Tensorflow:ValueError:输入大小(输入深度)必须可通过形状推断访问，但看到值无 [英] Tensorflow: ValueError: Input size (depth of inputs) must be accessible via shape inference, but saw value None

问题描述

示例代码如下:

class Model:

def __init__(self, config):
    inputs = self.get_inputs()
    outputs, _ = tf.nn.dynamic_rnn(
            cell=tf.contrib.rnn.BasicLSTMCell(config.hidden_dim, state_is_tuple=True),
            inputs=inputs,
            dtype=tf.float32)

def get_inputs(self):
    # do something to archive the inputs, 
    # which are not just the word embeddings,
    # rather, they are the outputs of another
    # model. The shape is (batch_size, ?, hidden_dim),
    # ? means the maxlength for each batch depends
    # on the data.

然而，当我训练我的模型时，我得到了这个错误:

However, when I trained my model, I got this error:

Tensorflow:ValueError:输入大小(输入深度)必须可通过形状推断访问，但看到值无.

我认为是变量 maxlength 导致了问题.我需要为我的模型编写自己的 LSTM 还是有办法解决这个问题?

I assume it's the variable maxlength that causes the problem. Do I need to write my own LSTM for my model or is there a way to fix this?

推荐答案

inputs 的最后一个维度必须在编译图形时已经知道.您可以通过打印其静态形状来检查这一点:

The last dimension of inputs has to be known already when compiling the graph. You can check this by printing its static shape:

print(inputs.get_shape())

您可能看到的是最后一个维度是 ? 意味着 TensorFlow 无法推断它.你说输入的形状总是[batch_size, ?, hidden_​​dim].但是，TensorFlow 不一定能够推断 hidden_​​dim.TensorFlow 用于推断不同操作的输出形状的智能水平因 TensorFlow 版本而异.

What you probably see is that the last dimension is ? meaning that TensorFlow was unable to infer it. You said that the shape of the inputs is always [batch_size, ?, hidden_dim]. However, TensorFlow is not necessarily able to infer hidden_dim. The level of intelligence that TensorFlow has for infering the output shape of different operations varies between TensorFlow versions.

您可以通过明确告知 TensorFlow 输入的维度来解决问题.在调用 tf.nn.dynamic_rnn() 之前，使用 inputs.set_shape(shape) 设置输入的形状.它的工作原理类似于 inputs = tf.reshape(inputs, shape)，但它只设置静态形状.如果shape的某些维度是None，它们将不会被改变:

You can fix the problem by explicitly telling the dimensionality of the inputs to TensorFlow. Before calling tf.nn.dynamic_rnn(), set the shape of the inputs usinginputs.set_shape(shape). It works like inputs = tf.reshape(inputs, shape), but it only sets the static shape. If some dimensions of shape are None, they won't be altered:

inputs.set_shape([None, None, hidden_dim])

这篇关于Tensorflow:ValueError:输入大小(输入深度)必须可通过形状推断访问，但看到值无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！