CSAILVision / CSAILVision/semantic-segmentation-pytorch
On using non-dilated Resnet weights for dilated Resnets
Open
- Dominant language
- Python
- Stars
- 5.1k
- Forks
- 1.1k
- PR merge metrics
- No merged PRs in 30d
Description
For the dilated ResNets (resnet50-dilated, resnet101-dilated, etc), the same pretrained weights as the non-dilated ResNets are used. Even though only the last two layers are different (so all earlier layers should be okay in terms of weights), wouldn't we expect significantly degraded performance if we naively use regular ResNet weights, but with an operation which removes striding and adds dilation?
Am I missing something?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.