Deep Learning Models -- A collection of various deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks.
%load_ext watermark
%watermark -a 'Sebastian Raschka' -v -p tensorflow
Sebastian Raschka CPython 3.6.0 IPython 6.0.0 tensorflow 1.1.0
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
##########################
### DATASET
##########################
mnist = input_data.read_data_sets("./", one_hot=True)
##########################
### SETTINGS
##########################
# Hyperparameters
learning_rate = 0.1
training_epochs = 10
batch_size = 64
# Architecture
n_hidden_1 = 128
n_hidden_2 = 256
n_input = 784
n_classes = 10
##########################
### GRAPH DEFINITION
##########################
g = tf.Graph()
with g.as_default():
# Input data
tf_x = tf.placeholder(tf.float32, [None, n_input], name='features')
tf_y = tf.placeholder(tf.float32, [None, n_classes], name='targets')
# Model parameters
weights = {
'h1': tf.Variable(tf.truncated_normal([n_input, n_hidden_1], stddev=0.1)),
'h2': tf.Variable(tf.truncated_normal([n_hidden_1, n_hidden_2], stddev=0.1)),
'out': tf.Variable(tf.truncated_normal([n_hidden_2, n_classes], stddev=0.1))
}
biases = {
'b1': tf.Variable(tf.zeros([n_hidden_1])),
'b2': tf.Variable(tf.zeros([n_hidden_2])),
'out': tf.Variable(tf.zeros([n_classes]))
}
# Multilayer perceptron
layer_1 = tf.add(tf.matmul(tf_x, weights['h1']), biases['b1'])
layer_1 = tf.nn.relu(layer_1)
layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
layer_2 = tf.nn.relu(layer_2)
out_layer = tf.matmul(layer_2, weights['out']) + biases['out']
# Loss and optimizer
loss = tf.nn.softmax_cross_entropy_with_logits(logits=out_layer, labels=tf_y)
cost = tf.reduce_mean(loss, name='cost')
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
train = optimizer.minimize(cost, name='train')
# Prediction
correct_prediction = tf.equal(tf.argmax(tf_y, 1), tf.argmax(out_layer, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name='accuracy')
##########################
### TRAINING & EVALUATION
##########################
with tf.Session(graph=g) as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = mnist.train.num_examples // batch_size
for i in range(total_batch):
batch_x, batch_y = mnist.train.next_batch(batch_size)
_, c = sess.run(['train', 'cost:0'], feed_dict={'features:0': batch_x,
'targets:0': batch_y})
avg_cost += c
train_acc = sess.run('accuracy:0', feed_dict={'features:0': mnist.train.images,
'targets:0': mnist.train.labels})
valid_acc = sess.run('accuracy:0', feed_dict={'features:0': mnist.validation.images,
'targets:0': mnist.validation.labels})
print("Epoch: %03d | AvgCost: %.3f" % (epoch + 1, avg_cost / (i + 1)), end="")
print(" | Train/Valid ACC: %.3f/%.3f" % (train_acc, valid_acc))
test_acc = sess.run(accuracy, feed_dict={'features:0': mnist.test.images,
'targets:0': mnist.test.labels})
print('Test ACC: %.3f' % test_acc)
Extracting ./train-images-idx3-ubyte.gz Extracting ./train-labels-idx1-ubyte.gz Extracting ./t10k-images-idx3-ubyte.gz Extracting ./t10k-labels-idx1-ubyte.gz Epoch: 001 | AvgCost: 0.349 | Train/Valid ACC: 0.945/0.944 Epoch: 002 | AvgCost: 0.164 | Train/Valid ACC: 0.962/0.961 Epoch: 003 | AvgCost: 0.118 | Train/Valid ACC: 0.973/0.969 Epoch: 004 | AvgCost: 0.092 | Train/Valid ACC: 0.979/0.971 Epoch: 005 | AvgCost: 0.075 | Train/Valid ACC: 0.983/0.974 Epoch: 006 | AvgCost: 0.061 | Train/Valid ACC: 0.985/0.976 Epoch: 007 | AvgCost: 0.052 | Train/Valid ACC: 0.988/0.976 Epoch: 008 | AvgCost: 0.043 | Train/Valid ACC: 0.991/0.978 Epoch: 009 | AvgCost: 0.037 | Train/Valid ACC: 0.993/0.980 Epoch: 010 | AvgCost: 0.030 | Train/Valid ACC: 0.994/0.979 Test ACC: 0.975
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
##########################
### DATASET
##########################
mnist = input_data.read_data_sets("./", one_hot=True)
##########################
### SETTINGS
##########################
# Hyperparameters
learning_rate = 0.1
training_epochs = 10
batch_size = 64
# Architecture
n_hidden_1 = 128
n_hidden_2 = 256
n_input = 784
n_classes = 10
##########################
### GRAPH DEFINITION
##########################
g = tf.Graph()
with g.as_default():
# Input data
tf_x = tf.placeholder(tf.float32, [None, n_input], name='features')
tf_y = tf.placeholder(tf.float32, [None, n_classes], name='targets')
# Multilayer perceptron
layer_1 = tf.layers.dense(tf_x, n_hidden_1, activation=tf.nn.relu,
kernel_initializer=tf.truncated_normal_initializer(stddev=0.1))
layer_2 = tf.layers.dense(layer_1, n_hidden_2, activation=tf.nn.relu,
kernel_initializer=tf.truncated_normal_initializer(stddev=0.1))
out_layer = tf.layers.dense(layer_2, n_classes, activation=None)
# Loss and optimizer
loss = tf.nn.softmax_cross_entropy_with_logits(logits=out_layer, labels=tf_y)
cost = tf.reduce_mean(loss, name='cost')
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
train = optimizer.minimize(cost, name='train')
# Prediction
correct_prediction = tf.equal(tf.argmax(tf_y, 1), tf.argmax(out_layer, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name='accuracy')
##########################
### TRAINING & EVALUATION
##########################
with tf.Session(graph=g) as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = mnist.train.num_examples // batch_size
for i in range(total_batch):
batch_x, batch_y = mnist.train.next_batch(batch_size)
_, c = sess.run(['train', 'cost:0'], feed_dict={'features:0': batch_x,
'targets:0': batch_y})
avg_cost += c
train_acc = sess.run('accuracy:0', feed_dict={'features:0': mnist.train.images,
'targets:0': mnist.train.labels})
valid_acc = sess.run('accuracy:0', feed_dict={'features:0': mnist.validation.images,
'targets:0': mnist.validation.labels})
print("Epoch: %03d | AvgCost: %.3f" % (epoch + 1, avg_cost / (i + 1)), end="")
print(" | Train/Valid ACC: %.3f/%.3f" % (train_acc, valid_acc))
test_acc = sess.run('accuracy:0', feed_dict={'features:0': mnist.test.images,
'targets:0': mnist.test.labels})
print('Test ACC: %.3f' % test_acc)
Extracting ./train-images-idx3-ubyte.gz Extracting ./train-labels-idx1-ubyte.gz Extracting ./t10k-images-idx3-ubyte.gz Extracting ./t10k-labels-idx1-ubyte.gz Epoch: 001 | AvgCost: 0.344 | Train/Valid ACC: 0.946/0.946 Epoch: 002 | AvgCost: 0.159 | Train/Valid ACC: 0.965/0.965 Epoch: 003 | AvgCost: 0.115 | Train/Valid ACC: 0.973/0.969 Epoch: 004 | AvgCost: 0.090 | Train/Valid ACC: 0.979/0.973 Epoch: 005 | AvgCost: 0.073 | Train/Valid ACC: 0.978/0.971 Epoch: 006 | AvgCost: 0.062 | Train/Valid ACC: 0.985/0.975 Epoch: 007 | AvgCost: 0.051 | Train/Valid ACC: 0.990/0.977 Epoch: 008 | AvgCost: 0.043 | Train/Valid ACC: 0.992/0.979 Epoch: 009 | AvgCost: 0.036 | Train/Valid ACC: 0.993/0.978 Epoch: 010 | AvgCost: 0.030 | Train/Valid ACC: 0.991/0.975 Test ACC: 0.975