Skip to content

LeNet5 architecture implementation using pytorch, network parameter optimization and performance evaluation on dataset with Symmetric Label Noise

Notifications You must be signed in to change notification settings

VishalP227/LeNet5-CNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

2adf97a · May 31, 2023

History

2 Commits
May 31, 2023
May 31, 2023
May 31, 2023
May 31, 2023

Repository files navigation

Convolution Neural Networks (LeNet5)

Project Description

The main goals of this project are as listed below:

  • Implement and understand CNN architecture, specifically LeNet5
  • Training the convolutional nerual network on MNIST, Fashion MNIST and CIFAR 10 dataset
  • Network parameters (learning rate, momentum, training batch size) tuning
  • Evaluation and Ablation study: Analyze Receiver Operating characteristic Curve (ROC) and Area under curve (AUC) metrics
  • Analyse classification performance on noisy data (by intrducing symmetric label noise)

Please consult the problem statement and project report documents for more details

About

LeNet5 architecture implementation using pytorch, network parameter optimization and performance evaluation on dataset with Symmetric Label Noise

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published