{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "Deep Learning Models -- A collection of various deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks.\n", "- Author: Sebastian Raschka\n", "- GitHub Repository: https://github.com/rasbt/deeplearning-models" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Sebastian Raschka \n", "\n", "CPython 3.6.1\n", "IPython 6.0.0\n", "\n", "tensorflow 1.2.0\n" ] } ], "source": [ "%load_ext watermark\n", "%watermark -a 'Sebastian Raschka' -v -p tensorflow" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Model Zoo -- Softmax Regression" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Implementation of softmax regression (multinomial logistic regression)." ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Extracting ./train-images-idx3-ubyte.gz\n", "Extracting ./train-labels-idx1-ubyte.gz\n", "Extracting ./t10k-images-idx3-ubyte.gz\n", "Extracting ./t10k-labels-idx1-ubyte.gz\n", "Epoch: 001 | AvgCost: 0.476 | Train/Valid ACC: 0.903/0.909\n", "Epoch: 002 | AvgCost: 0.339 | Train/Valid ACC: 0.911/0.918\n", "Epoch: 003 | AvgCost: 0.320 | Train/Valid ACC: 0.915/0.922\n", "Epoch: 004 | AvgCost: 0.309 | Train/Valid ACC: 0.918/0.923\n", "Epoch: 005 | AvgCost: 0.301 | Train/Valid ACC: 0.918/0.922\n", "Epoch: 006 | AvgCost: 0.296 | Train/Valid ACC: 0.919/0.922\n", "Epoch: 007 | AvgCost: 0.291 | Train/Valid ACC: 0.921/0.925\n", "Epoch: 008 | AvgCost: 0.287 | Train/Valid ACC: 0.922/0.925\n", "Epoch: 009 | AvgCost: 0.286 | Train/Valid ACC: 0.922/0.926\n", "Epoch: 010 | AvgCost: 0.283 | Train/Valid ACC: 0.923/0.926\n", "Epoch: 011 | AvgCost: 0.282 | Train/Valid ACC: 0.923/0.924\n", "Epoch: 012 | AvgCost: 0.278 | Train/Valid ACC: 0.925/0.927\n", "Epoch: 013 | AvgCost: 0.278 | Train/Valid ACC: 0.925/0.928\n", "Epoch: 014 | AvgCost: 0.276 | Train/Valid ACC: 0.925/0.925\n", "Epoch: 015 | AvgCost: 0.276 | Train/Valid ACC: 0.926/0.928\n", "Epoch: 016 | AvgCost: 0.274 | Train/Valid ACC: 0.927/0.927\n", "Epoch: 017 | AvgCost: 0.270 | Train/Valid ACC: 0.927/0.925\n", "Epoch: 018 | AvgCost: 0.273 | Train/Valid ACC: 0.927/0.930\n", "Epoch: 019 | AvgCost: 0.270 | Train/Valid ACC: 0.927/0.929\n", "Epoch: 020 | AvgCost: 0.268 | Train/Valid ACC: 0.927/0.927\n", "Epoch: 021 | AvgCost: 0.268 | Train/Valid ACC: 0.927/0.926\n", "Epoch: 022 | AvgCost: 0.270 | Train/Valid ACC: 0.928/0.926\n", "Epoch: 023 | AvgCost: 0.268 | Train/Valid ACC: 0.927/0.926\n", "Epoch: 024 | AvgCost: 0.266 | Train/Valid ACC: 0.929/0.926\n", "Epoch: 025 | AvgCost: 0.261 | Train/Valid ACC: 0.927/0.926\n", "Epoch: 026 | AvgCost: 0.269 | Train/Valid ACC: 0.929/0.927\n", "Epoch: 027 | AvgCost: 0.265 | Train/Valid ACC: 0.928/0.928\n", "Epoch: 028 | AvgCost: 0.261 | Train/Valid ACC: 0.929/0.928\n", "Epoch: 029 | AvgCost: 0.266 | Train/Valid ACC: 0.930/0.926\n", "Epoch: 030 | AvgCost: 0.261 | Train/Valid ACC: 0.929/0.924\n", "Test ACC: 0.925\n" ] } ], "source": [ "import tensorflow as tf\n", "from tensorflow.examples.tutorials.mnist import input_data\n", "\n", "\n", "##########################\n", "### DATASET\n", "##########################\n", "\n", "mnist = input_data.read_data_sets(\"./\", one_hot=True)\n", "\n", "\n", "##########################\n", "### SETTINGS\n", "##########################\n", "\n", "# Hyperparameters\n", "learning_rate = 0.5\n", "training_epochs = 30\n", "batch_size = 256\n", "\n", "# Architecture\n", "n_features = 784\n", "n_classes = 10\n", "\n", "\n", "##########################\n", "### GRAPH DEFINITION\n", "##########################\n", "\n", "g = tf.Graph()\n", "with g.as_default():\n", "\n", " # Input data\n", " tf_x = tf.placeholder(tf.float32, [None, n_features])\n", " tf_y = tf.placeholder(tf.float32, [None, n_classes])\n", "\n", " # Model parameters\n", " params = {\n", " 'weights': tf.Variable(tf.zeros(shape=[n_features, n_classes],\n", " dtype=tf.float32), name='weights'),\n", " 'bias': tf.Variable([[n_classes]], dtype=tf.float32, name='bias')}\n", "\n", " # Softmax regression\n", " linear = tf.matmul(tf_x, params['weights']) + params['bias']\n", " pred_proba = tf.nn.softmax(linear, name='predict_probas')\n", " \n", " # Loss and optimizer\n", " cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(\n", " logits=linear, labels=tf_y), name='cost')\n", " optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)\n", " train = optimizer.minimize(cost, name='train')\n", "\n", " # Class prediction\n", " pred_labels = tf.argmax(pred_proba, 1, name='predict_labels')\n", " correct_prediction = tf.equal(tf.argmax(tf_y, 1), pred_labels)\n", " accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name='accuracy')\n", "\n", " \n", "##########################\n", "### TRAINING & EVALUATION\n", "##########################\n", "\n", "with tf.Session(graph=g) as sess:\n", " sess.run(tf.global_variables_initializer())\n", "\n", " for epoch in range(training_epochs):\n", " avg_cost = 0.\n", " total_batch = mnist.train.num_examples // batch_size\n", "\n", " for i in range(total_batch):\n", " batch_x, batch_y = mnist.train.next_batch(batch_size)\n", " _, c = sess.run(['train', 'cost:0'], feed_dict={tf_x: batch_x,\n", " tf_y: batch_y})\n", " avg_cost += c\n", " \n", " train_acc = sess.run('accuracy:0', feed_dict={tf_x: mnist.train.images,\n", " tf_y: mnist.train.labels})\n", " valid_acc = sess.run('accuracy:0', feed_dict={tf_x: mnist.validation.images,\n", " tf_y: mnist.validation.labels}) \n", " \n", " print(\"Epoch: %03d | AvgCost: %.3f\" % (epoch + 1, avg_cost / (i + 1)), end=\"\")\n", " print(\" | Train/Valid ACC: %.3f/%.3f\" % (train_acc, valid_acc))\n", " \n", " test_acc = sess.run(accuracy, feed_dict={tf_x: mnist.test.images,\n", " tf_y: mnist.test.labels})\n", " print('Test ACC: %.3f' % test_acc)" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.1" } }, "nbformat": 4, "nbformat_minor": 2 }