Skip to content

Mahakpadlaya/Handwritten-Digits-Classifier-Using-MNIST-Dataset

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MNIST Digit Classifier (PyTorch)

This project builds a handwritten digit classifier using PyTorch.It Will Predict the number between 0-9 with the Help of Neural Network. The Dataset I used here is of MNIST which can be easily find on kaggle.

Model: Fully connected neural network

Accuracy: ~98%

RUNNING THE PROGRAM

Creating Virtual Environment: python -m venv .venv

If Using Python Install Manager: py -3.xx -m venv .venv (xx means python version For e.g. I have used 3.12.0)

Installing Modules pip install -r requirements.txt

Run training: python train.py This will download the Training data in the data directory.

Test model: python test.py

RUNNING ON GUI

Here I used Tkinter to Run it on GUI python predict_gui.py

GUI PREVIEW

Digit Classifier GUI

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages