Skip to content

[Fix] DDRNet: fix tensor size mismatch on non-standard input resolutions #3876

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

Open
Selig209 wants to merge 1 commit into
base: dev-1.x
Choose a base branch
from
Open

[Fix] DDRNet: fix tensor size mismatch on non-standard input resolutions #3876

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
5 changes: 4 additions & 1 deletion mmseg/models/backbones/ddrnet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,11 +180,14 @@ def _make_layer(self, block, inplanes, planes, num_blocks, stride=1):

def forward(self, x):
"""Forward function."""
out_size = (x.shape[-2] // 8, x.shape[-1] // 8)

# stage 0-2
x = self.stem(x)

# Use actual spatial dims after stem to avoid off-by-one errors
# when input resolution is not perfectly divisible by 8.
out_size = x.shape[-2:]

Comment on lines +187 to +190

Copilot AI Apr 25, 2026

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This bug fix isn’t covered by a regression test. Please add a unit test for DDRNet that feeds an input whose H/W aren’t divisible by 8 (e.g. 1025x1023 or a keep_ratio-like shape) and asserts the forward pass runs without error and that the feature maps being added/resized have matching spatial shapes.

Copilot uses AI. Check for mistakes.
# stage3
x_c = self.context_branch_layers[0](x)
x_s = self.spatial_branch_layers[0](x)
Expand Down
Loading