gray scale image issue

[yaozr]

for the genwts.py:

tmp = torch.ones(1, 3, 224, 224).to('cuda:0')
print('input: ', tmp)
out = net(tmp)
print('output:', out)
summary(net, (3, 224, 224))

if I train use gray scale image, should I change the 3 into 1 for the above codes?

Thanks！

[YuzhouPeng]

yes, if you trained with grayscale image, you need to change this to 1 to fit the channel number, meanwhile you should also change the channel number of input in cpp file's inference and netconstruction function