如何在没有嵌入的情况下使用 tensorflow seq2seq? [英] How to use tensorflow seq2seq without embeddings?
问题描述
我一直在使用 tensorflow 在 LSTM 上进行时间序列预测.现在,我想尝试序列到序列(seq2seq).在官方网站上有一个教程展示了 NMT with embeddings .那么,如何在没有嵌入的情况下使用这个新的 seq2seq 模块呢?(直接使用时间序列序列").
I have been working on LSTM for timeseries forecasting by using tensorflow. Now, i want to try sequence to sequence (seq2seq). In the official site there is a tutorial which shows NMT with embeddings . So, how can I use this new seq2seq module without embeddings? (directly using time series "sequences").
# 1. Encoder
encoder_cell = tf.contrib.rnn.BasicLSTMCell(LSTM_SIZE)
encoder_outputs, encoder_state = tf.nn.static_rnn(
encoder_cell,
x,
dtype=tf.float32)
# Decoder
decoder_cell = tf.nn.rnn_cell.BasicLSTMCell(LSTM_SIZE)
helper = tf.contrib.seq2seq.TrainingHelper(
decoder_emb_inp, decoder_lengths, time_major=True)
decoder = tf.contrib.seq2seq.BasicDecoder(
decoder_cell, helper, encoder_state)
# Dynamic decoding
outputs, _ = tf.contrib.seq2seq.dynamic_decode(decoder)
outputs = outputs[-1]
# output is result of linear activation of last layer of RNN
weight = tf.Variable(tf.random_normal([LSTM_SIZE, N_OUTPUTS]))
bias = tf.Variable(tf.random_normal([N_OUTPUTS]))
predictions = tf.matmul(outputs, weight) + bias
如果我使用 input_seq=x 和 output_seq=label,TrainingHelper() 的参数应该是什么?
What should be the args for TrainingHelper() if I use input_seq=x and output_seq=label?
decoder_emb_inp ???解码器长度???
decoder_emb_inp ??? decoder_lengths ???
其中 input_seq 是序列的前 8 个点,而 output_seq 是序列的最后 2 个点.提前致谢!
Where input_seq are the first 8 point of the sequence, and output_seq are the last 2 point of the sequence. Thanks on advance!
推荐答案
我使用非常基本的 InferenceHelper
让它在不嵌入的情况下工作:
I got it to work for no embedding using a very rudimentary InferenceHelper
:
inference_helper = tf.contrib.seq2seq.InferenceHelper(
sample_fn=lambda outputs: outputs,
sample_shape=[dim],
sample_dtype=dtypes.float32,
start_inputs=start_tokens,
end_fn=lambda sample_ids: False)
我的输入是形状为 [batch_size, time, dim]
的浮点数.对于下面的示例,dim
将为 1,但这可以很容易地扩展到更多维度.这是代码的相关部分:
My inputs are floats with the shape [batch_size, time, dim]
. For the example below dim
would be 1, but this can easily be extended to more dimensions. Here's the relevant part of the code:
projection_layer = tf.layers.Dense(
units=1, # = dim
kernel_initializer=tf.truncated_normal_initializer(
mean=0.0, stddev=0.1))
# Training Decoder
training_decoder_output = None
with tf.variable_scope("decode"):
# output_data doesn't exist during prediction phase.
if output_data is not None:
# Prepend the "go" token
go_tokens = tf.constant(go_token, shape=[batch_size, 1, 1])
dec_input = tf.concat([go_tokens, target_data], axis=1)
# Helper for the training process.
training_helper = tf.contrib.seq2seq.TrainingHelper(
inputs=dec_input,
sequence_length=[output_size] * batch_size)
# Basic decoder
training_decoder = tf.contrib.seq2seq.BasicDecoder(
dec_cell, training_helper, enc_state, projection_layer)
# Perform dynamic decoding using the decoder
training_decoder_output = tf.contrib.seq2seq.dynamic_decode(
training_decoder, impute_finished=True,
maximum_iterations=output_size)[0]
# Inference Decoder
# Reuses the same parameters trained by the training process.
with tf.variable_scope("decode", reuse=tf.AUTO_REUSE):
start_tokens = tf.constant(
go_token, shape=[batch_size, 1])
# The sample_ids are the actual output in this case (not dealing with any logits here).
# My end_fn is always False because I'm working with a generator that will stop giving
# more data. You may extend the end_fn as you wish. E.g. you can append end_tokens
# and make end_fn be true when the sample_id is the end token.
inference_helper = tf.contrib.seq2seq.InferenceHelper(
sample_fn=lambda outputs: outputs,
sample_shape=[1], # again because dim=1
sample_dtype=dtypes.float32,
start_inputs=start_tokens,
end_fn=lambda sample_ids: False)
# Basic decoder
inference_decoder = tf.contrib.seq2seq.BasicDecoder(dec_cell,
inference_helper,
enc_state,
projection_layer)
# Perform dynamic decoding using the decoder
inference_decoder_output = tf.contrib.seq2seq.dynamic_decode(
inference_decoder, impute_finished=True,
maximum_iterations=output_size)[0]
看看这个问题.我还发现这个 tutorial 非常有助于理解seq2seq 模型,尽管它确实使用嵌入.所以用我上面发布的 InferenceHelper
替换他们的 GreedyEmbeddingHelper
.
Have a look at this question. Also I found this tutorial to be very useful to understand seq2seq models, although it does use embeddings. So replace their GreedyEmbeddingHelper
by an InferenceHelper
like the one I posted above.
附:我将完整代码发布在 https://github.com/Andreea-G/tensorflow_examples
P.s. I posted the full code at https://github.com/Andreea-G/tensorflow_examples
这篇关于如何在没有嵌入的情况下使用 tensorflow seq2seq?的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!