Pytorch：mat1 和 mat2 形狀不能相乘

Question

我為我的第一個 pytorch 模型設置了一個玩具示例：

x = torch.from_numpy(np.linspace(1,100,num=100))
y = torch.from_numpy(np.dot(2,x))

我已經建立了模型如下：

class Net(nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        self.fc1 = nn.Linear(1,10)
        self.fc2 = nn.Linear(10,20)
        self.fc3 = nn.Linear(16,1)
        
    def forward(self,inputs):
        x = F.relu(self.fc1(inputs))
        x = F.relu(self.fc2(x))
        x = F.linear(self.fc3(x))
        return x

但是，當我嘗試訓練時遇到了這個錯誤：

RuntimeError: mat1 and mat2 shapes cannot be multiplied (1x20 and 1x10)

以下是完整代碼供參考：

import numpy as np # linear algebra
import torch
from torch.utils.data import Dataset
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

x = torch.from_numpy(np.linspace(1,100,num=100))
y = torch.from_numpy(np.dot(2,x))

class MyDataset(Dataset):
    def __init__(self):
        self.sequences = x
        self.target = y
        
    def __getitem__(self,i):
        return self.sequences[i], self.target[i]
    
    def __len__(self):
        return len(self.sequences)

class Net(nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        self.fc1 = nn.Linear(1,10)
        self.fc2 = nn.Linear(10,20)
        self.fc3 = nn.Linear(16,1)
        
    def forward(self,inputs):
        x = F.relu(self.fc1(inputs))
        x = F.relu(self.fc2(x))
        x = F.linear(self.fc3(x))
        return x

model = Net().to('cpu')

# Generators
training_set = MyDataset()
loader = torch.utils.data.DataLoader(training_set, batch_size=20)

#criterion and optimizer
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=0.0001)

### Training
n_epochs = 12

for epoch in range(n_epochs):
    for inputs,target in loader:
        print(target)
        
        optimizer.zero_grad()
        
        output = model(inputs)
        
        loss = criterion(output,target)
        
        loss.backward()
        
        optimizer.step()

以及完整的錯誤消息：

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-107-d32fd01d3b41> in <module>
      9         optimizer.zero_grad()
     10 
---> 11         output = model(inputs)
     12 
     13         loss = criterion(output,target)

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    725             result = self._slow_forward(*input, **kwargs)
    726         else:
--> 727             result = self.forward(*input, **kwargs)
    728         for hook in itertools.chain(
    729                 _global_forward_hooks.values(),

<ipython-input-103-aefe4823d2e8> in forward(self, inputs)
      7 
      8     def forward(self,inputs):
----> 9         x = F.relu(self.fc1(inputs))
     10         x = F.relu(self.fc2(x))
     11         x = F.linear(self.fc3(x))

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    725             result = self._slow_forward(*input, **kwargs)
    726         else:
--> 727             result = self.forward(*input, **kwargs)
    728         for hook in itertools.chain(
    729                 _global_forward_hooks.values(),

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/linear.py in forward(self, input)
     91 
     92     def forward(self, input: Tensor) -> Tensor:
---> 93         return F.linear(input, self.weight, self.bias)
     94 
     95     def extra_repr(self) -> str:

/opt/conda/lib/python3.7/site-packages/torch/nn/functional.py in linear(input, weight, bias)
   1690         ret = torch.addmm(bias, input, weight.t())
   1691     else:
-> 1692         output = input.matmul(weight.t())
   1693         if bias is not None:
   1694             output += bias

RuntimeError: mat1 and mat2 shapes cannot be multiplied (1x20 and 1x10)

任何建議將不勝感激。

Answer 1

這里有四個問題：

1. 查看模型的第一層，我假設您的批次大小為 100。在這種情況下，正確的輸入形狀應該是(100, 1) ，而不是(100,) 。 要解決此問題，您可以使用unsqueeze(-1) 。

2. 輸入應為D型浮動： x.float()

3. 層self.fc3的大小不正確。 以下內容對於self.fc2相對於self.fc2有效： nn.Linear(20,1) 。

4. 最后F.linear不是線性函數（即恆等函數）。 它實際上是一個線性變換（即x @ AT + b ）。 查看文檔以獲取更多詳細信息。 我不相信這就是你想要在你的情況下做的事情。

---

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(1, 10)
        self.fc2 = nn.Linear(10, 20)
        self.fc3 = nn.Linear(20, 1)
        
    def forward(self,inputs):
        x = F.relu(self.fc1(inputs))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

推理：

>>> x = torch.linspace(1, 100, 100).float().unsqueeze(-1)
>>> y_hat = Net()(x)
>>> y_hat.shape
torch.Size([100, 1])