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 3.6.1 IPython 6.0.0 tensorflow 1.2.0
import tensorflow as tf
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
This notebook contains three different approaches for training a simple 1-hidden layer multilayer perceptron using TensorFlow:
tf.train.GradientDescentOptimizer
tf.gradients
tf.train.GradientDescentOptimizer
¶# Dataset
np.random.seed(123) # set seed for mnist shuffling
mnist = input_data.read_data_sets("./", one_hot=True)
Extracting ./train-images-idx3-ubyte.gz Extracting ./train-labels-idx1-ubyte.gz Extracting ./t10k-images-idx3-ubyte.gz Extracting ./t10k-labels-idx1-ubyte.gz
##########################
### SETTINGS
##########################
# Hyperparameters
learning_rate = 0.1
training_epochs = 10
batch_size = 64
# Architecture
n_hidden_1 = 128
n_input = 784
n_classes = 10
##########################
### GRAPH DEFINITION
##########################
g = tf.Graph()
with g.as_default():
tf.set_random_seed(123)
# 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)),
'out': tf.Variable(tf.truncated_normal([n_hidden_1, n_classes], stddev=0.1))
}
biases = {
'b1': tf.Variable(tf.zeros([n_hidden_1])),
'out': tf.Variable(tf.zeros([n_classes]))
}
# Forward Propagation
h1_z = tf.add(tf.matmul(tf_x, weights['h1']), biases['b1'])
h1_act = tf.nn.sigmoid(h1_z)
out_z = tf.matmul(h1_act, weights['out']) + biases['out']
out_act = tf.nn.softmax(out_z, name='predicted_probabilities')
out_labels = tf.argmax(out_z, axis=1, name='predicted_labels')
######################
# Forward Propagation
######################
loss = tf.nn.softmax_cross_entropy_with_logits(logits=out_z, labels=tf_y)
cost = tf.reduce_mean(loss, name='cost')
##################
# Backpropagation
##################
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
train = optimizer.minimize(cost, name='train')
##############
# Prediction
##############
correct_prediction = tf.equal(tf.argmax(tf_y, 1), out_labels)
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)
Epoch: 001 | AvgCost: 0.785 | Train/Valid ACC: 0.885/0.891 Epoch: 002 | AvgCost: 0.370 | Train/Valid ACC: 0.906/0.915 Epoch: 003 | AvgCost: 0.317 | Train/Valid ACC: 0.914/0.921 Epoch: 004 | AvgCost: 0.289 | Train/Valid ACC: 0.922/0.925 Epoch: 005 | AvgCost: 0.268 | Train/Valid ACC: 0.926/0.929 Epoch: 006 | AvgCost: 0.250 | Train/Valid ACC: 0.931/0.933 Epoch: 007 | AvgCost: 0.235 | Train/Valid ACC: 0.936/0.937 Epoch: 008 | AvgCost: 0.221 | Train/Valid ACC: 0.939/0.941 Epoch: 009 | AvgCost: 0.209 | Train/Valid ACC: 0.943/0.943 Epoch: 010 | AvgCost: 0.198 | Train/Valid ACC: 0.947/0.948 Test ACC: 0.945
tf.gradients
(low level)¶# Dataset
np.random.seed(123) # set seed for mnist shuffling
mnist = input_data.read_data_sets("./", one_hot=True)
Extracting ./train-images-idx3-ubyte.gz Extracting ./train-labels-idx1-ubyte.gz Extracting ./t10k-images-idx3-ubyte.gz Extracting ./t10k-labels-idx1-ubyte.gz
##########################
### SETTINGS
##########################
# Hyperparameters
learning_rate = 0.1
training_epochs = 10
batch_size = 64
# Architecture
n_hidden_1 = 128
n_input = 784
n_classes = 10
##########################
### GRAPH DEFINITION
##########################
g = tf.Graph()
with g.as_default():
tf.set_random_seed(123)
# 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)),
'out': tf.Variable(tf.truncated_normal([n_hidden_1, n_classes], stddev=0.1))
}
biases = {
'b1': tf.Variable(tf.zeros([n_hidden_1])),
'out': tf.Variable(tf.zeros([n_classes]))
}
######################
# Forward Propagation
######################
h1_z = tf.add(tf.matmul(tf_x, weights['h1']), biases['b1'])
h1_act = tf.nn.sigmoid(h1_z)
out_z = tf.matmul(h1_act, weights['out']) + biases['out']
out_act = tf.nn.softmax(out_z, name='predicted_probabilities')
out_labels = tf.argmax(out_z, axis=1, name='predicted_labels')
# Loss
loss = tf.nn.softmax_cross_entropy_with_logits(logits=out_z, labels=tf_y)
cost = tf.reduce_mean(loss, name='cost')
##################
# Backpropagation
##################
# Get Gradients
dc_dw_out, dc_db_out = tf.gradients(cost, [weights['out'], biases['out']])
dc_dw_1, dc_db_1 = tf.gradients(cost, [weights['h1'], biases['b1']])
# Update Weights
upd_w_1 = tf.assign(weights['h1'], weights['h1'] - learning_rate * dc_dw_1)
upd_b_1 = tf.assign(biases['b1'], biases['b1'] - learning_rate * dc_db_1)
upd_w_out = tf.assign(weights['out'], weights['out'] - learning_rate * dc_dw_out)
upd_b_out = tf.assign(biases['out'], biases['out'] - learning_rate * dc_db_out)
train = tf.group(upd_w_1, upd_b_1, upd_w_out, upd_b_out, name='train')
##############
# Prediction
##############
correct_prediction = tf.equal(tf.argmax(tf_y, 1), out_labels)
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)
Epoch: 001 | AvgCost: 0.785 | Train/Valid ACC: 0.890/0.894 Epoch: 002 | AvgCost: 0.370 | Train/Valid ACC: 0.906/0.912 Epoch: 003 | AvgCost: 0.317 | Train/Valid ACC: 0.915/0.918 Epoch: 004 | AvgCost: 0.289 | Train/Valid ACC: 0.922/0.926 Epoch: 005 | AvgCost: 0.268 | Train/Valid ACC: 0.927/0.930 Epoch: 006 | AvgCost: 0.250 | Train/Valid ACC: 0.932/0.934 Epoch: 007 | AvgCost: 0.235 | Train/Valid ACC: 0.936/0.938 Epoch: 008 | AvgCost: 0.221 | Train/Valid ACC: 0.940/0.941 Epoch: 009 | AvgCost: 0.210 | Train/Valid ACC: 0.942/0.944 Epoch: 010 | AvgCost: 0.198 | Train/Valid ACC: 0.946/0.947 Test ACC: 0.945
# Dataset
np.random.seed(123) # set seed for mnist shuffling
mnist = input_data.read_data_sets("./", one_hot=True)
Extracting ./train-images-idx3-ubyte.gz Extracting ./train-labels-idx1-ubyte.gz Extracting ./t10k-images-idx3-ubyte.gz Extracting ./t10k-labels-idx1-ubyte.gz
##########################
### SETTINGS
##########################
# Hyperparameters
learning_rate = 0.1
training_epochs = 10
batch_size = 64
# Architecture
n_hidden_1 = 128
n_input = 784
n_classes = 10
##########################
### GRAPH DEFINITION
##########################
g = tf.Graph()
with g.as_default():
tf.set_random_seed(123)
# 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)),
'out': tf.Variable(tf.truncated_normal([n_hidden_1, n_classes], stddev=0.1))
}
biases = {
'b1': tf.Variable(tf.zeros([n_hidden_1])),
'out': tf.Variable(tf.zeros([n_classes]))
}
######################
# Forward Propagation
######################
h1_z = tf.add(tf.matmul(tf_x, weights['h1']), biases['b1'])
h1_act = tf.nn.sigmoid(h1_z)
out_z = tf.matmul(h1_act, weights['out']) + biases['out']
out_act = tf.nn.softmax(out_z, name='predicted_probabilities')
out_labels = tf.argmax(out_z, axis=1, name='predicted_labels')
# Loss
loss = tf.nn.softmax_cross_entropy_with_logits(logits=out_z, labels=tf_y)
cost = tf.reduce_mean(loss, name='cost')
##################
# Backpropagation
##################
# Get Gradients
# input/output dim: [n_samples, n_classlabels]
sigma_out = (out_act - tf_y) / batch_size
# input/output dim: [n_samples, n_hidden_1]
softmax_derivative_h1 = h1_act * (1. - h1_act)
# input dim: [n_samples, n_classlabels] dot [n_classlabels, n_hidden]
# output dim: [n_samples, n_hidden]
sigma_h = (tf.matmul(sigma_out, tf.transpose(weights['out'])) *
softmax_derivative_h1)
# input dim: [n_features, n_samples] dot [n_samples, n_hidden]
# output dim: [n_features, n_hidden]
grad_w_h1 = tf.matmul(tf.transpose(tf_x), sigma_h)
grad_b_h1 = tf.reduce_sum(sigma_h, axis=0)
# input dim: [n_hidden, n_samples] dot [n_samples, n_classlabels]
# output dim: [n_hidden, n_classlabels]
grad_w_out = tf.matmul(tf.transpose(h1_act), sigma_out)
grad_b_out = tf.reduce_sum(sigma_out, axis=0)
# Update weights
upd_w_1 = tf.assign(weights['h1'], weights['h1'] - learning_rate * grad_w_h1)
upd_b_1 = tf.assign(biases['b1'], biases['b1'] - learning_rate * grad_b_h1)
upd_w_out = tf.assign(weights['out'], weights['out'] - learning_rate * grad_w_out)
upd_b_out = tf.assign(biases['out'], biases['out'] - learning_rate * grad_b_out)
train = tf.group(upd_w_1, upd_b_1, upd_w_out, upd_b_out, name='train')
##############
# Prediction
##############
correct_prediction = tf.equal(tf.argmax(tf_y, 1), out_labels)
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)
Epoch: 001 | AvgCost: 0.785 | Train/Valid ACC: 0.884/0.892 Epoch: 002 | AvgCost: 0.370 | Train/Valid ACC: 0.905/0.909 Epoch: 003 | AvgCost: 0.317 | Train/Valid ACC: 0.914/0.916 Epoch: 004 | AvgCost: 0.288 | Train/Valid ACC: 0.921/0.926 Epoch: 005 | AvgCost: 0.268 | Train/Valid ACC: 0.927/0.931 Epoch: 006 | AvgCost: 0.251 | Train/Valid ACC: 0.931/0.934 Epoch: 007 | AvgCost: 0.235 | Train/Valid ACC: 0.936/0.937 Epoch: 008 | AvgCost: 0.222 | Train/Valid ACC: 0.940/0.942 Epoch: 009 | AvgCost: 0.209 | Train/Valid ACC: 0.944/0.944 Epoch: 010 | AvgCost: 0.199 | Train/Valid ACC: 0.946/0.948 Test ACC: 0.945