TensorFlow tf.nn.rnn函数...如何使用训练结果通过RNN进行单次前向通过 [英] TensorFlow tf.nn.rnn function ... how to use the results of your training to do a single forward-pass through the RNN

问题描述

在tf.nn.rnn函数中使用初始状态"参数时，我很难过.

I'm having a tough time using the 'initial state' argument in the tf.nn.rnn function.

val, _ = tf.nn.rnn(cell1, newBatch, initial_state=stateP, dtype=tf.float32)

newBatch.shape =>(1、1、11)
stateP.shape =>(2，2，1，11)

newBatch.shape => (1, 1, 11)
stateP.shape => (2, 2, 1, 11)

通常，我已经完成了LSTM神经网络的培训，现在我想使用它的值.我该怎么做呢?我知道tf.nn.rnn()函数将返回状态...但是我不知道如何将其插入.

In general, I've gone through the training for my LSTM neural net and now I want to use the values of it. How do I do this? I know that the tf.nn.rnn() function will return state... but I don't know how to plug it in.

fyi stateP.shape =>(2，2，1，11)......也许是因为我使用了堆叠的LSTM单元格?

fyi stateP.shape => (2, 2, 1, 11) ..... maybe because I used stacked LSTM cells?

我也尝试过:

val, _ = tf.nn.dynamic_rnn(stacked_lstm, newBatch, initial_state=stateP, dtype=tf.float32)

但是出现错误"AttributeError:'NoneType'对象没有属性'op'".
我很确定正在讨论的'NoneType'对象是我给的stateP元组，但是我不确定在这里做什么.

but I get the error "AttributeError: 'NoneType' object has no attribute 'op'".
I'm pretty sure that the 'NoneType' object being talked about is the stateP tuple I gave, but I'm not sure what to do here.

我终于通过使用以下命令来运行它:

init_state = cell.zero_state(batch_size, tf.float32)

要确定确切的形状，我需要传递"initial_state"参数.在我的情况下，它是一个由4个张量组成的TUPLE，每个张量具有(1，11)的形状.我是这样的:

To determine the exact shape I need to pass into the 'initial_state' argument. In my case, it was a TUPLE of 4 tensors, each with the shape of (1, 11). I made it like this:

    stateP0 = tf.convert_to_tensor(stateP[0][0])
    stateP1 = tf.convert_to_tensor(stateP[0][1])
    stateP2 = tf.convert_to_tensor(stateP[1][0])
    stateP3 = tf.convert_to_tensor(stateP[1][1])
    newStateP = stateP0, stateP1, stateP2, stateP3

好的！现在tf.dynamic_rnn()函数正在运行，但是每次运行它都会给我带来不同的结果....那么传递初始状态有什么意义呢?我想使用经过训练的状态来查找...，但我不想改变它.我想实际使用我的训练结果！

Alright! Now the tf.dynamic_rnn() function is working, but it's giving me different results every time I run it.... so what's the point of passing in the initial state? I want to use the state I trained to find... and I don't want it to change. I want to actually use the results of my training!

推荐答案

您可能正在使用不推荐使用(或即将使用)的行为.在您的情况下，stateP表示c(单元状态)和h(从展开的最后一步输出的lstm)的串联.因此，您需要沿维度1切片状态以获取实际状态.

You are probably using the deprecated (or soon to be) behavior. stateP in your case represents the concatenation of c (cell state) and h (output of lstm from the final step of unrolling). So you need to slice the state along dimension 1 to get the actual state.

或者，您可以使用state_is_tuple=True初始化LSTM单元，这是我建议的方式，这样您可以通过为状态stateP[0]编制索引来轻松获得最终状态(如果您想修改它).或者，您可以将状态元组直接传递给rnn(或dynamic_rnn).

Or, you can initialize your LSTM cell with state_is_tuple=True, which I would recommend, so that you could easily get the final state (if you want to tinker with it) by indexing the state stateP[0]. Or you could just pass the state tuple directly to rnn (or dynamic_rnn).

除了您没有提供初始化代码之外，我什么也不能说.所以我会猜测.

I cant say anything beyond that because you have not provided your initialization code. So I would be guessing.

如果您仍然遇到问题，您可以编辑问题以提供更多详细信息，我将编辑答案.

You can edit your question to provide more details if you still face problems and I would edit the answer.

这篇关于TensorFlow tf.nn.rnn函数...如何使用训练结果通过RNN进行单次前向通过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！