Skip to content

In this project, I Developed a CNN from scratch to predict specific landmarks, achieving an accuracy of 52%. With transfer learning using ResNet-18, the accuracy was improved to approximately 70%.

Notifications You must be signed in to change notification settings

mikkayadu/Landmark-Classification-using-PyTorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Landmark-Classification-using-PyTorch

Overview

This project involves classifying landmark images using a ResNet model enhanced through transfer learning. The dataset includes various landmark images from Google's dataset.

Features

  • Utilizes a pre-trained ResNet model.
  • Implements transfer learning techniques to fine-tune the model for better accuracy.
  • Designed to handle Google's landmark dataset.

Files

  • app.ipynb - Main application notebook.
  • cnn_from_scratch.ipynb - Notebook for constructing a CNN model from scratch.
  • transfer_learning.ipynb - Notebook illustrating transfer learning on the ResNet model.

About

In this project, I Developed a CNN from scratch to predict specific landmarks, achieving an accuracy of 52%. With transfer learning using ResNet-18, the accuracy was improved to approximately 70%.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors