hcleung35
hcleung35
I have fit a model with pixelshuffle operation to this flops calculation. However, it cannot calculate the flops in pixelshuffle layer. PixelShuffle(0.0 M, 0.000% Params, 0.0 GMac, 0.000% MACs, upscale_factor=2)...
Thanks for your work. For training ESRnet, why we need a pretrain model (experiments/pretrained_models/RealESRNet_x4plus.pth)? How can we train the ESRnet from stretch? Thanks.
Thanks for your effort. May I know where can I get the training code for the deeplabv3plus human seg model? Thanks.