LSTM error: AttributeError: 'tuple' object has no attribute 'dim'

Question

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。当在 model.forward 中定义 *input 时，我看到了此问题的相关修复，但我什至还没有实现任何东西。

/编辑：等等，有一个*input！？我该如何覆盖它？

Answer 1

您将无法使用 nn.RNN inside a nn.Sequential，因为 nn.LSTM 层将输出包含 (1)[ 的元组 =30=] 输出特征和 (2) 隐藏状态和细胞状态。

必须首先解压缩输出才能在后续层中使用输出功能：nn.Linear。比如，如果您对隐藏状态和单元格状态感兴趣：

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函数：

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])

Answer 2

错误是因为 nn.LSTM returns 你的输出和你的模型状态，这是一个包含隐藏状态和记忆状态的元组。

您可以通过定义自己的 nn.Module class 来修复它，returns 只是 LSTM 的输出。

class GetLSTMOutput(nn.Module):
    def forward(self, x):
        out, _ = x
        return out

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

GetLSTMOutputclass的forward方法是隐式调用的，前一层nn.LSTM(300, 300)的输出作为参数传递。然后 returns 只是输出部分，丢弃模型的状态。

LSTM error: AttributeError: 'tuple' object has no attribute 'dim'

LSTM error: AttributeError: 'tuple' object has no attribute 'dim'

python

lstm

pytorch