def run_training():
data_sets = data_mnist.read_data_sets()
with tf.Graph().as_default():
images_placeholder, labels_placeholder = placeholder_inputs(FLAGS.batch_size)
logits = mnist.inference(images_placeholder, FLAGS.hidden1, FLAGS.hidden2)
loss = mnist.loss(logits, labels_placeholder)
train_op = mnist.training(loss, FLAGS.learning_rate)
eval_correct = mnist.evaluation(logits, labels_placeholder)
summary_op = tf.merge_all_summaries()
saver = tf.train.Saver()
sess = tf.Session()
sess.run(tf.initialize_all_variables())
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph)
# Start the training loop.
for step in xrange(FLAGS.max_steps):
start_time = time.time()
feed_dict = fill_feed_dict(data_sets.train, images_placeholder, labels_placeholder)
_, loss_value = sess.run([train_op, loss], feed_dict=feed_dict)
duration = time.time() - start_time
if step % 100 == 0:
print('Step %d: loss = %.2f (%.3f sec)' % (step, loss_value, duration))
summary_str = sess.run(summary_op, feed_dict=feed_dict)
summary_writer.add_summary(summary_str, step)
summary_writer.flush()
if (step + 1) % 1000 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_file = os.path.join(FLAGS.train_dir, 'checkpoint')
saver.save(sess, checkpoint_file, global_step=step)
do_eval(sess,eval_correct, images_placeholder, labels_placeholder, data_sets.train)
do_eval(sess, eval_correct, images_placeholder, labels_placeholder, data_sets.validation)
do_eval(sess, eval_correct, images_placeholder, labels_placeholder, data_sets.test)
def test_mnist():
mnist = data_mnist.read_data_sets(one_hot=True)
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
y_pred = residual_network(x, 10)
cross_entropy = -tf.reduce_sum(y * tf.log(y_pred))
optimizer = tf.train.AdamOptimizer(1e-3).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, 'float'))
sess = tf.Session()
sess.run(tf.initialize_all_variables())
# %% We'll train in minibatches and report accuracy:
batch_size = 50
n_epochs = 5
for epoch_i in range(n_epochs):
# Training
train_accuracy = 0
for batch_i in range(mnist.train.num_examples // batch_size):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
local_accuracy = sess.run([optimizer, accuracy],
feed_dict={
x: batch_xs,
y: batch_ys
})[1]
print(local_accuracy)
train_accuracy += local_accuracy
train_accuracy /= (mnist.train.num_examples // batch_size)
# Validation
valid_accuracy = 0
for batch_i in range(mnist.validation.num_examples // batch_size):
batch_xs, batch_ys = mnist.validation.next_batch(batch_size)
valid_accuracy += sess.run(accuracy,
feed_dict={
x: batch_xs,
y: batch_ys
})
valid_accuracy /= (mnist.validation.num_examples // batch_size)
print('epoch:', epoch_i, ', train:', train_accuracy, ', valid:',
valid_accuracy)
def run_training():
data_sets = data_mnist.read_data_sets()
with tf.Graph().as_default():
images_placeholder, labels_placeholder = placeholder_inputs(
FLAGS.batch_size)
logits = mnist.inference(images_placeholder, FLAGS.hidden1,
FLAGS.hidden2)
loss = mnist.loss(logits, labels_placeholder)
train_op = mnist.training(loss, FLAGS.learning_rate)
eval_correct = mnist.evaluation(logits, labels_placeholder)
summary_op = tf.merge_all_summaries()
saver = tf.train.Saver()
sess = tf.Session()
sess.run(tf.initialize_all_variables())
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph)
# Start the training loop.
for step in xrange(FLAGS.max_steps):
start_time = time.time()
feed_dict = fill_feed_dict(data_sets.train, images_placeholder,
labels_placeholder)
_, loss_value = sess.run([train_op, loss], feed_dict=feed_dict)
duration = time.time() - start_time
if step % 100 == 0:
print('Step %d: loss = %.2f (%.3f sec)' %
(step, loss_value, duration))
summary_str = sess.run(summary_op, feed_dict=feed_dict)
summary_writer.add_summary(summary_str, step)
summary_writer.flush()
if (step + 1) % 1000 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_file = os.path.join(FLAGS.train_dir, 'checkpoint')
saver.save(sess, checkpoint_file, global_step=step)
do_eval(sess, eval_correct, images_placeholder,
labels_placeholder, data_sets.train)
do_eval(sess, eval_correct, images_placeholder,
labels_placeholder, data_sets.validation)
do_eval(sess, eval_correct, images_placeholder,
labels_placeholder, data_sets.test)
def main(_=None):
image_placeholder = tf.placeholder(tf.float32, [BATCH_SIZE, 28 * 28])
labels_placeholder = tf.placeholder(tf.float32, [BATCH_SIZE, 10])
if FLAGS.model == 'full':
result = multilayer_fully_connected(image_placeholder,
labels_placeholder)
elif FLAGS.model == 'conv':
result = lenet5(image_placeholder, labels_placeholder)
else:
raise ValueError('model must be full or conv: %s' % FLAGS.model)
accuracy = result.softmax.evaluate_classifier(labels_placeholder,
phase=pt.Phase.test)
optimizer = tf.train.GradientDescentOptimizer(0.01)
train_op = pt.apply_optimizer(optimizer, losses=[result.loss])
# 数据
mnist = data_mnist.read_data_sets(one_hot=True)
runner = pt.train.Runner(save_path=FLAGS.save_path)
with tf.Session():
for epoch in xrange(10):
# 训练
runner.train_model(
train_op,
result.loss,
EPOCH_SIZE,
feed_vars=(image_placeholder, labels_placeholder),
feed_data=pt.train.feed_numpy(BATCH_SIZE, mnist.train.images,
mnist.train.labels),
print_every=100)
# 正确率
classification_accuracy = runner.evaluate_model(
accuracy,
TEST_SIZE,
feed_vars=(image_placeholder, labels_placeholder),
feed_data=pt.train.feed_numpy(BATCH_SIZE, mnist.test.images,
mnist.test.labels))
print('Accuracy after %d epoch %g%%' %
(epoch + 1, classification_accuracy * 100))
def main(_=None):
image_placeholder = tf.placeholder(tf.float32, [BATCH_SIZE, 28*28])
labels_placeholder = tf.placeholder(tf.float32, [BATCH_SIZE, 10])
if FLAGS.model == 'full':
result = multilayer_fully_connected(image_placeholder, labels_placeholder)
elif FLAGS.model == 'conv':
result = lenet5(image_placeholder, labels_placeholder)
else:
raise ValueError('model must be full or conv: %s' % FLAGS.model)
accuracy = result.softmax.evaluate_classifier(labels_placeholder, phase=pt.Phase.test)
optimizer = tf.train.GradientDescentOptimizer(0.01)
train_op = pt.apply_optimizer(optimizer, losses=[result.loss])
# 数据
mnist = data_mnist.read_data_sets(one_hot=True)
runner = pt.train.Runner(save_path=FLAGS.save_path)
with tf.Session():
for epoch in xrange(10):
# 训练
runner.train_model(
train_op,
result.loss,
EPOCH_SIZE,
feed_vars=(image_placeholder, labels_placeholder),
feed_data= pt.train.feed_numpy(BATCH_SIZE, mnist.train.images, mnist.train.labels),
print_every=100)
# 正确率
classification_accuracy = runner.evaluate_model(
accuracy,
TEST_SIZE,
feed_vars=(image_placeholder, labels_placeholder),
feed_data=pt.train.feed_numpy(BATCH_SIZE, mnist.test.images, mnist.test.labels))
print('Accuracy after %d epoch %g%%' % (epoch + 1, classification_accuracy * 100))
def test_mnist():
mnist = data_mnist.read_data_sets(one_hot=True)
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
y_pred = residual_network(x, 10)
cross_entropy = -tf.reduce_sum(y * tf.log(y_pred))
optimizer = tf.train.AdamOptimizer(1e-3).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, 'float'))
sess = tf.Session()
sess.run(tf.initialize_all_variables())
# %% We'll train in minibatches and report accuracy:
batch_size = 50
n_epochs = 5
for epoch_i in range(n_epochs):
# Training
train_accuracy = 0
for batch_i in range(mnist.train.num_examples // batch_size):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
local_accuracy = sess.run([optimizer, accuracy], feed_dict={x: batch_xs, y: batch_ys})[1]
print(local_accuracy)
train_accuracy += local_accuracy
train_accuracy /= (mnist.train.num_examples // batch_size)
# Validation
valid_accuracy = 0
for batch_i in range(mnist.validation.num_examples // batch_size):
batch_xs, batch_ys = mnist.validation.next_batch(batch_size)
valid_accuracy += sess.run(accuracy, feed_dict={x: batch_xs,y: batch_ys})
valid_accuracy /= (mnist.validation.num_examples // batch_size)
print('epoch:', epoch_i, ', train:', train_accuracy, ', valid:', valid_accuracy)
# 训练
with graph.as_default():
# GPU
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.8
config.gpu_options.allow_growth = True
# sess
sess=tf.InteractiveSession(config=config)
tf.initialize_all_variables().run()
model.restore(sess, save_path)
data = mnist.read_data_sets()
x_, _ = data.train.next_batch(hp.batch_size)
x_ = (x_ > 0.5).astype(np.float32) #二值化
images = sess.run(model.output_tensors, {model.x: x_})
unit_images = []
for T, image in enumerate(images):
imgs = image.reshape(-1, hp.A, hp.B)[:100]
img = images2one(imgs)
img = (np.clip(img, 0.0, 1.0) * 255).astype(np.uint8)
unit_images.append(img)
imageio.imwrite('images/' +str(T) + '.png', img)
imageio.mimsave('images/reconstruct.gif', unit_images, duration=1.0)
# coding: utf-8
import time
import tensorflow as tf
import prettytensor as pt
import numpy as np
import cmtf.data.data_mnist as data_mnist
@pt.Register
def leaky_relu(input_pt):
return tf.select(tf.greater(input_pt, 0.0), input_pt, 0.01 * input_pt)
# 数据
mnist = data_mnist.read_data_sets(one_hot=True)
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
dropout = tf.placeholder(tf.float32, [1])
x_reshape = tf.reshape(x, [-1, 28, 28, 1])
seq = pt.wrap(x_reshape).sequential()
# CNN
# seq.conv2d(6, 16)
# seq.max_pool(2, 2)
# seq.conv2d(6, 16)
# seq.max_pool(2, 2)
def residual(seq, stride, output):
# coding: utf-8
import tensorflow as tf
import prettytensor as pt
import numpy as np
import cmtf.data.data_mnist as data_mnist
# 数据
mnist = data_mnist.read_data_sets(one_hot=True)
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None,10])
pretty_input = pt.wrap(x)
softmax, loss = (
pretty_input.
fully_connected(100, activation_fn=tf.nn.relu).
fully_connected(10, activation_fn=None).
softmax_classifier(10, labels=y))
accuracy = softmax.evaluate_classifier(y)
optimizer = tf.train.GradientDescentOptimizer(0.01) # learning rate
train_op = pt.apply_optimizer(optimizer, losses=[loss])
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
# train
for i in range(2000):
batch_xs, batch_ys = mnist.train.next_batch(100)
_, loss_val = sess.run([train_op, loss], feed_dict={x: batch_xs, y: batch_ys})
if (i+1)%100 == 0:
print 'index: %d, loss: %f' % (i+1, loss_val)
# test
def nn_train(to_name, param):
global lock, running
itchat.send(u'开工了...', to_name)
# Lock
with lock:
running = True
# mnist data reading
mnist = data_mnist.read_data_sets(one_hot=True)
# Parameters
# learning_rate = 0.001
# training_iters = 200000
# batch_size = 128
# display_step = 10
learning_rate, training_iters, batch_size, display_step = param
# Network Parameters
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)
dropout = 0.75 # Dropout, probability to keep units
# tf Graph input
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)
# Create some wrappers for simplicity
def conv2d(x, W, b, strides=1):
# Conv2D wrapper, with bias and relu activation
x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')
x = tf.nn.bias_add(x, b)
return tf.nn.relu(x)
def maxpool2d(x, k=2):
# MaxPool2D wrapper
return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME')
# Create model
def conv_net(x, weights, biases, dropout):
# Reshape input picture
x = tf.reshape(x, shape=[-1, 28, 28, 1])
# Convolution Layer
conv1 = conv2d(x, weights['wc1'], biases['bc1'])
# Max Pooling (down-sampling)
conv1 = maxpool2d(conv1, k=2)
# Convolution Layer
conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
# Max Pooling (down-sampling)
conv2 = maxpool2d(conv2, k=2)
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.relu(fc1)
# Apply Dropout
fc1 = tf.nn.dropout(fc1, dropout)
# Output, class prediction
out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
return out
# Store layers weight & bias
weights = {
# 5x5 conv, 1 input, 32 outputs
'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),
# 5x5 conv, 32 inputs, 64 outputs
'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),
# fully connected, 7*7*64 inputs, 1024 outputs
'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])),
# 1024 inputs, 10 outputs (class prediction)
'out': tf.Variable(tf.random_normal([1024, n_classes]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([32])),
'bc2': tf.Variable(tf.random_normal([64])),
'bd1': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
# Construct model
pred = conv_net(x, weights, biases, keep_prob)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.initialize_all_variables()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
step = 1
# Keep training until reach max iterations
print('Wait for lock')
with lock:
run_state = running
print('Start')
while step * batch_size < training_iters and run_state:
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y, keep_prob: dropout})
if step % display_step == 0:
# Calculate batch loss and accuracy
loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x, y: batch_y, keep_prob: 1.})
print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
itchat.send("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc), to_name)
step += 1
with lock:
run_state = running
print("Optimization Finished!")
itchat.send("Optimization Finished!", to_name)
# Calculate accuracy for 256 mnist test images
print("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.}))
itchat.send("Testing Accuracy: %s" %
sess.run(accuracy, feed_dict={x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.}), to_name)
with lock:
running = False
def train():
mnist = data_mnist.read_data_sets(one_hot=True, fake_data=FLAGS.fake_data)
sess = tf.InteractiveSession()
# 模型
with tf.name_scope('input'):
x = tf.placeholder(tf.float32, [None, 784], name='x-input')
y_ = tf.placeholder(tf.float32, [None, 10], name='y-input')
with tf.name_scope('input_reshape'):
image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])
tf.image_summary('input', image_shaped_input, 10)
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def variable_summaries(var, name):
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
tf.scalar_summary('mean/' + name, mean)
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_sum(tf.square(var - mean)))
tf.scalar_summary('sttdev/' + name, stddev)
tf.scalar_summary('max/' + name, tf.reduce_max(var))
tf.scalar_summary('min/' + name, tf.reduce_min(var))
tf.histogram_summary(name, var)
def nn_layer(input_tensor,
input_dim,
output_dim,
layer_name,
act=tf.nn.relu):
with tf.name_scope(layer_name):
# This Variable will hold the state of the weights for the layer
with tf.name_scope('weights'):
weights = weight_variable([input_dim, output_dim])
variable_summaries(weights, layer_name + '/weights')
with tf.name_scope('biases'):
biases = bias_variable([output_dim])
variable_summaries(biases, layer_name + '/biases')
with tf.name_scope('Wx_plus_b'):
preactivate = tf.matmul(input_tensor, weights) + biases
tf.histogram_summary(layer_name + '/pre_activations',
preactivate)
activations = act(preactivate, 'activation')
tf.histogram_summary(layer_name + '/activations', activations)
return activations
hidden1 = nn_layer(x, 784, 500, 'layer1')
with tf.name_scope('dropout'):
keep_prob = tf.placeholder(tf.float32)
tf.scalar_summary('dropout_keep_probability', keep_prob)
dropped = tf.nn.dropout(hidden1, keep_prob)
y = nn_layer(dropped, 500, 10, 'layer2', act=tf.nn.softmax)
with tf.name_scope('cross_entropy'):
diff = y_ * tf.log(y)
with tf.name_scope('total'):
cross_entropy = -tf.reduce_mean(diff)
tf.scalar_summary('cross entropy', cross_entropy)
with tf.name_scope('train'):
train_step = tf.train.AdamOptimizer(
FLAGS.learning_rate).minimize(cross_entropy)
with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
with tf.name_scope('accuracy'):
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.scalar_summary('accuracy', accuracy)
# Merge all the summaries and write them out to /tmp/mnist_logs (by default)
merged = tf.merge_all_summaries()
train_writer = tf.train.SummaryWriter(FLAGS.summaries_dir + '/train',
sess.graph)
test_writer = tf.train.SummaryWriter(FLAGS.summaries_dir + '/test')
tf.initialize_all_variables().run()
def feed_dict(train):
if train or FLAGS.fake_data:
xs, ys = mnist.train.next_batch(100, fake_data=FLAGS.fake_data)
k = FLAGS.dropout
else:
xs, ys = mnist.test.images, mnist.test.labels
k = 1.0
return {x: xs, y_: ys, keep_prob: k}
for i in range(FLAGS.max_steps):
if i % 10 == 0: # Record summaries and test-set accuracy
summary, acc = sess.run([merged, accuracy],
feed_dict=feed_dict(False))
test_writer.add_summary(summary, i)
print('Accuracy at step %s: %s' % (i, acc))
else: # Record train set summaries, and train
if i % 100 == 99: # Record execution stats
run_options = tf.RunOptions(
trace_level=tf.RunOptions.FULL_TRACE)
run_metadata = tf.RunMetadata()
summary, _ = sess.run([merged, train_step],
feed_dict=feed_dict(True),
options=run_options,
run_metadata=run_metadata)
train_writer.add_run_metadata(run_metadata, 'step%03d' % i)
train_writer.add_summary(summary, i)
print('Adding run metadata for', i)
else: # Record a summary
summary, _ = sess.run([merged, train_step],
feed_dict=feed_dict(True))
train_writer.add_summary(summary, i)
train_writer.close()
test_writer.close()
def train():
mnist = data_mnist.read_data_sets(one_hot=True, fake_data=FLAGS.fake_data)
sess = tf.InteractiveSession()
# 模型
with tf.name_scope('input'):
x = tf.placeholder(tf.float32, [None, 784], name='x-input')
y_ = tf.placeholder(tf.float32, [None, 10], name='y-input')
with tf.name_scope('input_reshape'):
image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])
tf.image_summary('input', image_shaped_input, 10)
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def variable_summaries(var, name):
with tf.name_scope('summaries'):
mean = tf.reduce_mean(var)
tf.scalar_summary('mean/' + name, mean)
with tf.name_scope('stddev'):
stddev = tf.sqrt(tf.reduce_sum(tf.square(var - mean)))
tf.scalar_summary('sttdev/' + name, stddev)
tf.scalar_summary('max/' + name, tf.reduce_max(var))
tf.scalar_summary('min/' + name, tf.reduce_min(var))
tf.histogram_summary(name, var)
def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu):
with tf.name_scope(layer_name):
# This Variable will hold the state of the weights for the layer
with tf.name_scope('weights'):
weights = weight_variable([input_dim, output_dim])
variable_summaries(weights, layer_name + '/weights')
with tf.name_scope('biases'):
biases = bias_variable([output_dim])
variable_summaries(biases, layer_name + '/biases')
with tf.name_scope('Wx_plus_b'):
preactivate = tf.matmul(input_tensor, weights) + biases
tf.histogram_summary(layer_name + '/pre_activations', preactivate)
activations = act(preactivate, 'activation')
tf.histogram_summary(layer_name + '/activations', activations)
return activations
hidden1 = nn_layer(x, 784, 500, 'layer1')
with tf.name_scope('dropout'):
keep_prob = tf.placeholder(tf.float32)
tf.scalar_summary('dropout_keep_probability', keep_prob)
dropped = tf.nn.dropout(hidden1, keep_prob)
y = nn_layer(dropped, 500, 10, 'layer2', act=tf.nn.softmax)
with tf.name_scope('cross_entropy'):
diff = y_ * tf.log(y)
with tf.name_scope('total'):
cross_entropy = -tf.reduce_mean(diff)
tf.scalar_summary('cross entropy', cross_entropy)
with tf.name_scope('train'):
train_step = tf.train.AdamOptimizer(FLAGS.learning_rate).minimize(cross_entropy)
with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
with tf.name_scope('accuracy'):
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.scalar_summary('accuracy', accuracy)
# Merge all the summaries and write them out to /tmp/mnist_logs (by default)
merged = tf.merge_all_summaries()
train_writer = tf.train.SummaryWriter(FLAGS.summaries_dir + '/train', sess.graph)
test_writer = tf.train.SummaryWriter(FLAGS.summaries_dir + '/test')
tf.initialize_all_variables().run()
def feed_dict(train):
if train or FLAGS.fake_data:
xs, ys = mnist.train.next_batch(100, fake_data=FLAGS.fake_data)
k = FLAGS.dropout
else:
xs, ys = mnist.test.images, mnist.test.labels
k = 1.0
return {x: xs, y_: ys, keep_prob: k}
for i in range(FLAGS.max_steps):
if i % 10 == 0: # Record summaries and test-set accuracy
summary, acc = sess.run([merged, accuracy], feed_dict=feed_dict(False))
test_writer.add_summary(summary, i)
print('Accuracy at step %s: %s' % (i, acc))
else: # Record train set summaries, and train
if i % 100 == 99: # Record execution stats
run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_metadata = tf.RunMetadata()
summary, _ = sess.run([merged, train_step], feed_dict=feed_dict(True), options=run_options, run_metadata=run_metadata)
train_writer.add_run_metadata(run_metadata, 'step%03d' % i)
train_writer.add_summary(summary, i)
print('Adding run metadata for', i)
else: # Record a summary
summary, _ = sess.run([merged, train_step], feed_dict=feed_dict(True))
train_writer.add_summary(summary, i)
train_writer.close()
test_writer.close()
def nn_train(to_name, param):
global lock, running
itchat.send(u'开工了...', to_name)
# Lock
with lock:
running = True
# mnist data reading
mnist = data_mnist.read_data_sets(one_hot=True)
# Parameters
# learning_rate = 0.001
# training_iters = 200000
# batch_size = 128
# display_step = 10
learning_rate, training_iters, batch_size, display_step = param
# Network Parameters
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)
dropout = 0.75 # Dropout, probability to keep units
# tf Graph input
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)
# Create some wrappers for simplicity
def conv2d(x, W, b, strides=1):
# Conv2D wrapper, with bias and relu activation
x = tf.nn.conv2d(x,
W,
strides=[1, strides, strides, 1],
padding='SAME')
x = tf.nn.bias_add(x, b)
return tf.nn.relu(x)
def maxpool2d(x, k=2):
# MaxPool2D wrapper
return tf.nn.max_pool(x,
ksize=[1, k, k, 1],
strides=[1, k, k, 1],
padding='SAME')
# Create model
def conv_net(x, weights, biases, dropout):
# Reshape input picture
x = tf.reshape(x, shape=[-1, 28, 28, 1])
# Convolution Layer
conv1 = conv2d(x, weights['wc1'], biases['bc1'])
# Max Pooling (down-sampling)
conv1 = maxpool2d(conv1, k=2)
# Convolution Layer
conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
# Max Pooling (down-sampling)
conv2 = maxpool2d(conv2, k=2)
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.relu(fc1)
# Apply Dropout
fc1 = tf.nn.dropout(fc1, dropout)
# Output, class prediction
out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
return out
# Store layers weight & bias
weights = {
# 5x5 conv, 1 input, 32 outputs
'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),
# 5x5 conv, 32 inputs, 64 outputs
'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),
# fully connected, 7*7*64 inputs, 1024 outputs
'wd1': tf.Variable(tf.random_normal([7 * 7 * 64, 1024])),
# 1024 inputs, 10 outputs (class prediction)
'out': tf.Variable(tf.random_normal([1024, n_classes]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([32])),
'bc2': tf.Variable(tf.random_normal([64])),
'bd1': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
# Construct model
pred = conv_net(x, weights, biases, keep_prob)
# Define loss and optimizer
cost = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(
learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.initialize_all_variables()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
step = 1
# Keep training until reach max iterations
print('Wait for lock')
with lock:
run_state = running
print('Start')
while step * batch_size < training_iters and run_state:
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop)
sess.run(optimizer,
feed_dict={
x: batch_x,
y: batch_y,
keep_prob: dropout
})
if step % display_step == 0:
# Calculate batch loss and accuracy
loss, acc = sess.run([cost, accuracy],
feed_dict={
x: batch_x,
y: batch_y,
keep_prob: 1.
})
print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
itchat.send("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc), to_name)
step += 1
with lock:
run_state = running
print("Optimization Finished!")
itchat.send("Optimization Finished!", to_name)
# Calculate accuracy for 256 mnist test images
print("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.}))
itchat.send(
"Testing Accuracy: %s" % sess.run(accuracy,
feed_dict={
x: mnist.test.images[:256],
y: mnist.test.labels[:256],
keep_prob: 1.
}), to_name)
with lock:
running = False
