umcconnell / mnist-cnn

Basic image classification. Trained on MNIST. Written in pytorch.

mnist-cnn

Basic image classification. Trained on MNIST. Written in pytorch.

Table of Contents

• Getting Started
  • Prerequisites
  • Initial setup
• Contributing
• Versioning
• Authors
• License
• See also
• Acknowledgments

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

If you would just like to play around with the model without downloading anything to your machine, you can open this notebook in Google Colab (Note that a Google account is required to run the notebook): Open in Google Colab

Prerequisites

You will need python3 and pip3 installed on your machine. You can install it from the official website https://www.python.org/.

To be able to view und run the notebooks on your machine, jupyter is required. An installation guide can be found on their website: https://jupyter.org/install

To install pytorch with CUDA support, conda is recommended. An installation guide is available in the conda docs: https://docs.conda.io/projects/conda/en/latest/user-guide/install/

Initial setup

A step by step series of examples that tell you how to get the example jupyter notebook running:

Clone the git repository:

git clone https://github.com/umcconnell/mnist-gan.git
cd mnist-cnn/

Then create your virtual environment:

conda create --name torch
conda activate torch

Next, installed the required packages. This may vary based on your system hardware and requirements. Read more about pytorch installation: https://pytorch.org/get-started/locally/

conda install pytorch torchvision cudatoolkit=10.2 -c pytorch

Create a jupyter kernel for your conda environment:

pip install --user ipykernel
python -m ipykernel install --user --name=torch

Finally, open jupyter lab:

jupyter lab src/

Important: Make sure you use the kernel you created above. After opening the notebook, navigate to Kernel > Change Kernel... in the UI and select torch from the dropdown. See this blog post for more info: https://janakiev.com/blog/jupyter-virtual-envs/

To exit the virtual environment run

conda deactivate

Happy coding!

Contributing

Please read CONTRIBUTING.md and CODE_OF_CONDUCT.md for details on our code of conduct, and the process for submitting pull requests to us.

Versioning

We use SemVer for versioning. For the versions available, see the tags on this repository.

Authors

Ulysse McConnell - umcconnell

See also the list of contributors who participated in this project.

License

This project is licensed under the MIT License - see the LICENSE.md file for details.

See also

Play around interactively with image kernels on Setosa.io: Image Kernels Explained Visually

Learn the basics of Convolutional Neural Networks with Convolutional Neural Networks | MIT 6.S191

For some awesome visualizations of convolutional layers, check out Towards Data Science: Intuitively Understanding Convolutions for Deep Learning

Acknowledgments

• numpy gitignore - Gitignore inspiration
• github python gitignore template - The gitignore template
• Contributor Covenant - Code of Conduct
• GAN Tutorial Notebook - Inspiration for this project
• Jupyter Virtual Envs - Setting up jupyter kernels for conda environments