def tower_loss(scope):
"""Calculate the total loss on a single tower running the CIFAR model.
Args:
scope: unique prefix string identifying the CIFAR tower, e.g. 'tower_0'
Returns:
Tensor of shape [] containing the total loss for a batch of data
"""
# Get images and labels for CIFAR-10.
images, labels = cifar10.distorted_inputs()
# Build inference Graph.
logits = cifar10.inference(images)
# Build the portion of the Graph calculating the losses. Note that we will
# assemble the total_loss using a custom function below.
_ = cifar10.loss(logits, labels)
# Assemble all of the losses for the current tower only.
losses = tf.get_collection('losses', scope)
# Calculate the total loss for the current tower.
total_loss = tf.add_n(losses, name='total_loss')
# Compute the moving average of all individual losses and the total loss.
loss_averages = tf.train.ExponentialMovingAverage(0.9, name='avg')
loss_averages_op = loss_averages.apply(losses + [total_loss])
# Attach a scalar summary to all individual losses and the total loss; do the
# same for the averaged version of the losses.
for l in losses + [total_loss]:
# Remove 'tower_[0-9]/' from the name in case this is a multi-GPU training
# session. This helps the clarity of presentation on tensorboard.
loss_name = re.sub('%s_[0-9]*/' % cifar10.TOWER_NAME, '', l.op.name)
# Name each loss as '(raw)' and name the moving average version of the loss
# as the original loss name.
tf.scalar_summary(loss_name + ' (raw)', l)
tf.scalar_summary(loss_name, loss_averages.average(l))
with tf.control_dependencies([loss_averages_op]):
total_loss = tf.identity(total_loss)
return total_loss
def train():
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.train.get_or_create_global_step()
# Get images and labels for CIFAR-10.
# Force input pipeline to CPU:0 to avoid operations sometimes ending up on
# GPU and resulting in a slow down.
with tf.device('/cpu:0'):
images, labels = cifar10.distorted_inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
logits = cifar10.inference(images)
# Calculate loss.
loss = cifar10.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = cifar10.train(loss, global_step)
class _LoggerHook(tf.train.SessionRunHook):
"""Logs loss and runtime."""
def begin(self):
self._step = -1
self._start_time = time.time()
def before_run(self, run_context):
self._step += 1
return tf.train.SessionRunArgs(loss) # Asks for loss value.
def after_run(self, run_context, run_values):
if self._step % FLAGS.log_frequency == 0:
current_time = time.time()
duration = current_time - self._start_time
self._start_time = current_time
loss_value = run_values.results
examples_per_sec = FLAGS.log_frequency * FLAGS.batch_size / duration
sec_per_batch = float(duration / FLAGS.log_frequency)
format_str = (
'%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
'sec/batch)')
print(format_str % (datetime.now(), self._step, loss_value,
examples_per_sec, sec_per_batch))
with tf.train.MonitoredTrainingSession(
checkpoint_dir=FLAGS.train_dir,
hooks=[
tf.train.StopAtStepHook(last_step=FLAGS.max_steps),
tf.train.NanTensorHook(loss),
_LoggerHook()
],
config=tf.ConfigProto(log_device_placement=FLAGS.
log_device_placement)) as mon_sess:
while not mon_sess.should_stop():
mon_sess.run(train_op)
def train():
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
# Get images and labels for CIFAR-10.
images, labels = cifar10.distorted_inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
logits = cifar10.inference(images)
# Calculate loss.
loss = cifar10.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = cifar10.train(loss, global_step)
# Create a saver.
saver = tf.train.Saver(tf.all_variables())
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(
log_device_placement=FLAGS.log_device_placement))
sess.run(init)
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir,
graph_def=sess.graph_def)
for step in xrange(FLAGS.max_steps):
start_time = time.time()
_, loss_value = sess.run([train_op, loss])
duration = time.time() - start_time
assert not np.isnan(loss_value), 'Model diverged with loss = NaN'
if step % 10 == 0:
num_examples_per_step = FLAGS.batch_size
examples_per_sec = num_examples_per_step / duration
sec_per_batch = float(duration)
format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
'sec/batch)')
print(format_str % (datetime.now(), step, loss_value,
examples_per_sec, sec_per_batch))
if step % 100 == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, step)
# Save the model checkpoint periodically.
if step % 1000 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
def tower_loss(scope, args):
"""Calculate the total loss on a single tower running the CIFAR model.
Args:
scope: unique prefix string identifying the CIFAR tower, e.g. 'tower_0'
args: Command line arguments.
Returns:
Tensor of shape [] containing the total loss for a batch of data
"""
# Get images and labels for CIFAR-10.
images, labels = cifar10.distorted_inputs(args.data_dir, args.batch_size,
args.use_fp16)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = cifar10.inference(images, args.batch_size, args.use_fp16)
# Build the portion of the Graph calculating the losses. Note that we will
# assemble the total_loss using a custom function below.
_ = cifar10.loss(logits, labels)
# Assemble all of the losses for the current tower only.
losses = tf.get_collection('losses', scope)
# Calculate the total loss for the current tower.
total_loss = tf.add_n(losses, name='total_loss')
# Attach a scalar summary to all individual losses and the total loss; do the
# same for the averaged version of the losses.
for l in losses + [total_loss]:
# Remove 'tower_[0-9]/' from the name in case this is a multi-GPU training
# session. This helps the clarity of presentation on tensorboard.
loss_name = re.sub('%s_[0-9]*/' % cifar10.TOWER_NAME, '', l.op.name)
tf.summary.scalar(loss_name, l)
return total_loss
def train(args):
"""Train CIFAR-10 for a number of steps.
Args:
args: The command line arguments.
"""
with tf.Graph().as_default():
# Create the global step
global_step = tf.contrib.framework.create_global_step()
# Get images and labels for CIFAR-10.
images, labels = cifar10.distorted_inputs(args.data_dir,
args.batch_size,
args.use_fp16)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = cifar10.inference(images, args.batch_size, args.use_fp16)
# Calculate loss.
loss = cifar10.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = cifar10.train(loss, global_step, args.batch_size)
scaffold = monitored_session.Scaffold()
session_creator = monitored_session.ChiefSessionCreator(
scaffold,
checkpoint_dir=args.train_dir,
config=tf.ConfigProto(
log_device_placement=args.log_device_placement))
hooks = [
# Hook to save the model every N steps and at the end.
basic_session_run_hooks.CheckpointSaverHook(
args.train_dir,
checkpoint_basename=CHECKPOINT_BASENAME,
save_steps=args.checkpoint_interval_steps,
scaffold=scaffold),
# Hook to save a summary every N steps.
basic_session_run_hooks.SummarySaverHook(
save_steps=args.summary_interval_steps,
output_dir=args.train_dir,
scaffold=scaffold),
# Hook to stop at step N.
basic_session_run_hooks.StopAtStepHook(
last_step=args.train_max_steps)
]
# Start a new monitored session. This will automatically restart the
# sessions if the parameter servers are preempted.
with monitored_session.MonitoredSession(
session_creator=session_creator, hooks=hooks) as sess:
while not sess.should_stop():
start_time = time.time()
_, loss_value, global_step_value = sess.run(
[train_op, loss, global_step])
duration = time.time() - start_time
assert not np.isnan(
loss_value), 'Model diverged with loss = NaN'
if global_step_value % 10 == 0:
num_examples_per_step = args.batch_size
examples_per_sec = num_examples_per_step / duration
sec_per_batch = float(duration)
logging.info(
('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
'sec/batch)'), datetime.now(), global_step_value,
loss_value, examples_per_sec, sec_per_batch)
def train():
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default(), tf.device('/cpu:0'):
# Create a variable to count the number of train() calls. This equals the
# number of batches processed * FLAGS.num_gpus.
global_step = tf.get_variable(
'global_step', [],
initializer=tf.constant_initializer(0), trainable=False)
# Calculate the learning rate schedule.
num_batches_per_epoch = (cifar10.NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN /
FLAGS.batch_size)
decay_steps = int(num_batches_per_epoch * cifar10.NUM_EPOCHS_PER_DECAY)
# Decay the learning rate exponentially based on the number of steps.
lr = tf.train.exponential_decay(cifar10.INITIAL_LEARNING_RATE,
global_step,
decay_steps,
cifar10.LEARNING_RATE_DECAY_FACTOR,
staircase=True)
# Create an optimizer that performs gradient descent.
opt = tf.train.GradientDescentOptimizer(lr)
# Get images and labels for CIFAR-10.
images, labels = cifar10.distorted_inputs()
batch_queue = tf.contrib.slim.prefetch_queue.prefetch_queue(
[images, labels], capacity=2 * FLAGS.num_gpus)
# Calculate the gradients for each model tower.
tower_grads = []
with tf.variable_scope(tf.get_variable_scope()):
for i in xrange(FLAGS.num_gpus):
with tf.device('/gpu:%d' % i):
with tf.name_scope('%s_%d' % (cifar10.TOWER_NAME, i)) as scope:
# Dequeues one batch for the GPU
image_batch, label_batch = batch_queue.dequeue()
# Calculate the loss for one tower of the CIFAR model. This function
# constructs the entire CIFAR model but shares the variables across
# all towers.
loss = tower_loss(scope, image_batch, label_batch)
# Reuse variables for the next tower.
tf.get_variable_scope().reuse_variables()
# Retain the summaries from the final tower.
summaries = tf.get_collection(tf.GraphKeys.SUMMARIES, scope)
# Calculate the gradients for the batch of data on this CIFAR tower.
grads = opt.compute_gradients(loss)
# Keep track of the gradients across all towers.
tower_grads.append(grads)
# We must calculate the mean of each gradient. Note that this is the
# synchronization point across all towers.
grads = average_gradients(tower_grads)
# Add a summary to track the learning rate.
summaries.append(tf.summary.scalar('learning_rate', lr))
# Add histograms for gradients.
for grad, var in grads:
if grad is not None:
summaries.append(tf.summary.histogram(var.op.name + '/gradients', grad))
# Apply the gradients to adjust the shared variables.
apply_gradient_op = opt.apply_gradients(grads, global_step=global_step)
# Add histograms for trainable variables.
for var in tf.trainable_variables():
summaries.append(tf.summary.histogram(var.op.name, var))
# Track the moving averages of all trainable variables.
variable_averages = tf.train.ExponentialMovingAverage(
cifar10.MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())
# Group all updates to into a single train op.
train_op = tf.group(apply_gradient_op, variables_averages_op)
# Create a saver.
saver = tf.train.Saver(tf.global_variables())
# Build the summary operation from the last tower summaries.
summary_op = tf.summary.merge(summaries)
# Build an initialization operation to run below.
init = tf.global_variables_initializer()
# Start running operations on the Graph. allow_soft_placement must be set to
# True to build towers on GPU, as some of the ops do not have GPU
# implementations.
sess = tf.Session(config=tf.ConfigProto(
allow_soft_placement=True,
log_device_placement=FLAGS.log_device_placement))
sess.run(init)
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
summary_writer = tf.summary.FileWriter(FLAGS.train_dir, sess.graph)
for step in xrange(FLAGS.max_steps):
start_time = time.time()
_, loss_value = sess.run([train_op, loss])
duration = time.time() - start_time
assert not np.isnan(loss_value), 'Model diverged with loss = NaN'
if step % 10 == 0:
num_examples_per_step = FLAGS.batch_size * FLAGS.num_gpus
examples_per_sec = num_examples_per_step / duration
sec_per_batch = duration / FLAGS.num_gpus
format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
'sec/batch)')
print (format_str % (datetime.now(), step, loss_value,
examples_per_sec, sec_per_batch))
if step % 100 == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, step)
# Save the model checkpoint periodically.
if step % 1000 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)