Skip to content

devrijhwani3118/FaceAndDigitClassification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Face and Digit Classification

This project implements a three-layer neural network from scratch in NumPy to classify handwritten digits and facial images using ASCII-based datasets. It also includes functionality to evaluate the performance of the network on varying amounts of training data.

Setup Instructions

  1. Clone the repository or download the project folder.

  2. Navigate to the project directory:

    cd FaceAndDigitClassification
    
  3. (Optional but recommended) Create a virtual environment:

  4. Install pytorch

About

Developed from-scratch implementations of Perceptron and Neural Networks (including backpropagation and the PyTorch Library) to classify handwritten digits and detect faces using edge-detected images. Compared performance with a PyTorch model across varying training sizes, analyzing accuracy, training time, and model robustness.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages