ageitgey / ageitgey/face_recognition
Fast Inferencing on Embedded board in real time Face Recognition using Tensor RT
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 56.8k
- Forks
- 13.7k
- PR merge metrics
- No merged PRs in 30d
Description
- face_recognition version: 1.2.3
- Python version: 3.6.8
- Operating System: Ubuntu 18.04(Jetson Nano Optimized)
Hello Adam sir! First of all, let me tell you that face_recognition is an extremely Robust and Highly Accurate API till date for Facial Detection/ Recognition. KUDOS to your work !!!
I was wondering whether we can take the performance of real-time inference of Face Recognition even further using Nvidia's TensorRT on Nvidia's Embedded boards(Jetson Nano, AGX Xavier, etc.)???
If yes then how?? I have tried exploring Tensor RT with reference to this API but I am unable to get to a satisfactory output!
All help appreciated!
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 reported face_recognition 1.2.3, Python 3.6.8, Ubuntu 18.04 Jetson Nano setup and the proposed TensorRT path. Determine whether real-time inference on Nvidia embedded boards can be supported and document a reproducible approach; done means producing satisfactory real-time output.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- embedded-iot, machine-learning, performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100