deepinsight / deepinsight/insightface
ArcFace Inference Time
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
I am getting the following average inference time for different ArcFace backbones, is arcFace this slow?
- Backbone ResNet18 : 60ms
- Backbone ResNet50 : 130ms
- Backbone ResNet100 : 230ms
I tested this on g4dn GPU. I have noticed that implementation of arcFace with resnet50 backbone of this repo : https://github.com/luckycallor/InsightFace-tensorflow is on avg. taking only around 10 ms.
Contributor guide
No contributing guide indexed for this repository
Research direction
No files, tests, or entry points are identified in the issue. Start by reproducing the reported ResNet18, ResNet50, and ResNet100 inference times on the stated g4dn GPU, then compare the conditions with the linked InsightFace-TensorFlow implementation. Done means explaining whether the timings are expected and identifying the source of the discrepancy.
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
- 20/100