/Keras-DCL

This is a Keras implementation of the CVPR2019 paper "Destruction and Construction Learning for Fine-grained Image Recognition"

Primary LanguagePython

Keras-DCL

This is an implementation of CVPR 2019 paper DCL on Python 3, Keras, and TensorFlow.

Requirements

  • python 3+
  • keras 2.2.4+
  • tensorflow-gpu 1.9+
  • numpy
  • keras_lr_multiplier
  • datetime

Datasets

Download the CUB-200-2011 datasets and put it in the dataset directory named CUB_200_2011, You can also try other fine-grained datasets.

Train the model

run train.py.

Acknowledgement

Original implementation JDAI-CV/DCL