|
f 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 average_gradients(tower_grads):
"""Calculate the average gradient for each shared variable across all towers.
Note that this function provides a synchronization point across all towers.
Args:
tower_grads: List of lists of (gradient, variable) tuples. The outer list
is over individual gradients. The inner list is over the gradient
calculation for each tower.
Returns:
List of pairs of (gradient, variable) where the gradient has been averaged
across all towers.
"""
average_grads = []
for grad_and_vars in zip(*tower_grads):
# Note that each grad_and_vars looks like the following:
# ((grad0_gpu0, var0_gpu0), ... , (grad0_gpuN, var0_gpuN))
grads = []
for g, _ in grad_and_vars:
# Add 0 dimension to the gradients to represent the tower.
expanded_g = tf.expand_dims(g, 0)
# Append on a 'tower' dimension which we will average over below.
grads.append(expanded_g)
# Average over the 'tower' dimension.
grad = tf.concat(grads, 0)
grad = tf.reduce_mean(grad, 0)
# Keep in mind that the Variables are redundant because they are shared
# across towers. So .. we will just return the first tower's pointer to
# the Variable.
v = grad_and_vars[0][1]
grad_and_var = (grad, v)
average_grads.append(grad_and_var)
return average_grads
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 /
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)
# Calculate the gradients for each model tower.
tower_grads = []
for i in range(num_gpus):
with tf.device('/gpu:%d' % i):
with tf.name_scope('%s_%d' % (cifar10 |