我不久前刚刚开始研究tensorflow。我正在研究seq2seq模型并以某种方式使教程工作,但我仍然坚持得到每个句子的状态。
据我了解,seq2seq模型采用输入序列并通过RNN为序列生成隐藏状态。之后,该模型使用序列的隐藏状态来生成新的数据序列。
如果我想直接使用输入序列的隐藏状态,我的问题是该怎么办?比方说,如果我有一个训练有素的模型,我应该如何获得输入序列[token1,token2,....,token N]的最终隐藏状态?
我已经坚持了2天,我尝试了很多不同的方法,但没有一种方法有效。
答案 0 :(得分:1)
在seq2seq模型中,编码器始终是RNN,通过rnn.rnn调用。
对rnn.rnn的调用返回输出和状态,所以要获得状态,你可以这样做:
_,encoder_state = rnn.rnn(encoder_cell,encoder_inputs,dtype = dtype)
在seq2seq模块中以相同的方式完成。 https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/ops/seq2seq.py#L103
答案 1 :(得分:1)
好吧,我想我的问题是我真的不知道怎么用tensorflow样式编码,所以我粗暴地强迫它。
(*代表修改的地方)
在python / ops / seq2seq,修改model_with_buckets()
outputs = []
*states = []
with ops.op_scope(all_inputs, name, "model_with_buckets"):
for j in xrange(len(buckets)):
if j > 0:
vs.get_variable_scope().reuse_variables()
bucket_encoder_inputs = [encoder_inputs[i]
for i in xrange(buckets[j][0])]
bucket_decoder_inputs = [decoder_inputs[i]
for i in xrange(buckets[j][1])]
*bucket_outputs, _ ,bucket_states= seq2seq(bucket_encoder_inputs,
bucket_decoder_inputs)
outputs.append(bucket_outputs)
states.append(bucket_states)
bucket_targets = [targets[i] for i in xrange(buckets[j][1])]
bucket_weights = [weights[i] for i in xrange(buckets[j][1])]
losses.append(sequence_loss(
outputs[-1], bucket_targets, bucket_weights, num_decoder_symbols,
softmax_loss_function=softmax_loss_function))
return outputs, losses,*states
在python / ops / seq2seq,修改embedding_attention_seq2seq()
if isinstance(feed_previous, bool):
* outputs, states = embedding_attention_decoder(
decoder_inputs, encoder_states[-1], attention_states, cell,
num_decoder_symbols, num_heads, output_size, output_projection,
feed_previous)
* return outputs, states, tf.constant(encoder_states[-1])
else: # If feed_previous is a Tensor, we construct 2 graphs and use cond.
outputs1, states1 = embedding_attention_decoder(
decoder_inputs, encoder_states[-1], attention_states, cell,
num_decoder_symbols, num_heads, output_size, output_projection, True)
vs.get_variable_scope().reuse_variables()
outputs2, states2 = embedding_attention_decoder(
decoder_inputs, encoder_states[-1], attention_states, cell,
num_decoder_symbols, num_heads, output_size, output_projection, False)
outputs = control_flow_ops.cond(feed_previous,
lambda: outputs1, lambda: outputs2)
states = control_flow_ops.cond(feed_previous,
lambda: states1, lambda: states2)
*return outputs, states, tf.constant(encoder_states[-1])
在model / rnn / translate / seq2seq_model.py修改 init ()
if forward_only:
* self.outputs, self.losses, self.states = seq2seq.model_with_buckets(
self.encoder_inputs, self.decoder_inputs, targets,
self.target_weights, buckets, self.target_vocab_size,
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.nn.xw_plus_b(output, output_projection[0],
output_projection[1])
for output in self.outputs[b]]
else:
* self.outputs, self.losses,_ = seq2seq.model_with_buckets(
self.encoder_inputs, self.decoder_inputs, targets,
self.target_weights, buckets, self.target_vocab_size,
lambda x, y: seq2seq_f(x, y, False),
softmax_loss_function=softmax_loss_function)
在model / rnn / translate / seq2seq_model.py修改步骤()
if not forward_only:
return outputs[1], outputs[2], None # Gradient norm, loss, no outputs.
else:
*return None, outputs[0], outputs[1:-1], outputs[-1]
完成所有这些后,我们可以通过调用:
来获取编码状态 _, _, _,states = model.step(all_other_arguements, forward_only = True)
答案 2 :(得分:1)
(*代表修改的地方)
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
在python / ops / seq2seq,修改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
在model / rnn / translate / seq2seq_model.py修改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)
在model / rnn / translate / seq2seq_model.py修改步骤()
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.
完成所有这些后,我们可以通过调用:
来获取编码状态_, _, output_logits, states = model.step(sess, encoder_inputs, decoder_inputs,
target_weights, bucket_id, True)
print (states)
翻译中的。