benchopt / benchopt/benchmark_resnet_classif
Correct ResNet init for torch when adapting to CIFAR
Open
- Dominant language
- Python
- Stars
- 12
- Forks
- 4
- PR merge metrics
- No merged PRs in 30d
Description
Currenlty the first conv layer of the resnet in torch, when adapted to cifar is initialized using the wrong initialization scheme, the default.
It should be changed to the one used in resnets
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.