deepinsight / deepinsight/insightface
Getting Inference time for SCRFD_500M => 31.227 millisecond vs 3.6 millisecond claimed ? how ?
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
As you can see i ran the loop 10 times to confirm the result.
The results are way off the time given by you. Am i missing something ?
Note:
Onnx file exported from the model.pth file given at the following link.
https://1drv.ms/u/s!AswpsDO2toNKqyYWxScdiTITY4TQ?e=DjXof9
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reviewing the supplied model.pth and exported ONNX file, then reproduce the SCRFD_500M inference timing using the same 10-iteration loop described in the issue. Compare the runtime setup and measurement method with the claimed 3.6 ms result. Done means identifying the source of the timing discrepancy and documenting the correct benchmark conditions.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 30/100