Real-Time face recognition on CPU with Python

[@sakshamverma2421]

Hey there great video. I have been trying to this project but the issue im facing is converting that model to onxx. If possible can you please state what version of tensorflow and tf2onxx do i require to make it work on ubuntu. Thanks in advance

[@PyLessons]

Thanks! Try the following: tensorflow==2.11.0, tf2onnx==1.14.0, onnx==1.14.0

[@yosayaan7013]

how to get the faceNet.onnx file on models folder?? after download and move the facenet_keras_weights.h5 file in models folder. . . please reply

[@bouachaisraa6147]

Hi, The code works correctly but it does not recognize me

[@jrkdndb]

Very good..

[@happysunvn]

I tested it and there were quite a few errors. Can you please give me information about specific versions of opencv-python mediapipe stow numpy tqdm onnxruntime tf2onnx Is tensorflow okay? Thanks a lot

[@Nico-hf6hw]

This is fantastic! Just a question, why is it that when I provide multiple photos per person the accuracy goes extremely low? Whilst with one photo per person is really accurate

[@UzaifKhatri]

Here is to start, 9:40

[@nicolassabumathew8451]

Greetings Sir!, Thank you for the tutorial but could you please provide the facenet.onnx file required ? I am unable to execute the code due to not being able to convert and i have tried a lot of methods. Thanks *EDIT* The issue got fixed, i downgraded tf2onnx to version 1.4.1 and it worked

[@PyLessons]

Great that you were able to solve it! :)

[@sakshamverma2421]

Can you share the onxx model file, thanks in advance

[@nicolassabumathew8451]

@@sakshamverma2421 Hey, I made my very first git hub repo to share the file with you. The problem is, you can't share non YT links in comments. So I will make a video and link the git hub repo in the comments

[@sakshamverma2421]

Any update on the video and link ☹️

[@sakshamverma2421]

@@nicolassabumathew8451 ..

[@apurvathakur9416]

how to calculate accuracy

[@Nico-hf6hw]

Is it possible to train more than one photo per face? Like if I wanted to add like 10 photos of one person to make it more accurate

[@PyLessons]

Yes, you can create an array where you save encodings, and then calculate distance on that array

[@Nico-hf6hw]

@@PyLessons you are a legend, thanks for taking time to reply to me. Would you say this would increase the accuracy?

[@cando_jo]

Hi! Why can't you just give us the .onnx file? I am getting so much errors using the tf2onnx I think it's outdated or it doesnt work well with the last module in Tensorflow

[@cando_jo]

Fixed by downgrading tensorflow. Thanks alot for the video, subscribed and waiting for more!

[@PyLessons]

Yes, there is difference in tensorflow 2.11, on windows it works differently... For now best option to stay on 2.10 if you on windows

[@cando_jo]

@@PyLessons It would be perfect if you pin a comment with the module versions you used for people in the future :) Because it took me me a lot of time to make it work.