LSTM 错误：AttributeError：“tuple”对象没有属性“dim”

我有以下代码：

import torch
import torch.nn as nn

model = nn.Sequential(
          nn.LSTM(300, 300),
          nn.Linear(300, 100),
          nn.ReLU(),
          nn.Linear(300, 7),
          )

s = torch.ones(1, 50, 300)
a = model(s)

我得到：

My-MBP:Desktop myname$ python3 testmodel.py 
Traceback (most recent call last):
  File "testmodel.py", line 12, in <module>
    a = model(s)
  File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/torch/nn/modules/container.py", line 117, in forward
    input = module(input)
  File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/torch/nn/modules/linear.py", line 93, in forward
    return F.linear(input, self.weight, self.bias)
  File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/torch/nn/functional.py", line 1688, in linear
    if input.dim() == 2 and bias is not None:
AttributeError: 'tuple' object has no attribute 'dim'

为什么？尺寸应该没问题。我看到了此问题的相关修复*input定义于model.forward，但我什至还没有实施任何东西。

/编辑：等等，有一个*input！？我怎样才能覆盖这个？

您将无法使用nn.RNN https://pytorch.org/docs/stable/generated/torch.nn.RNN.html里面一个nn.Sequential https://pytorch.org/docs/stable/generated/torch.nn.Sequential.html since nn.LSTM层将输出tuple含有(1)输出特征和(2)隐藏状态和单元状态。

必须首先对输出进行解包，以便在后续层中使用输出特征：nn.Linear。例如，如果您对隐藏状态和单元状态感兴趣：

rnn = nn.LSTM(300, 300)
output, (h_n, c_n) = rnn(x)

您可以定义一个自定义nn.Module并实现一个简单的转发功能：

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()

        self.rnn = nn.LSTM(300, 300)
        
        self.body = nn.Sequential(
          nn.Linear(300, 100),
          nn.ReLU(),
          nn.Linear(100, 7)) # <- had it set to in_features=300

    def forward(self, x):
        x, _ = self.rnn(x) # <- ignore second output
        x = self.body(x)
        return x

这样：

>>> model = Model()
>>> s = torch.ones(1, 50, 300)

>>> model(s).shape
torch.Size([1, 50, 7])