search

Ning-Ding / Implementation-CVPR2015-CNN-for-ReID

Implementation for CVPR 2015 Paper: "An Improved Deep Learning Architecture for Person Re-Identification".
MIT License
147 stars 71 forks source link

Testing the model #42

Open abhigoku10 opened 6 years ago

abhigoku10 commented 6 years ago

@Ning-Ding @prashanthbasani @wangbm HI guys thanks for the wonderful work , just wanted to know after running the model how to test it , i donot see any test.py file can you let me know the mode to test it

M-Ghorbel commented 5 years ago

Hi i'm looking for the testing code too

bmiftah commented 5 years ago

I guess the test file is not separate one, it is a function inside the main function as in : -

def test(model,val_or_test='test'): a,b = _get_test_data(val_or_test) # from camera pairs return model.predict_on_batch([a,b]) ..... The data for test has been already set aside inside data_preparation file my guess is the test result needs to be written to file so that it can be easy to analyze or plot the curve

M-Ghorbel commented 5 years ago

Yes that's right but it's not giving the same cmc curve as the article.

I guess the test file is not separate one, it is a function inside the main function as in : -

def test(model,val_or_test='test'): a,b = _get_test_data(val_or_test) # from camera pairs return model.predict_on_batch([a,b]) ..... The data for test has been already set aside inside data_preparation file

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/Ning-Ding/Implementation-CVPR2015-CNN-for-ReID/issues/42#issuecomment-436994640, or mute the thread https://github.com/notifications/unsubscribe-auth/Aiwr-hL5G3_95iU5eO94vvEDqjK0z1V9ks5utDKAgaJpZM4VNJv9 .