Skip to content

zbirobin/Deep_Learning_Project_1

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Classification, weight sharing, auxiliary losses

Project 1 of Deep Learning course (EE559) at EPFL,

by Jalel Zgonda, Jonathan Labhard, Robin Zbinden

The goal of this project is to test different architectures to compare two digits visible in a two-channel image. It aims at showing in particular the impact of weight sharing, and of the use of an auxiliary loss to help the training of the main objective. More about this project can be read in the report.pdf file.

Usage

Run the script test.py to test our model with:

python test.py

Detailed file description

EnhancedSiamese.py defines the enhanced model

NaiveSiamese.py defines the naive model

Nets.py contains the two networks, i.e., CompNet and DigitNet

dlc_practical_prologue.py contains the functions to generate the data

helpers.py contains useful helpers functions

test.ipynb is a script to test our model

About

Project 1 of the Deep Learning course (EE559) at EPFL

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •