depthwise-conv-pytorch
depthwise-conv-pytorch copied to clipboard
Faster depthwise convolutions for PyTorch
TypeError: expected string or bytes-like object
Your work is so valuable for running mobilenet, convnext, and so on. I have one request. Could you support bias of dwconv for further value? Thanks
I use your code but slow than the origin function do you know why? my code is self.cheap_operation = nn.Conv2d(init_channels, new_channels, dw_size, 1,dw_size // 2, groups=init_channels, bias=False) and I replace...
This is an awesome repo, Thanks for making it! One of the annoyances of pytorch is that if you try to use a 3x3 depthwise conv and then 1x1 pointwise...
torch_dwconv/dwconv.cpp:25:62: error: ‘TORCH_CHECK’ was not declared in this scope There is no definiation of TORCH_CHECK.