Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Works around internal PyTorch bug related to shared weights #96

Merged
merged 1 commit into from
Aug 2, 2018
Merged

Works around internal PyTorch bug related to shared weights #96

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 11 additions & 10 deletions robosat/unet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,11 +93,8 @@ def __init__(self, num_classes, num_filters=32, pretrained=True):

self.resnet = resnet50(pretrained=pretrained)

self.enc0 = nn.Sequential(self.resnet.conv1, self.resnet.bn1, self.resnet.relu, self.resnet.maxpool)
self.enc1 = self.resnet.layer1 # 256
self.enc2 = self.resnet.layer2 # 512
self.enc3 = self.resnet.layer3 # 1024
self.enc4 = self.resnet.layer4 # 2048
# Access resnet directly in forward pass; do not store refs here due to
# https://github.com/pytorch/pytorch/issues/8392

self.center = DecoderBlock(2048, num_filters * 8)

Expand All @@ -120,11 +117,15 @@ def forward(self, x):
The networks output tensor.
"""

enc0 = self.enc0(x)
enc1 = self.enc1(enc0)
enc2 = self.enc2(enc1)
enc3 = self.enc3(enc2)
enc4 = self.enc4(enc3)
enc0 = self.resnet.conv1(x)
enc0 = self.resnet.bn1(enc0)
enc0 = self.resnet.relu(enc0)
enc0 = self.resnet.maxpool(enc0)

enc1 = self.resnet.layer1(enc0)
enc2 = self.resnet.layer2(enc1)
enc3 = self.resnet.layer3(enc2)
enc4 = self.resnet.layer4(enc3)

center = self.center(nn.functional.max_pool2d(enc4, kernel_size=2, stride=2))

Expand Down