Существует родственный post, но он основан на tensorflow-0,6, который является довольно устаревшей. Поэтому я обновляю его ответ в fiforflow-0.8, который также похож на тот, что и в самой новой версии.
(* представляют где изменить)
losses = []
outputs = []
*states = []
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, _ ,bucket_states= 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, *states
на Python/OPS/seq2seq, изменять embedding_attention_seq2seq()
if isinstance(feed_previous, bool):
*outputs, states = embedding_attention_decoder(
decoder_inputs, encoder_state, attention_states, cell,
num_decoder_symbols, embedding_size, num_heads=num_heads,
output_size=output_size, output_projection=output_projection,
feed_previous=feed_previous,
initial_state_attention=initial_state_attention)
*return outputs, states, encoder_state
# If feed_previous is a Tensor, we construct 2 graphs and use cond.
def decoder(feed_previous_bool):
reuse = None if feed_previous_bool else True
with variable_scope.variable_scope(variable_scope.get_variable_scope(),reuse=reuse):
outputs, state = embedding_attention_decoder(
decoder_inputs, encoder_state, attention_states, cell,
num_decoder_symbols, embedding_size, num_heads=num_heads,
output_size=output_size, output_projection=output_projection,
feed_previous=feed_previous_bool,
update_embedding_for_previous=False,
initial_state_attention=initial_state_attention)
return outputs + [state]
outputs_and_state = control_flow_ops.cond(feed_previous, lambda: decoder(True), lambda: decoder(False))
*return outputs_and_state[:-1], outputs_and_state[-1], encoder_state
в модели/РНН/перевод/seq2seq_model.py изменить Init()
if forward_only:
*self.outputs, self.losses, self.states= tf.nn.seq2seq.model_with_buckets(
self.encoder_inputs, self.decoder_inputs, targets,
self.target_weights, buckets, lambda x, y: seq2seq_f(x, y, True),
softmax_loss_function=softmax_loss_function)
# If we use output projection, we need to project outputs for decoding.
if output_projection is not None:
for b in xrange(len(buckets)):
self.outputs[b] = [
tf.matmul(output, output_projection[0]) + output_projection[1]
for output in self.outputs[b]
]
else:
*self.outputs, self.losses, _ = tf.nn.seq2seq.model_with_buckets(
self.encoder_inputs, self.decoder_inputs, targets,
self.target_weights, buckets,
lambda x, y: seq2seq_f(x, y, False),
softmax_loss_function=softmax_loss_function)
в модели/РНН/переводить/seq2seq_model.py изменить шаг()
if not forward_only:
return outputs[1], outputs[2], None # Gradient norm, loss, no outputs.
else:
*return None, outputs[0], outputs[1:], outputs[-1] # No gradient norm, loss, outputs.
со всем этим делать, мы можем получить закодированные состояния по телефону:
_, _, output_logits, states = model.step(sess, encoder_inputs, decoder_inputs,
target_weights, bucket_id, True)
print (states)
в translate.py.