Closed OTapias closed 2 years ago
do you have any update? why do you need to run unit tests?
I was running face verification demo. The output comparing img1 and img3 using VGG-FACE or other methods report a distance too lower reporting the images "They are the same" (img1 = Angelina Jolie and img3 = Jennifer Aniston)
the following output is reported: result = {'verified': True, 'distance': 0.08396705698437923, 'max_threshold_to_verify': 0.1, 'model': 'OpenFace', 'similarity_metric': 'cosine'} They are the same
I'm not sure why the programs execution is too slow. I followed your video and the answers are too fast, I'm not sure why my execution is too slow.
I get the solution. It was required to uninstall/install again anaconda, DeepFace and all libraries required. All is working fine. Thanks Sefik.
Please advise me, the following error is reported at the end of the test:
File "D:\emotions\libro tesis\papers\deepface\tests\unit_tests.py", line 246, in
raise ValueError("Unit test score does not satisfy the minimum required accuracy. Minimum expected score is ",threshold,"% but this got ",accuracy,"%")
ValueError: ('Unit test score does not satisfy the minimum required accuracy. Minimum expected score is ', 70, '% but this got ', 66.67, '%')