Megvii-BaseDetection / Megvii-BaseDetection/YOLOX
multipe threads inference，but the speed too slowly
Open
Nobody has claimed this yet.
check
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
@steinmann single thread is fast when inference get 100fps, but 8 threads get the 2 fps and GPU using only 30%. It can't set the batchsize, the default batchsize is 1.My device is RTX3090. How can I deal with the problem . How to set the batchsize?
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
No file, test, or entry point is named. Start by locating the inference and batch-size configuration, then compare single-thread and multi-thread runs on the RTX 3090. Done means the batch size can be configured and multi-thread throughput no longer collapses while GPU utilization improves.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100