Megvii-BaseDetection / Megvii-BaseDetection/YOLOX
Runtime Error
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
Hi, Dear
For training coco128 mini datasets:
I used this command:
batchsize = 4
python tools/train.py -n yolox-s -d 1 -b 4 --fp16 -o
I have a RTX3060 12GB GPU
but: after 10 epochs we have below runtime Error:
RuntimeError: CUDA out of memory. Tried to allocate 100.00 MiB (GPU 0; 12.00 GiB total capacity; 9.91 GiB already allocated; 43.94 MiB free; 9.99 GiB reserved in total by PyTorch)
I guess yolox have GPU memmory leak , becuase after 10 epochs we will have RuntimeError
so:
with batchsize = 1 I will have below RuntimeError:
python tools/train.py -n yolox-s -d 1 -b 1 --fp16 -o
RuntimeError: DataLoader worker (pid(s) 2296, 12300, 5844) exited unexpectedly
please help me to use yolox for train a custom dataset as soon as possible
Best Regards
Hosseini
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 reproduce the reported coco128 runs using batch sizes 4 and 1. Compare the CUDA out-of-memory failure after 10 epochs with the DataLoader worker failure, then document a confirmed cause and reproducible fix or configuration guidance.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100