你好，我遇到了问题 我正在使用python 3.6.5和tensorflow 1.8.0。 我的输入是1000 max_textlength * 64嵌入* 4个步骤和3个协议= 64007 神经数= 10
正常的RNN可行，但我想通过
对其进行改进 attentioncellwrapper(neurons, 2, state_is_tuple = True)
我收到以下消息：
Value Error: Dimension 1 in both shapes must be equal, but are 10 and
20. Shapes are [?, 10) and [?, 20].
From merging shape 1 with another shape for 'fully_connected/packed'(op: Pack) with input shapes [?,10], [?,10], [?,20]
为什么会这样？ 有没有人也有这个问题？
我也在尝试state_is_tuple = False， 没有给出错误信息，但是python突然崩溃了：（
顺便说一句，当我改变注意力长度时，例如从2更改为3或4，更改为
Value Error: Dimension 1 in both shapes must be equal, but are 10 and
30. Shapes are [?, 10) and [?, 30].
Value Error: Dimension 1 in both shapes must be equal, but are 10 and
40. Shapes are [?, 10) and [?, 40].
好像注意长度乘以形状 非常感谢您的帮助！