本文整理汇总了Python中tensorflow.python.ops.seq2seq.sequence_loss方法的典型用法代码示例。如果您正苦于以下问题：Python seq2seq.sequence_loss方法的具体用法？Python seq2seq.sequence_loss怎么用？Python seq2seq.sequence_loss使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类tensorflow.python.ops.seq2seq的用法示例。
在下文中一共展示了seq2seq.sequence_loss方法的4个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: sequence_loss
# 需要导入模块: from tensorflow.python.ops import seq2seq [as 别名]
# 或者: from tensorflow.python.ops.seq2seq import sequence_loss [as 别名]
def sequence_loss(self, y_pred, y_true):
'''
Loss function for the seq2seq RNN. Reshape predicted and true (label) tensors, generate dummy weights,
then use seq2seq.sequence_loss to actually compute the loss function.
'''
if self.verbose > 2: print ("my_sequence_loss y_pred=%s, y_true=%s" % (y_pred, y_true))
logits = tf.unpack(y_pred, axis=1) # list of [-1, num_decoder_synbols] elements
targets = tf.unpack(y_true, axis=1) # y_true has shape [-1, self.out_seq_len]; unpack to list of self.out_seq_len [-1] elements
if self.verbose > 2:
print ("my_sequence_loss logits=%s" % (logits,))
print ("my_sequence_loss targets=%s" % (targets,))
weights = [tf.ones_like(yp, dtype=tf.float32) for yp in targets]
if self.verbose > 4: print ("my_sequence_loss weights=%s" % (weights,))
sl = seq2seq.sequence_loss(logits, targets, weights)
if self.verbose > 2: print ("my_sequence_loss return = %s" % sl)
return sl 示例2: add_loss_op
# 需要导入模块: from tensorflow.python.ops import seq2seq [as 别名]
# 或者: from tensorflow.python.ops.seq2seq import sequence_loss [as 别名]
def add_loss_op(self, output):
"""Adds loss ops to the computational graph.
Hint: Use tensorflow.python.ops.seq2seq.sequence_loss to implement sequence loss.
Args:
output: A tensor of shape (None, self.vocab)
Returns:
loss: A 0-d tensor (scalar)
"""
### YOUR CODE HERE
all_ones = [tf.ones([self.config.batch_size * self.config.num_steps])]
cross_entropy = sequence_loss( # cross entropy
[output], [tf.reshape(self.labels_placeholder, [-1])], all_ones, len(self.vocab))
tf.add_to_collection('total_loss', cross_entropy)
loss = tf.add_n(tf.get_collection('total_loss')) # ???loss
### END YOUR CODE
return loss 示例3: add_loss_op
# 需要导入模块: from tensorflow.python.ops import seq2seq [as 别名]
# 或者: from tensorflow.python.ops.seq2seq import sequence_loss [as 别名]
def add_loss_op(self, output):
"""Adds loss ops to the computational graph.
Hint: Use tensorflow.python.ops.seq2seq.sequence_loss to implement sequence loss.
Args:
output: A tensor of shape (None, self.vocab)
Returns:
loss: A 0-d tensor (scalar)
"""
### YOUR CODE HERE
targets = [tf.reshape(self.labels_placeholder, (-1,))]
weights = [tf.ones((self.config.batch_size * self.config.num_steps,))]
loss = sequence_loss([output], targets, weights)
### END YOUR CODE
return loss 示例4: model_with_buckets
# 需要导入模块: from tensorflow.python.ops import seq2seq [as 别名]
# 或者: from tensorflow.python.ops.seq2seq import sequence_loss [as 别名]
def model_with_buckets(encoder_inputs, decoder_inputs, targets, weights,
buckets, seq2seq, softmax_loss_function=None,
per_example_loss=False, name=None):
if len(encoder_inputs) < buckets[-1][0]:
raise ValueError("Length of encoder_inputs (%d) must be at least that of la"
"st bucket (%d)." % (len(encoder_inputs), buckets[-1][0]))
if len(targets) < buckets[-1][1]:
raise ValueError("Length of targets (%d) must be at least that of last"
"bucket (%d)." % (len(targets), buckets[-1][1]))
if len(weights) < buckets[-1][1]:
raise ValueError("Length of weights (%d) must be at least that of last"
"bucket (%d)." % (len(weights), buckets[-1][1]))
all_inputs = encoder_inputs + decoder_inputs + targets + weights
losses = []
outputs = []
with ops.op_scope(all_inputs, name, "model_with_buckets"):
for j, bucket in enumerate(buckets):
with variable_scope.variable_scope(variable_scope.get_variable_scope(),
reuse=True if j > 0 else None):
bucket_outputs, _, _ = seq2seq(encoder_inputs[:bucket[0]], decoder_inputs[:bucket[1]])
outputs.append(bucket_outputs)
if per_example_loss:
losses.append(sequence_loss_by_example(
outputs[-1], targets[:bucket[1]], weights[:bucket[1]],
softmax_loss_function=softmax_loss_function))
else:
losses.append(sequence_loss(
outputs[-1], targets[:bucket[1]], weights[:bucket[1]],
softmax_loss_function=softmax_loss_function))
return outputs, losses