Pytorch 从上一层获取conv2d的输入通道?

Pytorch 从上一层获取conv2d的输入通道?,pytorch,conv-neural-network,cnn,torchvision,Pytorch,Conv Neural Network,Cnn,Torchvision,我想知道是否有许多卷积层(conv1-->conv2)。如何从conv1输出通道获取conv2的输入通道参数 class MyModel(nn.Module): def __init__(self, in_ch, num_features, out_ch2): super(MyModel, self).__init__() self.conv1 = nn.Conv2D(in_channels,num_features) self.conv2 = nn.Conv2D(i

我想知道是否有许多卷积层(conv1-->conv2)。如何从conv1输出通道获取conv2的输入通道参数

class MyModel(nn.Module):
  def __init__(self, in_ch, num_features, out_ch2):
    super(MyModel, self).__init__()
    self.conv1 = nn.Conv2D(in_channels,num_features)
    self.conv2 = nn.Conv2D(in_channnels_from_out_channels_of_conv1,out_ch2)

我可以从conv1层获取输出通道并将其用作conv2的输入通道吗?

nn.Conv2D构造函数的第二个参数是输出通道数:

self.conv1 = nn.Conv2D(in_channels,conv1_out_channels)
self.conv2 = nn.Conv2D(conv1_out_channels,out_ch2)
如中所述

也可作为一个属性使用:

self.conv1.out_channels

安东,谢谢。我在pytorch讨论页面上找到了我想要的东西。