about the number of channels in the convolutional layer
xxLinLucky opened this issue · comments
xxLinLucky commented
Hello, this is a question about the number of channels in the convolutional layer
The paper described:
We use three-layer encoders with [64, 32, 16] channels, and three�layer decoders with [16, 32, 64] channels correspondingly.
But the code is:
def encoder1(self, x):
net = self.conv_block(x, 64)
net = self.conv_block(net, 64)
net = self.conv_block(net, 64)
return net
Did I misunderstand? Thank you
Binyuan Hui commented
This belongs to the hyper-parameter of the network, which can be adjusted according to different data, not a fixed value.