n*m*3输入图像到一个nxm标签在PyTorch。-n*m*3inputimagetoannxmlabelinPyTorch

The input to my network is an RGB image with dimensions nm, how can I get the output to have dimensions of nm.

我的网络的输入是一个带有尺寸nm的RGB图像，我怎样才能使输出的尺寸为nm。

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 20, kernel_size = 5)
        self.conv2 = nn.Conv2d(20, 50, kernel_size = 3)
        self.conv3 = nn.ConvTranspose2d(50,20, kernel_size = 5)
        self.conv4 = nn.ConvTranspose2d(20,1, kernel_size = 3)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = F.relu(self.conv2(x))
        x = F.relu(self.conv3(x))
        x = F.relu(self.conv4(x))
    return x

I currently output a 1 * n * m. How can I output an n*m?

我现在输出的是1 * n*m，如何输出n*m?

1 个解决方案