Skip to content

Takes 2 images and says how similar they are based on Euclidean distance of feature vectors

Notifications You must be signed in to change notification settings

dipayan90/deep-learning-image-similarity

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Image Similarity Detection using Resnet50

Introduction

Given a batch of images, the program tries to find similarity between images using Resnet50 based feature vector extraction.

Usage

python kreas_resnet50.py will compare all the images present in images folder with each other and provide the most similar image for every image.

Pre-Requisites

  • Download Anaconda
  • Make the downloaded shell script executable and install
  • conda -V to check that installation was successfull.
  • conda update conda and conda update anaconda
  • conda update scikit-learn
  • conda install theano
  • conda install -c conda-forge tensorflow
  • pip install keras
  • export MKL_THREADING_LAYER=GNU

Note: More Descriptive Instructions On Installation

About

Takes 2 images and says how similar they are based on Euclidean distance of feature vectors

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages