ageitgey / ageitgey/face_recognition

Optimum Image size

Open
#768 0 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:1.0
  • Python version:3.5.3
  • Operating System:Windows
Description

Wanted to check what is the optimum size of the image. This should depend on the CNN initial input nodes used?

also how will the number_of_times_to_upsample parameter can get tuned defaukt is one. But should be use 2,3,4,...

Also while using dlib.shape_predictor("./shape_predictor_68_face_landmarks.dat") I can detect faces but when using the same Box to face_locations no boxes were detected

What I Did
Paste the command(s) you ran and the output.
If there was a crash, please include the traceback here.

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 reported behavior with face_recognition 1.0, Python 3.5.3, and Windows, but the issue provides no commands, image, output, or traceback. Investigate the questions about image size, number_of_times_to_upsample, and passing a dlib.shape_predictor-detected box to face_locations. Done should include a reproducible finding and clearly documented behavior or a confirmed fix.

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
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.