如何获得Tensorflow seq2seq嵌入输出

时间:2016-06-06 15:00:21

标签: python tensorflow

我正在尝试使用tensorflow训练序列到序列模型,并且一直在查看它们的示例代码。

我希望能够访问编码器创建的矢量嵌入,因为它们似乎有一些有趣的属性。

然而,我真的不清楚这是怎么回事。

在单词示例的矢量表示中,他们谈论了很多关于这些嵌入可以用于什么的内容,然后似乎没有提供一种简单的方法来访问它们,除非我弄错了。

非常感谢任何有关如何访问它们的帮助。

2 个答案:

答案 0 :(得分:5)

与所有Tensorflow操作一样,大多数变量都是动态创建的。有不同的方法来访问这些变量(及其值)。在这里,您感兴趣的变量是训练变量集的一部分。要访问这些,我们可以使用tf.trainable_variables()函数:

for var in tf.trainable_variables():
    print var.name

这将为我们提供GRU seq2seq模型,以下列表:

embedding_rnn_seq2seq/RNN/EmbeddingWrapper/embedding:0
embedding_rnn_seq2seq/RNN/GRUCell/Gates/Linear/Matrix:0
embedding_rnn_seq2seq/RNN/GRUCell/Gates/Linear/Bias:0
embedding_rnn_seq2seq/RNN/GRUCell/Candidate/Linear/Matrix:0
embedding_rnn_seq2seq/RNN/GRUCell/Candidate/Linear/Bias:0
embedding_rnn_seq2seq/embedding_rnn_decoder/embedding:0
embedding_rnn_seq2seq/embedding_rnn_decoder/rnn_decoder/GRUCell/Gates/Linear/Matrix:0
embedding_rnn_seq2seq/embedding_rnn_decoder/rnn_decoder/GRUCell/Gates/Linear/Bias:0
embedding_rnn_seq2seq/embedding_rnn_decoder/rnn_decoder/GRUCell/Candidate/Linear/Matrix:0
embedding_rnn_seq2seq/embedding_rnn_decoder/rnn_decoder/GRUCell/Candidate/Linear/Bias:0
embedding_rnn_seq2seq/embedding_rnn_decoder/rnn_decoder/OutputProjectionWrapper/Linear/Matrix:0
embedding_rnn_seq2seq/embedding_rnn_decoder/rnn_decoder/OutputProjectionWrapper/Linear/Bias:0

这告诉我们嵌入被称为embedding_rnn_seq2seq/RNN/EmbeddingWrapper/embedding:0,我们可以使用它来检索早期迭代器中该变量的指针:

for var in tf.trainable_variables():
    print var.name
    if var.name == 'embedding_rnn_seq2seq/RNN/EmbeddingWrapper/embedding:0':
        embedding_op = var

然后我们可以将其他操作传递给会话运行:

_, loss_t, summary, embedding = sess.run([train_op, loss, summary_op, embedding_op], feed_dict)

我们自己拥有(批量列表)嵌入...

答案 1 :(得分:0)

有一个相关的post,但它基于tensorflow-0.6,这已经过时了。所以我在tensorflow-0.8中更新了他的答案,这也与最新版本中的答案类似。

(*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