https://github.com/fzl-22/mnist-classification-cnn

Handwritten digits classification using CNN in PyTorch.
https://github.com/fzl-22/mnist-classification-cnn

Last synced: about 2 months ago
JSON representation

Handwritten digits classification using CNN in PyTorch.

• Host: GitHub
• URL: https://github.com/fzl-22/mnist-classification-cnn
• Owner: fzl-22
• Created: 2024-11-03T10:20:32.000Z (2 months ago)
• Default Branch: master
• Last Pushed: 2024-11-03T10:24:46.000Z (2 months ago)
• Last Synced: 2024-11-03T11:20:21.697Z (2 months ago)
• Language: Jupyter Notebook
• Size: 0 Bytes
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Handwritten Digits (MNIST) Classification using CNN

This project uses a Convolutional Neural Network (CNN) in PyTorch to classify handwritten digits (0-9) from the MNIST dataset. The model is trained to recognize patterns in 28x28 grayscale images, achieving high accuracy in digit classification (97.9%).

To create the predefined virtual environment, run this command.

```bash

conda env create -f environment.yml -p ./venv

```

Then activate it with the following command.

```bash

conda activate ./venv

```

If you are using CUDA instead of Apple's Metal, modify all occurences of `torch.mps.is_available` and `torch.device("mps")` to `torch.cuda.is_available` and `torch.device("cuda")`, respectively.