https://github.com/glgl0x00/handwritten-digits-classifier-with_pytorch
https://github.com/glgl0x00/handwritten-digits-classifier-with_pytorch
cnn-classification convolutional-neural-networks matplotlib mnist-dataset numpy python3 pytorch torchvision
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/glgl0x00/handwritten-digits-classifier-with_pytorch
- Owner: GLGL0x00
- Created: 2025-01-06T00:47:33.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2025-01-06T00:49:42.000Z (5 months ago)
- Last Synced: 2025-03-15T14:12:37.124Z (3 months ago)
- Topics: cnn-classification, convolutional-neural-networks, matplotlib, mnist-dataset, numpy, python3, pytorch, torchvision
- Language: HTML
- Homepage:
- Size: 312 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# MNIST Handwritten Digits Classifier
This project demonstrates a simple implementation of a Convolutional Neural Network (CNN) for classifying handwritten digits using the MNIST dataset. The notebook walks through data loading, preprocessing, model building, training, and evaluation using PyTorch.
## Dataset
The MNIST dataset contains 70,000 grayscale images of handwritten digits (0-9), each of size 28x28 pixels. It is a benchmark dataset in the field of machine learning.
## Key Features
- **Data Preprocessing**: The dataset is normalized and transformed using PyTorch's `torchvision.transforms`.
- **Model Architecture**: A simple CNN model is built using PyTorch's `torch.nn` module.
- **Training**: The model is trained using the `Adam` optimizer and `cross-entropy` loss.
- **Evaluation**: The model's performance is evaluated on the test set, and metrics like accuracy are reported.
## Installation
To run this notebook, you need Python 3.x and the following libraries:
- PyTorch
- torchvision
- NumPy
- Matplotlib
Install the required libraries using pip:
```bash
pip install -r requirements.txt