Megvii-BaseDetection / Megvii-BaseDetection/YOLOX
hi，bro，please help ，
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
When I train my own dataset, I always report this result at the beginning. I don't know exactly what went wrong. I'm going crazy. Please help me think about it
2022-12-16 22:46:39 | INFO | yolox.core.trainer:203 - ---> start train epoch1
C:\cb\pytorch_1000000000000\work\aten\src\ATen\native\cuda\ScatterGatherKernel.cu:276: block: [0,0,0], thread: [0,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
2022-12-16 22:46:42 | INFO | yolox.core.trainer:195 - Training of experiment is done and the best AP is 0.00
2022-12-16 22:46:42 | ERROR | yolox.core.launch:98 - An error has been caught in function 'launch', process 'MainProcess' (12104), thread 'MainThread' (15040):
Traceback (most recent call last):
File "tools\train.py", line 133, in
launch(
(x) H:\YOLOX-0.3.0>python tools/train.py -f exps/example/custom/yolox_s.py -d 1 -b 8
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 with tools\train.py and exps/example/custom/yolox_s.py, then trace the training path around the yolox.core.trainer and yolox.core.launch entries shown in the log. Reproduce the failure with the custom dataset and collect the experiment configuration and annotation details needed to identify the invalid index. Done means the cause is documented and training completes without the CUDA assertion.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100