cherish24 / OSME_MAMC

implement of Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition with keras

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

OSME with MAMC

implement of Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition with keras

introduction

OSME.py is the model written by Keras

data_classify.py is used to classify the cub_200_2011 dataset into training-dataset and test-dataset

MAMC.py is the implemet of MAMC loss and softmax loss in papper with tensorflow

train.py is the decument to train model

npairs_loss.py is the implement of MAMC by Pytorch

About

implement of Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition with keras


Languages

Language:Python 100.0%