|
@@ -0,0 +1,297 @@
|
|
|
+{
|
|
|
+ "cells": [
|
|
|
+ {
|
|
|
+ "cell_type": "markdown",
|
|
|
+ "metadata": {},
|
|
|
+ "source": [
|
|
|
+ "# Neural Network with Eager API\n",
|
|
|
+ "\n",
|
|
|
+ "Build a 2-hidden layers fully connected neural network (a.k.a multilayer perceptron) with TensorFlow's Eager API.\n",
|
|
|
+ "\n",
|
|
|
+ "This example is using some of TensorFlow higher-level wrappers (tf.estimators, tf.layers, tf.metrics, ...), you can check 'neural_network_raw' example for a raw, and more detailed TensorFlow implementation.\n",
|
|
|
+ "\n",
|
|
|
+ "- Author: Aymeric Damien\n",
|
|
|
+ "- Project: https://github.com/aymericdamien/TensorFlow-Examples/"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "markdown",
|
|
|
+ "metadata": {},
|
|
|
+ "source": [
|
|
|
+ "## Neural Network Overview\n",
|
|
|
+ "\n",
|
|
|
+ "<img src=\"http://cs231n.github.io/assets/nn1/neural_net2.jpeg\" alt=\"nn\" style=\"width: 400px;\"/>\n",
|
|
|
+ "\n",
|
|
|
+ "## MNIST Dataset Overview\n",
|
|
|
+ "\n",
|
|
|
+ "This example is using MNIST handwritten digits. The dataset contains 60,000 examples for training and 10,000 examples for testing. The digits have been size-normalized and centered in a fixed-size image (28x28 pixels) with values from 0 to 1. For simplicity, each image has been flattened and converted to a 1-D numpy array of 784 features (28*28).\n",
|
|
|
+ "\n",
|
|
|
+ "\n",
|
|
|
+ "\n",
|
|
|
+ "More info: http://yann.lecun.com/exdb/mnist/"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 1,
|
|
|
+ "metadata": {
|
|
|
+ "collapsed": true
|
|
|
+ },
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "from __future__ import print_function\n",
|
|
|
+ "\n",
|
|
|
+ "import tensorflow as tf\n",
|
|
|
+ "import tensorflow.contrib.eager as tfe"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 2,
|
|
|
+ "metadata": {
|
|
|
+ "collapsed": true
|
|
|
+ },
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "# Set Eager API\n",
|
|
|
+ "tfe.enable_eager_execution()"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 3,
|
|
|
+ "metadata": {
|
|
|
+ "collapsed": false
|
|
|
+ },
|
|
|
+ "outputs": [
|
|
|
+ {
|
|
|
+ "name": "stdout",
|
|
|
+ "output_type": "stream",
|
|
|
+ "text": [
|
|
|
+ "Extracting /tmp/data/train-images-idx3-ubyte.gz\n",
|
|
|
+ "Extracting /tmp/data/train-labels-idx1-ubyte.gz\n",
|
|
|
+ "Extracting /tmp/data/t10k-images-idx3-ubyte.gz\n",
|
|
|
+ "Extracting /tmp/data/t10k-labels-idx1-ubyte.gz\n"
|
|
|
+ ]
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "# Import MNIST data\n",
|
|
|
+ "from tensorflow.examples.tutorials.mnist import input_data\n",
|
|
|
+ "mnist = input_data.read_data_sets(\"/tmp/data/\", one_hot=False)"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 4,
|
|
|
+ "metadata": {
|
|
|
+ "collapsed": true
|
|
|
+ },
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "# Parameters\n",
|
|
|
+ "learning_rate = 0.001\n",
|
|
|
+ "num_steps = 1000\n",
|
|
|
+ "batch_size = 128\n",
|
|
|
+ "display_step = 100\n",
|
|
|
+ "\n",
|
|
|
+ "# Network Parameters\n",
|
|
|
+ "n_hidden_1 = 256 # 1st layer number of neurons\n",
|
|
|
+ "n_hidden_2 = 256 # 2nd layer number of neurons\n",
|
|
|
+ "num_input = 784 # MNIST data input (img shape: 28*28)\n",
|
|
|
+ "num_classes = 10 # MNIST total classes (0-9 digits)"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 5,
|
|
|
+ "metadata": {
|
|
|
+ "collapsed": true
|
|
|
+ },
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "# Using TF Dataset to split data into batches\n",
|
|
|
+ "dataset = tf.data.Dataset.from_tensor_slices(\n",
|
|
|
+ " (mnist.train.images, mnist.train.labels)).batch(batch_size)\n",
|
|
|
+ "dataset_iter = tfe.Iterator(dataset)"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 6,
|
|
|
+ "metadata": {
|
|
|
+ "collapsed": true
|
|
|
+ },
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "# Define the neural network. To use eager API and tf.layers API together,\n",
|
|
|
+ "# we must instantiate a tfe.Network class as follow:\n",
|
|
|
+ "class NeuralNet(tfe.Network):\n",
|
|
|
+ " def __init__(self):\n",
|
|
|
+ " # Define each layer\n",
|
|
|
+ " super(NeuralNet, self).__init__()\n",
|
|
|
+ " # Hidden fully connected layer with 256 neurons\n",
|
|
|
+ " self.layer1 = self.track_layer(\n",
|
|
|
+ " tf.layers.Dense(n_hidden_1, activation=tf.nn.relu))\n",
|
|
|
+ " # Hidden fully connected layer with 256 neurons\n",
|
|
|
+ " self.layer2 = self.track_layer(\n",
|
|
|
+ " tf.layers.Dense(n_hidden_2, activation=tf.nn.relu))\n",
|
|
|
+ " # Output fully connected layer with a neuron for each class\n",
|
|
|
+ " self.out_layer = self.track_layer(tf.layers.Dense(num_classes))\n",
|
|
|
+ "\n",
|
|
|
+ " def call(self, x):\n",
|
|
|
+ " x = self.layer1(x)\n",
|
|
|
+ " x = self.layer2(x)\n",
|
|
|
+ " return self.out_layer(x)\n",
|
|
|
+ "\n",
|
|
|
+ "\n",
|
|
|
+ "neural_net = NeuralNet()"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 7,
|
|
|
+ "metadata": {
|
|
|
+ "collapsed": true
|
|
|
+ },
|
|
|
+ "outputs": [],
|
|
|
+ "source": [
|
|
|
+ "# Cross-Entropy loss function\n",
|
|
|
+ "def loss_fn(inference_fn, inputs, labels):\n",
|
|
|
+ " # Using sparse_softmax cross entropy\n",
|
|
|
+ " return tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(\n",
|
|
|
+ " logits=inference_fn(inputs), labels=labels))\n",
|
|
|
+ "\n",
|
|
|
+ "\n",
|
|
|
+ "# Calculate accuracy\n",
|
|
|
+ "def accuracy_fn(inference_fn, inputs, labels):\n",
|
|
|
+ " prediction = tf.nn.softmax(inference_fn(inputs))\n",
|
|
|
+ " correct_pred = tf.equal(tf.argmax(prediction, 1), labels)\n",
|
|
|
+ " return tf.reduce_mean(tf.cast(correct_pred, tf.float32))\n",
|
|
|
+ "\n",
|
|
|
+ "\n",
|
|
|
+ "# SGD Optimizer\n",
|
|
|
+ "optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)\n",
|
|
|
+ "\n",
|
|
|
+ "# Compute gradients\n",
|
|
|
+ "grad = tfe.implicit_gradients(loss_fn)"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 8,
|
|
|
+ "metadata": {
|
|
|
+ "collapsed": false
|
|
|
+ },
|
|
|
+ "outputs": [
|
|
|
+ {
|
|
|
+ "name": "stdout",
|
|
|
+ "output_type": "stream",
|
|
|
+ "text": [
|
|
|
+ "Initial loss= 2.340397596\n",
|
|
|
+ "Step: 0001 loss= 2.340397596 accuracy= 0.0703\n",
|
|
|
+ "Step: 0100 loss= 0.586046159 accuracy= 0.8305\n",
|
|
|
+ "Step: 0200 loss= 0.253318846 accuracy= 0.9282\n",
|
|
|
+ "Step: 0300 loss= 0.214748293 accuracy= 0.9377\n",
|
|
|
+ "Step: 0400 loss= 0.180644721 accuracy= 0.9466\n",
|
|
|
+ "Step: 0500 loss= 0.137285724 accuracy= 0.9591\n",
|
|
|
+ "Step: 0600 loss= 0.119845696 accuracy= 0.9636\n",
|
|
|
+ "Step: 0700 loss= 0.113618039 accuracy= 0.9665\n",
|
|
|
+ "Step: 0800 loss= 0.109642141 accuracy= 0.9676\n",
|
|
|
+ "Step: 0900 loss= 0.085067607 accuracy= 0.9746\n",
|
|
|
+ "Step: 1000 loss= 0.079819344 accuracy= 0.9754\n"
|
|
|
+ ]
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "# Training\n",
|
|
|
+ "average_loss = 0.\n",
|
|
|
+ "average_acc = 0.\n",
|
|
|
+ "for step in range(num_steps):\n",
|
|
|
+ "\n",
|
|
|
+ " # Iterate through the dataset\n",
|
|
|
+ " try:\n",
|
|
|
+ " d = dataset_iter.next()\n",
|
|
|
+ " except StopIteration:\n",
|
|
|
+ " # Refill queue\n",
|
|
|
+ " dataset_iter = tfe.Iterator(dataset)\n",
|
|
|
+ " d = dataset_iter.next()\n",
|
|
|
+ "\n",
|
|
|
+ " # Images\n",
|
|
|
+ " x_batch = d[0]\n",
|
|
|
+ " # Labels\n",
|
|
|
+ " y_batch = tf.cast(d[1], dtype=tf.int64)\n",
|
|
|
+ "\n",
|
|
|
+ " # Compute the batch loss\n",
|
|
|
+ " batch_loss = loss_fn(neural_net, x_batch, y_batch)\n",
|
|
|
+ " average_loss += batch_loss\n",
|
|
|
+ " # Compute the batch accuracy\n",
|
|
|
+ " batch_accuracy = accuracy_fn(neural_net, x_batch, y_batch)\n",
|
|
|
+ " average_acc += batch_accuracy\n",
|
|
|
+ "\n",
|
|
|
+ " if step == 0:\n",
|
|
|
+ " # Display the initial cost, before optimizing\n",
|
|
|
+ " print(\"Initial loss= {:.9f}\".format(average_loss))\n",
|
|
|
+ "\n",
|
|
|
+ " # Update the variables following gradients info\n",
|
|
|
+ " optimizer.apply_gradients(grad(neural_net, x_batch, y_batch))\n",
|
|
|
+ "\n",
|
|
|
+ " # Display info\n",
|
|
|
+ " if (step + 1) % display_step == 0 or step == 0:\n",
|
|
|
+ " if step > 0:\n",
|
|
|
+ " average_loss /= display_step\n",
|
|
|
+ " average_acc /= display_step\n",
|
|
|
+ " print(\"Step:\", '%04d' % (step + 1), \" loss=\",\n",
|
|
|
+ " \"{:.9f}\".format(average_loss), \" accuracy=\",\n",
|
|
|
+ " \"{:.4f}\".format(average_acc))\n",
|
|
|
+ " average_loss = 0.\n",
|
|
|
+ " average_acc = 0."
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "cell_type": "code",
|
|
|
+ "execution_count": 9,
|
|
|
+ "metadata": {
|
|
|
+ "collapsed": false
|
|
|
+ },
|
|
|
+ "outputs": [
|
|
|
+ {
|
|
|
+ "name": "stdout",
|
|
|
+ "output_type": "stream",
|
|
|
+ "text": [
|
|
|
+ "Testset Accuracy: 0.9719\n"
|
|
|
+ ]
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "# Evaluate model on the test image set\n",
|
|
|
+ "testX = mnist.test.images\n",
|
|
|
+ "testY = mnist.test.labels\n",
|
|
|
+ "\n",
|
|
|
+ "test_acc = accuracy_fn(neural_net, testX, testY)\n",
|
|
|
+ "print(\"Testset Accuracy: {:.4f}\".format(test_acc))"
|
|
|
+ ]
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "metadata": {
|
|
|
+ "kernelspec": {
|
|
|
+ "display_name": "Python [default]",
|
|
|
+ "language": "python",
|
|
|
+ "name": "python2"
|
|
|
+ },
|
|
|
+ "language_info": {
|
|
|
+ "codemirror_mode": {
|
|
|
+ "name": "ipython",
|
|
|
+ "version": 2
|
|
|
+ },
|
|
|
+ "file_extension": ".py",
|
|
|
+ "mimetype": "text/x-python",
|
|
|
+ "name": "python",
|
|
|
+ "nbconvert_exporter": "python",
|
|
|
+ "pygments_lexer": "ipython2",
|
|
|
+ "version": "2.7.12"
|
|
|
+ }
|
|
|
+ },
|
|
|
+ "nbformat": 4,
|
|
|
+ "nbformat_minor": 1
|
|
|
+}
|