Feedback about Real Time Inference on Raspberry Pi 4 and 5 (40 fps!)
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 9.3k
- Forks
- 4.4k
- Avg merge
- 1d 21h
- Merged PRs (30d)
- 4
Description
There is the following issue on this page: https://docs.pytorch.org/tutorials/intermediate/realtime_rpi.html
I have a YOLO like model which I used QAT and the quantized model is very slow. It is slower 4 time than the floating point model. Although I used fused layers.
Any help?
Contributor guide
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 the realtime_rpi.html tutorial linked in the issue and reproduce the reported timing difference between the floating-point and QAT quantized models on Raspberry Pi 4 or 5. Compare the reported setup with the tutorial's approach; done means documenting a confirmed cause or a reproducible limitation and updating the tutorial if appropriate.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch, raspberry-pi
- 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