qinzheng93/diagonalwise-refactorization-pytorch

Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions (in PyTorch)

PythonMIT

Issues

diagonalwise-refactorization-darknet
#3 opened 5 years ago by CuongNguyen218
1
no performance improvement over nn.Conv2D(... groups=in_channels) in pytorch 1.0
#2 opened 6 years ago by jaidmin
3
Can you please add a license file
#1 opened 7 years ago by mathmanu
1