def loss(logits, labels):
"""Adds all losses for the model.
Note the final loss is not returned. Instead, the list of losses are collected
by slim.losses. The losses are accumulated in tower_loss() and summed to
calculate the total loss.
Args:
logits: List of logits from inference(). Each entry is a 2-D float Tensor.
labels: Labels from distorted_inputs or inputs(). 1-D tensor
of shape [batch_size]
batch_size: integer
"""
batch_size = FLAGS.batch_size * FLAGS.sticker_candidates
# Reshape the labels into a dense Tensor of
# shape [FLAGS.batch_size, num_classes].
sparse_labels = tf.reshape(labels, [batch_size, 1])
indices = tf.reshape(tf.range(batch_size), [batch_size, 1])
concated = tf.concat(axis=1, values=[indices, sparse_labels])
num_classes = logits[0].get_shape()[-1].value
dense_labels = tf.sparse_to_dense(concated,
[batch_size, num_classes],
1.0, 0.0)
# Cross entropy loss for the main softmax prediction.
losses.cross_entropy_loss(logits[0],
dense_labels,
label_smoothing=0.1,
weight=1.0)
# Cross entropy loss for the auxiliary softmax head.
losses.cross_entropy_loss(logits[1],
dense_labels,
label_smoothing=0.1,
weight=0.4,
scope='aux_loss')
def loss(logits, labels, batch_size):
sparse_labels = tf.reshape(labels, [batch_size,1])
indices = tf.reshape(tf.range(batch_size), [batch_size,1])
concated = tf.concat(1, [indices, sparse_labels])
num_classes = logits.get_shape()[-1].value
dense_labels = tf.sparse_to_dense(concated, [batch_size, num_classes], 1.0, 0.0)
losses.cross_entropy_loss(logits, dense_labels, label_smoothing=0.0, weight=1.0)
def loss(logits, labels, batch_size):
sparse_labels = tf.reshape(labels, [batch_size,1])
indices = tf.reshape(tf.range(batch_size), [batch_size,1])
concated = tf.concat(1, [indices, sparse_labels])
num_classes = logits.get_shape()[-1].value
dense_labels = tf.sparse_to_dense(concated, [batch_size, num_classes], 1.0, 0.0)
losses.cross_entropy_loss(logits, dense_labels, label_smoothing=0.0, weight=1.0)