Pytorch上的1D CNN: mat1和mat2形状不能相乘(10x3和10x2)

Question

我有一个500大小的样本和2种类型的标签的时间序列，想在它们上面用pytorch构建一个1D CNN:

class Simple1DCNN(torch.nn.Module):
def __init__(self):
super(Simple1DCNN, self).__init__()
self.layer1 = torch.nn.Conv1d(in_channels=50, 
out_channels=20, 
kernel_size=5, 
stride=2)
self.act1 = torch.nn.ReLU()
self.layer2 = torch.nn.Conv1d(in_channels=20, 
out_channels=10, 
kernel_size=1)

self.fc1 = nn.Linear(10* 1 * 1, 2)
def forward(self, x):
x = x.view(1, 50,-1)
x = self.layer1(x)
x = self.act1(x)
x = self.layer2(x)
x = self.fc1(x)

return x
model = Simple1DCNN()
model(torch.tensor(np.random.uniform(-10, 10, 500)).float())

但是得到这个错误信息:

Traceback (most recent call last):
File "so_pytorch.py", line 28, in <module>
model(torch.tensor(np.random.uniform(-10, 10, 500)).float())
File "/Users/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "so_pytorch.py", line 23, in forward
x = self.fc1(x)
File "/Users/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/Users/lib/python3.8/site-packages/torch/nn/modules/linear.py", line 93, in forward
return F.linear(input, self.weight, self.bias)
File "/Users/lib/python3.8/site-packages/torch/nn/functional.py", line 1692, in linear
output = input.matmul(weight.t())
RuntimeError: mat1 and mat2 shapes cannot be multiplied (10x3 and 10x2)

我做错了什么?

Answer 1

x = self.layer2(x)(也是下一行x = self.fc1(x)的输入)的输出形状为torch.Size([1, 10, 3])。

现在从self.fc1的定义来看，它期望输入的最后一个维度是10 * 1 * 1，即10，而您的输入是3，因此出现错误。

我不知道你想做什么，但假设你想做的是;

1. 将整个500大小序列标记为两个标签之一，当您这样做时。

# replace self.fc1 = nn.Linear(10* 1 * 1, 2) with
self.fc1 = nn.Linear(10 * 3, 2)
# replace x = self.fc1(x) with
x = x.view(1, -1)
x = self.fc1(x)

2. label10时间步长分别为两个标签之一，然后执行此操作

# replace self.fc1 = nn.Linear(10* 1 * 1, 2) with
self.fc1 = nn.Linear(2, 2)

1的输出形状将为(批大小，2)，对于2将是(批量大小，10,2)。

Answer 2

激活输入x到self。Fc没有预期的特征数量，因此您需要更改第一个nn的in_features。self.fc中的线性层