Megvii-BaseDetection / Megvii-BaseDetection/YOLOX
yolox nano 模型参数更少，反而比yolov5n 慢
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
在对yolox nano 和yolov5n转tensorrt后 进行推理速度比较， 在jetson平台 yoloxnano 的FPS是22 yolov5n的FPS 是33.
理论上模型参数越少，速度应该更快啊？
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
Reproduce the YOLOX Nano and YOLOv5n TensorRT inference comparison on the Jetson platform, starting with the reported FPS values of 22 and 33. Check the model conversion and inference settings that affect the comparison; the issue is done when the performance difference is explained with a reproducible conclusion or a clearly identified correction.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- embedded-iot, machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100