在具有多个通道的PyTorch中创建简单的1D CNN

Question

PyTorch输入的维度不是模型所期望的，我不确定为什么。

据我所知......

in_channels首先是我们想要传递给模型的一维输入的数量，并且是之前所有后续层的out_channel。

out_channels是所需数量的内核（过滤器）。

kernel_size是每个过滤器的参数数量。

因此，随着数据向前传递，我们期望具有7个1D通道（即2D输入）的数据集。

但是，以下代码抛出的错误与我期望的不一致，其中此代码：

import numpy
import torch

X = numpy.random.uniform(-10, 10, 70).reshape(-1, 7)
# Y = np.random.randint(0, 9, 10).reshape(-1, 1)

class Simple1DCNN(torch.nn.Module):
    def __init__(self):
        super(Simple1DCNN, self).__init__()
        self.layer1 = torch.nn.Conv1d(in_channels=7, 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)
    def forward(self, x):
        x = self.layer1(x)
        x = self.act1(x)
        x = self.layer2(x)

        log_probs = torch.nn.functional.log_softmax(x, dim=1)

        return log_probs

model = Simple1DCNN()
print(model(torch.tensor(X)).size)

引发以下错误：

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-5-eca5856a2314> in <module>()
     21 
     22 model = Simple1DCNN()
---> 23 print(model(torch.tensor(X)).size)

~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    487             result = self._slow_forward(*input, **kwargs)
    488         else:
--> 489             result = self.forward(*input, **kwargs)
    490         for hook in self._forward_hooks.values():
    491             hook_result = hook(self, input, result)

<ipython-input-5-eca5856a2314> in forward(self, x)
     12         self.layer2 = torch.nn.Conv1d(in_channels=20, out_channels=10, kernel_size=1)
     13     def forward(self, x):
---> 14         x = self.layer1(x)
     15         x = self.act1(x)
     16         x = self.layer2(x)

~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    487             result = self._slow_forward(*input, **kwargs)
    488         else:
--> 489             result = self.forward(*input, **kwargs)
    490         for hook in self._forward_hooks.values():
    491             hook_result = hook(self, input, result)

~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/torch/nn/modules/conv.py in forward(self, input)
    185     def forward(self, input):
    186         return F.conv1d(input, self.weight, self.bias, self.stride,
--> 187                         self.padding, self.dilation, self.groups)
    188 
    189 

RuntimeError: Expected 3-dimensional input for 3-dimensional weight [20, 7, 5], but got 2-dimensional input of size [10, 7] instead

编辑：见Shai的动机，见下面的解决方案。

import numpy
import torch

X = numpy.random.uniform(-10, 10, 70).reshape(1, 7, -1)
# Y = np.random.randint(0, 9, 10).reshape(1, 1, -1)

class Simple1DCNN(torch.nn.Module):
    def __init__(self):
        super(Simple1DCNN, self).__init__()
        self.layer1 = torch.nn.Conv1d(in_channels=7, 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)
    def forward(self, x):
        x = self.layer1(x)
        x = self.act1(x)
        x = self.layer2(x)

        log_probs = torch.nn.functional.log_softmax(x, dim=1)

        return log_probs

model = Simple1DCNN().double()
print(model(torch.tensor(X)).shape)

Answer 1

您忘记了“小批量维”，每个“1D”样本确实有两个维度：通道数（示例中为7）和长度（在您的情况下为10）。然而，pytorch预计输入不是单个样本，而是沿着“minibatch维度”堆叠在一起的B样本的小批量。 因此，pytorch中的“1D”CNN需要3D张量作为输入：BxCxT。如果您只有一个信号，则可以添加单个维度：

 out = model(torch.tensor(X)[None, ...])