Open guruvishnuvardan opened 6 years ago
Try using this other library https://github.com/ageitgey/face_recognition
Try using this other library https://github.com/ageitgey/face_recognition
Use what library??i didn't understand.
@albertoZurini @SijinJohn
Same problem with me? Have you train this model for unknown person?
What is exactly your problem? The readme is enough easy to understand. If you could be more specific I'd be glad to help you
@albertoZurini the model recognizes an unknown face as member from the dataset. How to solve this issue?
Okay, now I understood what you meant (it's been a while since i last used these libraries). Before you start using these libraries I highly recommend you to read the paper of the original research (it should be found on Arxiv). So what does the neural network do? You basically input it to images and it will output the difference between the faces as a float. So in order to check if a face is the actual face of a person you threshold the output of the net (eg. if out>2 that isn't the faces of the person). That's the approach I used in my project
if i have trained the model for faces A,B,C and if D comes during testing, it may predict D as A,B,C even after reducing the threshold value.
Yeah, that's a limitation of this library. Try using the other one which I've linked
@albertoZurini and the other thing is that ? How can i export my result from this experiment?
i want to export my result from this experiment. So can you help me how to generate result from this experiments .
On Fri, Nov 22, 2019 at 7:55 PM Alberto Zurini notifications@github.com wrote:
Yeah, that's a limitation of this library. Try using the other one which I've linked
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/AISangam/Facenet-Real-time-face-recognition-using-deep-learning-Tensorflow/issues/4?email_source=notifications&email_token=ALJYEZWTZTTA4FUBLVHMOXDQU7CDDA5CNFSM4FA3IPJ2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEE5NP6Y#issuecomment-557504507, or unsubscribe https://github.com/notifications/unsubscribe-auth/ALJYEZSBR2D56QF5LYQ5GELQU7CDDANCNFSM4FA3IPJQ .
when i run python identify_face_image.py it shows me this ? can you tell me please what is this ? result indices :7 sometime 5 [[0.00921852 0.07074382 0.00716605 0.00421573 0.02599692 0.01865331 0.01690321 0.01006578 0.06874712 0.00450729 0.01254694 0.02206854 0.02750619 0.00432872 0.03058342 0.00813806 0.64345926 0.00723246 0.00791865]] [0.64345926]
On Sun, Nov 24, 2019 at 11:50 PM Jackson Lily engr.irfan958@gmail.com wrote:
i want to export my result from this experiment. So can you help me how to generate result from this experiments .
On Fri, Nov 22, 2019 at 7:55 PM Alberto Zurini notifications@github.com wrote:
Yeah, that's a limitation of this library. Try using the other one which I've linked
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/AISangam/Facenet-Real-time-face-recognition-using-deep-learning-Tensorflow/issues/4?email_source=notifications&email_token=ALJYEZWTZTTA4FUBLVHMOXDQU7CDDA5CNFSM4FA3IPJ2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEE5NP6Y#issuecomment-557504507, or unsubscribe https://github.com/notifications/unsubscribe-auth/ALJYEZSBR2D56QF5LYQ5GELQU7CDDANCNFSM4FA3IPJQ .
@albertoZurini and the other thing is that ? How can i export my result from this experiment?
I'm pretty sure you can't export the data from this neural network to the other due to architecture differences
@albertoZurini and what about this one ?
@albertoZurini and what about this one ?
I've tried to get it running, but with no result. If you can get it that would be the best NN for facial recognition.
HI,
I am using this code to identify unknown faces that are not trained, so Can you please let me know, where to add "Unknown" label, so that I can take screen shot of those unknown persons to train later.
Thanks Guru