ageitgey / ageitgey/face_recognition

receiving error with face_encoding of face_recognition library after cuda setup

Open
#737 3 comments 0 reactions 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: 3.6.5
  • Operating System: windows 10
What I Did

I have just setup my CUDA with dlib and after that I am receiving this error when running the encoding of face using face_recognition library

face_encodings = face_recognition.face_encodings(frame, face_locations, num_jitters=1)

  File "C:\Users\abhinav.jhanwar\AppData\Local\Continuum\anaconda3\lib\site-packages\face_recognition\api.py", line 210, in face_encodings
    :return: A list of 128-dimensional face encodings (one for each face in the image)

  File "C:\Users\abhinav.jhanwar\AppData\Local\Continuum\anaconda3\lib\site-packages\face_recognition\api.py", line 210, in <listcomp>
    :return: A list of 128-dimensional face encodings (one for each face in the image)

RuntimeError: Error while calling cudnnCreate(&handles[new_device_id]) in file C:\dlib-master\dlib-master\dlib\cuda\cudnn_dlibapi.cpp:104. code: 1, reason: CUDA Runtime API initialization failed.

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 by reproducing the face_recognition.face_encodings call with the reported Python, Windows, CUDA, and dlib setup. Inspect face_recognition/api.py around line 210 and dlib/cuda/cudnn_dlibapi.cpp around line 104, then determine whether the CUDA initialization failure is actionable in this repository and what evidence would confirm resolution.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.