lxtGH / lxtGH/OctaveConv_pytorch
训练效果
Open
question
- Dominant language
- Python
- Stars
- 581
- Forks
- 83
- PR merge metrics
- No merged PRs in 30d
Description
你好，我实际应用于我的一个算法，替代resnet50，其他保持不变，但是发现训练速度明显变慢了，而且模型收敛反而更不好。不知道是和原因。
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reproducing the reported replacement of ResNet-50 in this PyTorch implementation and compare training speed and convergence with the original model. The issue does not name a file, test, dataset, or configuration, so collect those details before defining what a successful fix would look like.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100