1 conv layer with 2 channels output and 2 conv layers with 1 channel output. Are they same with each other?

self.conv1 = nn.Conv2d(32, 1, 1)
self.conv2 = nn.Conv2d(32, 1, 1)
# VS
self.conv = nn.Conv2d(32, 2, 1)

I don’t understand the question at all. Conv is equivalent to stack conv1 and conv2 if it’s what you are asking.

Could you be clearer about what you try to accomplish here?

Yes these two will have the same number of parameters.
And depending on how you use them, you can get an output of the same size by using torch.cat.
Was that the question?

1 Like