StarMirror
/
data-science-ipython-notebooks
mirror of https://github.com/donnemartin/data-science-ipython-notebooks
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
data-science-ipython-notebooks/deep-learning/tensor-flow-examples/notebooks/3_neural_networks/alexnet.ipynb

346 lines
12 KiB
Python
Raw Blame History

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AlexNet in TensorFlow\n",
"\n",
"Credits: Forked from [TensorFlow-Examples](https://github.com/aymericdamien/TensorFlow-Examples) by Aymeric Damien\n",
"\n",
"## Setup\n",
"\n",
"Refer to the [setup instructions](http://nbviewer.ipython.org/github/donnemartin/data-science-ipython-notebooks/blob/master/deep-learning/tensor-flow-examples/Setup_TensorFlow.md)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"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 MINST data\n",
"import input_data\n",
"mnist = input_data.read_data_sets(\"/tmp/data/\", one_hot=True)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import tensorflow as tf"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Parameters\n",
"learning_rate = 0.001\n",
"training_iters = 300000\n",
"batch_size = 64\n",
"display_step = 100"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Network Parameters\n",
"n_input = 784 # MNIST data input (img shape: 28*28)\n",
"n_classes = 10 # MNIST total classes (0-9 digits)\n",
"dropout = 0.8 # Dropout, probability to keep units"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# tf Graph input\n",
"x = tf.placeholder(tf.float32, [None, n_input])\n",
"y = tf.placeholder(tf.float32, [None, n_classes])\n",
"keep_prob = tf.placeholder(tf.float32) # dropout (keep probability)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Create AlexNet model\n",
"def conv2d(name, l_input, w, b):\n",
" return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(l_input, w, strides=[1, 1, 1, 1], \n",
" padding='SAME'),b), name=name)\n",
"\n",
"def max_pool(name, l_input, k):\n",
" return tf.nn.max_pool(l_input, ksize=[1, k, k, 1], strides=[1, k, k, 1], \n",
" padding='SAME', name=name)\n",
"\n",
"def norm(name, l_input, lsize=4):\n",
" return tf.nn.lrn(l_input, lsize, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name=name)\n",
"\n",
"def alex_net(_X, _weights, _biases, _dropout):\n",
" # Reshape input picture\n",
" _X = tf.reshape(_X, shape=[-1, 28, 28, 1])\n",
"\n",
" # Convolution Layer\n",
" conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1'])\n",
" # Max Pooling (down-sampling)\n",
" pool1 = max_pool('pool1', conv1, k=2)\n",
" # Apply Normalization\n",
" norm1 = norm('norm1', pool1, lsize=4)\n",
" # Apply Dropout\n",
" norm1 = tf.nn.dropout(norm1, _dropout)\n",
"\n",
" # Convolution Layer\n",
" conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2'])\n",
" # Max Pooling (down-sampling)\n",
" pool2 = max_pool('pool2', conv2, k=2)\n",
" # Apply Normalization\n",
" norm2 = norm('norm2', pool2, lsize=4)\n",
" # Apply Dropout\n",
" norm2 = tf.nn.dropout(norm2, _dropout)\n",
"\n",
" # Convolution Layer\n",
" conv3 = conv2d('conv3', norm2, _weights['wc3'], _biases['bc3'])\n",
" # Max Pooling (down-sampling)\n",
" pool3 = max_pool('pool3', conv3, k=2)\n",
" # Apply Normalization\n",
" norm3 = norm('norm3', pool3, lsize=4)\n",
" # Apply Dropout\n",
" norm3 = tf.nn.dropout(norm3, _dropout)\n",
"\n",
" # Fully connected layer\n",
" # Reshape conv3 output to fit dense layer input\n",
" dense1 = tf.reshape(norm3, [-1, _weights['wd1'].get_shape().as_list()[0]]) \n",
" # Relu activation\n",
" dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc1')\n",
" \n",
" # Relu activation\n",
" dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'], name='fc2') \n",
"\n",
" # Output, class prediction\n",
" out = tf.matmul(dense2, _weights['out']) + _biases['out']\n",
" return out"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Store layers weight & bias\n",
"weights = {\n",
" 'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64])),\n",
" 'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128])),\n",
" 'wc3': tf.Variable(tf.random_normal([3, 3, 128, 256])),\n",
" 'wd1': tf.Variable(tf.random_normal([4*4*256, 1024])),\n",
" 'wd2': tf.Variable(tf.random_normal([1024, 1024])),\n",
" 'out': tf.Variable(tf.random_normal([1024, 10]))\n",
"}\n",
"biases = {\n",
" 'bc1': tf.Variable(tf.random_normal([64])),\n",
" 'bc2': tf.Variable(tf.random_normal([128])),\n",
" 'bc3': tf.Variable(tf.random_normal([256])),\n",
" 'bd1': tf.Variable(tf.random_normal([1024])),\n",
" 'bd2': tf.Variable(tf.random_normal([1024])),\n",
" 'out': tf.Variable(tf.random_normal([n_classes]))\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Construct model\n",
"pred = alex_net(x, weights, biases, keep_prob)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Define loss and optimizer\n",
"cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))\n",
"optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Evaluate model\n",
"correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))\n",
"accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Initializing the variables\n",
"init = tf.global_variables_initializer()"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Iter 6400, Minibatch Loss= 29666.185547, Training Accuracy= 0.59375\n",
"Iter 12800, Minibatch Loss= 22125.562500, Training Accuracy= 0.60938\n",
"Iter 19200, Minibatch Loss= 22631.134766, Training Accuracy= 0.59375\n",
"Iter 25600, Minibatch Loss= 18498.414062, Training Accuracy= 0.62500\n",
"Iter 32000, Minibatch Loss= 11318.283203, Training Accuracy= 0.70312\n",
"Iter 38400, Minibatch Loss= 12076.280273, Training Accuracy= 0.70312\n",
"Iter 44800, Minibatch Loss= 8195.520508, Training Accuracy= 0.82812\n",
"Iter 51200, Minibatch Loss= 5176.181641, Training Accuracy= 0.84375\n",
"Iter 57600, Minibatch Loss= 8951.896484, Training Accuracy= 0.81250\n",
"Iter 64000, Minibatch Loss= 10096.946289, Training Accuracy= 0.78125\n",
"Iter 70400, Minibatch Loss= 11466.641602, Training Accuracy= 0.68750\n",
"Iter 76800, Minibatch Loss= 7469.824219, Training Accuracy= 0.78125\n",
"Iter 83200, Minibatch Loss= 4147.449219, Training Accuracy= 0.89062\n",
"Iter 89600, Minibatch Loss= 5904.782227, Training Accuracy= 0.82812\n",
"Iter 96000, Minibatch Loss= 718.493713, Training Accuracy= 0.93750\n",
"Iter 102400, Minibatch Loss= 2184.151367, Training Accuracy= 0.93750\n",
"Iter 108800, Minibatch Loss= 2354.463135, Training Accuracy= 0.89062\n",
"Iter 115200, Minibatch Loss= 8612.959961, Training Accuracy= 0.81250\n",
"Iter 121600, Minibatch Loss= 2225.773926, Training Accuracy= 0.84375\n",
"Iter 128000, Minibatch Loss= 160.583618, Training Accuracy= 0.96875\n",
"Iter 134400, Minibatch Loss= 1524.846069, Training Accuracy= 0.93750\n",
"Iter 140800, Minibatch Loss= 3501.871094, Training Accuracy= 0.89062\n",
"Iter 147200, Minibatch Loss= 661.977051, Training Accuracy= 0.96875\n",
"Iter 153600, Minibatch Loss= 367.857788, Training Accuracy= 0.98438\n",
"Iter 160000, Minibatch Loss= 1735.458740, Training Accuracy= 0.90625\n",
"Iter 166400, Minibatch Loss= 209.320374, Training Accuracy= 0.95312\n",
"Iter 172800, Minibatch Loss= 1788.553955, Training Accuracy= 0.90625\n",
"Iter 179200, Minibatch Loss= 912.995544, Training Accuracy= 0.93750\n",
"Iter 185600, Minibatch Loss= 2534.074463, Training Accuracy= 0.87500\n",
"Iter 192000, Minibatch Loss= 73.052612, Training Accuracy= 0.96875\n",
"Iter 198400, Minibatch Loss= 1609.606323, Training Accuracy= 0.93750\n",
"Iter 204800, Minibatch Loss= 1823.219727, Training Accuracy= 0.96875\n",
"Iter 211200, Minibatch Loss= 578.051086, Training Accuracy= 0.96875\n",
"Iter 217600, Minibatch Loss= 1532.326172, Training Accuracy= 0.89062\n",
"Iter 224000, Minibatch Loss= 769.775269, Training Accuracy= 0.95312\n",
"Iter 230400, Minibatch Loss= 2614.737793, Training Accuracy= 0.92188\n",
"Iter 236800, Minibatch Loss= 938.664368, Training Accuracy= 0.95312\n",
"Iter 243200, Minibatch Loss= 1520.495605, Training Accuracy= 0.93750\n",
"Iter 249600, Minibatch Loss= 657.419739, Training Accuracy= 0.95312\n",
"Iter 256000, Minibatch Loss= 522.802124, Training Accuracy= 0.90625\n",
"Iter 262400, Minibatch Loss= 211.188477, Training Accuracy= 0.96875\n",
"Iter 268800, Minibatch Loss= 520.451172, Training Accuracy= 0.92188\n",
"Iter 275200, Minibatch Loss= 1418.759155, Training Accuracy= 0.89062\n",
"Iter 281600, Minibatch Loss= 241.748596, Training Accuracy= 0.96875\n",
"Iter 288000, Minibatch Loss= 0.000000, Training Accuracy= 1.00000\n",
"Iter 294400, Minibatch Loss= 1535.772827, Training Accuracy= 0.92188\n",
"Optimization Finished!\n",
"Testing Accuracy: 0.980469\n"
]
}
],
"source": [
"# Launch the graph\n",
"with tf.Session() as sess:\n",
" sess.run(init)\n",
" step = 1\n",
" # Keep training until reach max iterations\n",
" while step * batch_size < training_iters:\n",
" batch_xs, batch_ys = mnist.train.next_batch(batch_size)\n",
" # Fit training using batch data\n",
" sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout})\n",
" if step % display_step == 0:\n",
" # Calculate batch accuracy\n",
" acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})\n",
" # Calculate batch loss\n",
" loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})\n",
" print \"Iter \" + str(step*batch_size) + \", Minibatch Loss= \" \\\n",
" + \"{:.6f}\".format(loss) + \", Training Accuracy= \" + \"{:.5f}\".format(acc)\n",
" step += 1\n",
" print \"Optimization Finished!\"\n",
" # Calculate accuracy for 256 mnist test images\n",
" print \"Testing Accuracy:\", sess.run(accuracy, feed_dict={x: mnist.test.images[:256], \n",
" y: mnist.test.labels[:256], \n",
" keep_prob: 1.})"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"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": 0
}
Reference in New Issue View Git Blame Copy Permalink