ageitgey / ageitgey/face_recognition

Fast Inferencing on Embedded board in real time Face Recognition using Tensor RT

Open
#985 2 comments 1 reaction 0 assignees View on GitHub

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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.