Modify your network to train on Single channel Image

Open ghost opened this issue 5 years ago • 1 comments

I'm trying to replicate your model, but I have a single-channel image as an input. So can you please help me on how to achieve it

Mar 02 '20 13:03 ghost

Sounds like the main change is replacing the first parameter "3" in https://github.com/chenxi116/DeepLabv3.pytorch/blob/master/deeplab.py#L144 and https://github.com/chenxi116/DeepLabv3.pytorch/blob/master/deeplab.py#L148 to "1".

Mar 04 '20 15:03 chenxi116