Modify your network to train on Single channel Image

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

[chenxi116]

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".