Skip to content

nikola310/Siamese-Neural-Networks

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

33 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Siamese Neural Networks

Introduction

Code used for my master thesis. Comparison of two different Siamese neural networks for image recognition:

  1. Keras' Siamese neural network trained and tested on MNIST, KMNIST and Kannada-MNIST
  2. Siamese neural network for oneshot image recognition by Koch et al.

Project structure

Keras network folder contains scripts for training and testing of Keras' siamese neural network.

Koch network folder contains scripts for running siamese neural network by Koch et al.

Installation

First, create conda and activate environment with:

conda create -n tf_venv python=3.7.7

conda activate tf_venv

After that, you can install requirements by running:

conda install -c conda-forge --file requirements.txt

About

Comparison of Keras and Koch's Siamese neural networks for image recognition.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published