search

rainofmine / Face_Attention_Network

Pytorch implementation of face attention network
313 stars 55 forks source link

Do you eval yout model on Wider Face? #2

Open luuuyi opened 6 years ago

luuuyi commented 6 years ago

same as title. Hello, I wonder know the result when eval on Wider Face.

rainofmine commented 6 years ago

Sorry I haven't test on that dataset. Maybe some parameters should be modified, especially the attention scale that is not explained clearly in the paper.

luuuyi commented 6 years ago

@rainofmine finally i get the result, on the hard set of WIDER FACE, this code get about 40(mAP).

rainofmine commented 6 years ago

@luuuyi The anchor assign and data augmentation is not the same as the paper. I will update them when I have time.