Skip to content

This is a Keras implementation of the ECCV2018 paper "Learning to Navigate for Fine-grained Classification"

Notifications You must be signed in to change notification settings

csulihong/Keras-NTS-Net

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

34 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Keras-NTS-Net

This is an implementation of NTS-Net(https://arxiv.org/pdf/1809.00287.pdf) on Python 3, Keras, and TensorFlow.

Requirements

  • python 3+
  • keras 2.2.4+
  • tensorflow-gpu 1.9+
  • numpy
  • opencv-python 3.4+
  • 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

You may need to change the configurations in config.py, and just run train.py.

Acknowledgement

Original implementation NTS-Net

Third Party Libs NTS-Net-keras

About

This is a Keras implementation of the ECCV2018 paper "Learning to Navigate for Fine-grained Classification"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%