search

dangweili / pedestrian-attribute-recognition-pytorch

A simple baseline for pedestrian attribute recognition in surveillance scenarios
332 stars 80 forks source link

The performance of the model on RAP datasets #8

Closed trikim closed 5 years ago

trikim commented 5 years ago

Have you tested the performance of trained model on RAP dataset? I have trained the first 51 attributes of RAP dataset with ResNet50, but the result is not good enough compared to the paper. the result is as follow: mA: 0.7549 Acc: 0.5831, Prec: 0.7393, Rec: 0.7097, F1: 0.7242

trikim commented 5 years ago

sorry to disturb you, I finally found that I made a mistake in data pre-processing. Now I get a good result: mA: 0.7525 Acc: 0.6588, Prec: 0.8040, Rec: 0.7637, F1: 0.7833 Thanks to the great repository.

dangweili commented 5 years ago

@trikim Got it~

nakill commented 5 years ago

@trikim Can you share me RAP dataset vs pretrained model Thanks.

daiwc commented 4 years ago

@trikim Can you share me RAP dataset vs pretrained model Thanks.

if you got rap dataset, please share with me !!! thanks a lot!