google-deepmind / google-deepmind/tapnet
ResNet implementation for TAPIR different from typical
Open
- Dominant language
- Jupyter Notebook
- Stars
- 2k
- Forks
- 192
- PR merge metrics
- No merged PRs in 30d
Description
Why has TAPIR used a different implementation for the ResNet than the typical one used (https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py, particularly BasicBlock vs BlockV2)?
Contributor guide
Assessment
This issue has not been assessed yet.