def tower_loss(scope, feats, labels, seq_lens):
"""Calculate the total loss on a single tower running the deepSpeech model.
This function builds the graph for computing the loss per tower(GPU).
ARGS:
scope: unique prefix string identifying the
deepSpeech tower, e.g. 'tower_0'
feats: Tensor of shape BxFxT representing the
audio features (mfccs or spectrogram).
labels: sparse tensor holding labels of each utterance.
seq_lens: tensor of shape [batch_size] holding
the sequence length per input utterance.
Returns:
Tensor of shape [batch_size] containing
the total loss for a batch of data
"""
# Build inference Graph.
logits = deepSpeech.inference(feats, seq_lens, ARGS)
# Build the portion of the Graph calculating the losses. Note that we will
# assemble the total_loss using a custom function below.
_ = deepSpeech.loss(logits, labels, seq_lens)
# 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 loss 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]*/' % helper_routines.TOWER_NAME, '',
loss.op.name)
# Name each loss as '(raw)' and name the moving average
# version of the loss as the original loss name.
tf.summary.scalar(loss_name + '(raw)', loss)
tf.summary.scalar(loss_name, loss_averages.average(loss))
# Without this loss_averages_op would never run
with tf.control_dependencies([loss_averages_op]):
total_loss = tf.identity(total_loss)
return total_loss
def tower_loss(sess, scope, feats, labels, seq_lens):
"""Calculate the total loss on a single tower running the deepSpeech model.
This function builds the graph for computing the loss per tower(GPU).
ARGS:
scope: unique prefix string identifying the
deepSpeech tower, e.g. 'tower_0'
feats: Tensor of shape BxFxT representing the
audio features (mfccs or spectrogram).
labels: sparse tensor holding labels of each utterance.
seq_lens: tensor of shape [batch_size] holding
the sequence length per input utterance.
Returns:
Tensor of shape [batch_size] containing
the total loss for a batch of data
"""
# Build inference Graph.
logits = deepSpeech.inference(sess, feats, seq_lens, ARGS)
# Build the portion of the Graph calculating the losses. Note that we will
# assemble the total_loss using a custom function below.
total_loss = deepSpeech.loss(logits, labels, seq_lens)
# 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([total_loss])
# Attach a scalar summary to all individual losses and the total loss;
# do the same for the averaged version of the losses.
loss_name = total_loss.op.name
# Name each loss as '(raw)' and name the moving average
# version of the loss as the original loss name.
tf.summary.scalar(loss_name + '(raw)', total_loss)
tf.summary.scalar(loss_name, loss_averages.average(total_loss))
# Without this loss_averages_op would never run
with tf.control_dependencies([loss_averages_op]):
total_loss = tf.identity(total_loss)
return total_loss