=============================ADSH Pytorch Code============================

0.This package contains the source code for the following paper:
    Qing-Yuan Jiang and Wu-Jun Li. Asymmetric Deep Supervised Hashing. AAAI 2018.
    We only carry out experiment on CIFAR-10. And we utilize pre-trained ResNet-50 for feature learning rather CNN-F in our original paper.
    Please note that the results for paper is based on MatConvNet version.
1.Author: Qing-Yuan Jiang and Wu-Jun Li.
    Contact: jiangqy@lamda.nju.edu.cn or liwujun@nju.edu.cn
2.We implement ADSH on Pytorch.
3.setup:
    3.1.preprocessing: Please download matlab CIFAR-10 data and run DataPrepare.m and SaveFig.m to generate data.
    Or you can re-implement utils/data_processing.py to loader data.
    3.2.put files in correct path :
    3.4.run ADSH_demo.py.
4.if you have any questions about this demo, please contact Jiang Qing-Yuan (jiangqy@lamda.nju.edu.cn)
