Skip to content

Implementation of LeNet-5 on MNIST Dataset in PyTorch

Notifications You must be signed in to change notification settings

suryansh-sinha/LeNet5-MNIST

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 

Repository files navigation

LeNet5 PyTorch Implementation

This is a simple implementation of the paper "Gradient-Based Learning Applied to Document Recognition" by LeCun et. al in PyTorch. I have also tried to improve the model using ReLU instead of Tanh and max-pooling instead of average-pooling.

Feel free to ask anything!

Architecture

image.png

Requirments

Python3
PyTorch >= 2.0.0
torchvision >= 0.14.0

Accuracy

Average precision on test set: 98%