wehub-resource-sync
208 lines
7.5 KiB
Plaintext
208 lines
7.5 KiB
Plaintext
{
|
|
"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
|
|
}
|