ENSEEIHT/projet-long
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

delete convolution bias before BN

Browse source 
The convolution bias before BN is redundan

Former-commit-id: 514f18e1a961fee4bf98fa6f50084a166e3bff4b
This commit is contained in:
Kaiyu Li 2021-12-13 14:51:44 +08:00 committed by GitHub
parent 473a03ce17
commit a953415a0d
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
unet/unet_parts.py
View file

@ -13,10 +13,10 @@ class DoubleConv(nn.Module):
if not mid_channels:
mid_channels = out_channels
self.double_conv = nn.Sequential(
nn.Conv2d(in_channels, mid_channels, kernel_size=3, padding=1),
nn.Conv2d(in_channels, mid_channels, kernel_size=3, padding=1, bias=False),
nn.BatchNorm2d(mid_channels),
nn.ReLU(inplace=True),
nn.Conv2d(mid_channels, out_channels, kernel_size=3, padding=1),
nn.Conv2d(mid_channels, out_channels, kernel_size=3, padding=1, bias=False),
nn.BatchNorm2d(out_channels),
nn.ReLU(inplace=True)
)