hed
hed copied to clipboard
padding=35 in first conv layer
Hi, Nice repo. What is the reason for keeping padding=35 for the first convolutional layer? I am not sure if the HED architecture advises that.
Hi @debvrat, the padding=35
is re-used from the original HED network. You may refer to https://github.com/s9xie/hed/issues/20 and some other posts in the original HED repo for more details.