Welcome to the repository containing innovative software developed by Ultralytics 🧠. Our code is 🌟 open-sourced and freely available for redistribution under the AGPL-3.0 license. For more insight into our work and impact, head over to https://www.ultralytics.com.

The repository at https://github.com/ultralytics/mnist is our dedicated playground for the MNIST dataset. 🖐 This repository houses sandbox code that allows for experimentation and training of different neural network architectures on the famous MNIST digit database.

Ensure you have Python 3.7 or later installed on your machine. The following packages are required, and you can install them using pip with the provided command: pip3 install -U -r requirements.txt.

• numpy: A fundamental package for scientific computing in Python.
• torch: PyTorch, an open-source machine learning library for Python.
• torchvision: A PyTorch package that includes datasets and model architectures for computer vision.
• opencv-python: An open-source computer vision and machine learning software library.

To start training on the MNIST digits dataset, execute train.py from your Python environment. The training and test data are located in the data/ folder and were initially curated by Yann LeCun (http://yann.lecun.com/exdb/mnist/).

# Example snippet of train.py to showcase its usage.
# This will set up the environment for training a model on MNIST dataset.

# Import necessary libraries (Make sure they are installed as per requirements)
import torch

# Your training script will start here, initialize models, load data, etc.
# ...

# Start the training process
# ...

# Save your trained model
torch.save(model.state_dict(), 'path_to_save_model.pt')

# Add suitable comments to each segment of your code for better understanding.

Image credit: Josef Steppan - Own work, CC BY-SA 4.0, Link

We welcome contributions from the community! Whether you're fixing bugs, adding new features, or improving documentation, your input is invaluable. Take a look at our Contributing Guide to get started. Also, we'd love to hear about your experience with Ultralytics products. Please consider filling out our Survey. A huge 🙏 and thank you to all of our contributors!

Ultralytics is excited to offer two different licensing options to meet your needs:

• AGPL-3.0 License: Perfect for students and hobbyists, this OSI-approved open-source license encourages collaborative learning and knowledge sharing. Please refer to the LICENSE file for detailed terms.
• Enterprise License: Ideal for commercial use, this license allows for the integration of Ultralytics software and AI models into commercial products without the open-source requirements of AGPL-3.0. For use cases that involve commercial applications, please contact us via Ultralytics Licensing.

For bug reports, feature requests, and contributions, head to GitHub Issues. For questions and discussions about this project and other Ultralytics endeavors, join us on Discord!