Code for the ICCV 2021 paper "Pixel Difference Networks for Efficient Edge Detection" (Oral).
445
stars
69
forks
source link
the intention of in_channels // groups in nn.Parameter(torch.Tensor(out_channels, in_channels // groups, kernel_size, kernel_size)) #57
Open
chenfh21 opened 7 months ago
https://github.com/hellozhuo/pidinet/blob/36f6506df68e46260d4424446ceb9da3aa267598/models/ops.py#L27