Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Can we make face_recognition.face_encodings a bit faster #929

Open
talhaanwarch opened this issue Sep 13, 2019 · 2 comments
Open

Can we make face_recognition.face_encodings a bit faster #929

talhaanwarch opened this issue Sep 13, 2019 · 2 comments

Comments

@talhaanwarch
Copy link

  • face_recognition version:
  • Python version 3.6:
  • Windows 10
    GTX 1060
    16 gb ram

I have notices face_recognition.face_encodings takes a lot of time, is there a way to make it bit faster?

@tomasdembelli
Copy link

I recommend you to downscale the images before encoding them.
For that, I used opencv to read and downscale the image (on the fly) and encoded by face_encodings.
For my project, keeping the maximum dimension of an image at 600 worked quite well and it massively increased the speed.
Look at my code here.

@dharamhbtik
Copy link

dharamhbtik commented Oct 15, 2019

I have situation where I have to match a single image among 100+ images. What I am doing is looping all images and encoding them and then comparing which is not good at all. and it is taking around 20 seconds to respond.
Can you suggest me any other good method which can be used to make the process faster.

Any Example will be a great help.
Also is there a way in which we can compare base64 encoded images?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants