Megvii-BaseDetection / Megvii-BaseDetection/YOLOX
学习率设置
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
当我训练自己的数据集时，在本地电脑训练，batch_size设为4，此时应该怎么调整学习率？self.basic_lr_per_img = 0.01/64.0，改成self.basic_lr_per_img = 0.01/4.0精度较差
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by locating the training configuration that defines self.basic_lr_per_img and review how batch_size is used during training. Reproduce the batch_size=4 case and compare it with the reported 0.01/64.0 and 0.01/4.0 settings. Done means establishing and documenting a validated learning-rate setting or identifying the cause of the accuracy degradation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100