138019562, Test Accuracy: 98.20999908447266\n",
      "Epoch 4, Loss: 0.014405352994799614, Accuracy: 99.55833435058594, Test Loss: 0.05141943320631981, Test Accuracy: 98.48999786376953\n",
      "Epoch 5, Loss: 0.008999002166092396, Accuracy: 99.71833038330078, Test Loss: 0.06053818389773369, Test Accuracy: 98.27999877929688\n"
     ]
    }
   ],
   "source": [
    "EPOCHS = 5\n",
    "\n",
    "for epoch in range(EPOCHS):\n",
    "    train_loss.reset_states()\n",
    "    train_accuracy.reset_states()\n",
    "    test_loss.reset_states()\n",
    "    test_accuracy.reset_states()\n",
    "\n",
    "    for images, labels in train_ds:\n",
    "        train_step(images, labels)\n",
    "\n",
    "    for test_images, test_labels in test_ds:\n",
    "        test_step(test_images, test_labels)\n",
    "\n",
    "    print(\n",
    "    f'Epoch {epoch + 1}, '\n",
    "    f'Loss: {train_loss.result()}, '\n",
    "    f'Accuracy: {train_accuracy.result() * 100}, '\n",
    "    f'Test Loss: {test_loss.result()}, '\n",
    "    f'Test Accuracy: {test_accuracy.result() * 100}'\n",
    "  )"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "outputs": [],
   "source": [],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}