Skip to content

Python implementation of "A non-alternating graph hashing algorithm for large scale image search" paper.

Notifications You must be signed in to change notification settings

sobhanhemati/Efficient-Spectral-Hashing-ESH-

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 

Repository files navigation

Efficient-Spectral-Hashing (ESH) algorithm

Python implementation of "A non-alternating graph hashing algorithm for large scale image search" paper.

Dependencies:

Tensorflow 2.1.0 or later

How to use?

1- Download the dataset:
labelme_vggfc7
cifar10_vggfc7
nuswide_vgg
colorectal_EfficientNet

2- Complete the parameter initialization in either demo_ESH.py or demo_ESH_manifold.py
For example:

method_name = 'ESH1' # or ESH2 (manifold optimization)
path = r'cifar10_vggfc7' # folder containing dataset
dataset_name = 'cifar10_vggfc7' #options: cifar10_vggfc7, labelme_vggfc7, nuswide_vgg, colorectal_efficientnet
K = 16 # number of bits

3- Run either demo_ESH.py for ESH1 or demo_ESH_manifold.py for ESH2.

About

Python implementation of "A non-alternating graph hashing algorithm for large scale image search" paper.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages