Skip to main content

A neural network model architecture template

Project description

Template NN

Template NN is a lightweight, easy-to-use library designed to streamline the learning process of machine learning. It aims to provide a more opinionated interface while maintaining full compatibility with any existing PyTorch code.

Huge thanks to the PyTorch team for enabling projects like this.

Purpose

Initially developed for my thesis to simplify the codebase, but evolved to a library with a declarative interface for testing and benchmarking neural networks.

The classes uses shortened acronyms such as CNN for Convolution Neural Network with single line instantiation to better focus on the learning aspect of ML.

Installation

Install this library from PyPI:

pip install template-nn

Clone the repository and install it locally for development:

git clone https://github.com/gabrielchoong/template-nn.git
cd template-nn

Using uv (recommended):

uv venv
uv sync

Using pip (not recommended for contributing):

pip install -r requirements.txt
pip install .

Releases and Contributing

See changelog for previous changes. Expect breaking changes at this stage.

See contributing if you wish to contribute to this project.

License

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

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

template_nn-0.2.1.tar.gz (7.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

template_nn-0.2.1-py3-none-any.whl (8.7 kB view details)

Uploaded Python 3

File details

Details for the file template_nn-0.2.1.tar.gz.

File metadata

  • Download URL: template_nn-0.2.1.tar.gz
  • Upload date:
  • Size: 7.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.17

File hashes

Hashes for template_nn-0.2.1.tar.gz
Algorithm Hash digest
SHA256 ec021be4c71452adc09b27ba4c489585d3523b1cf509d465c5de1fc68d1f64da
MD5 104af9de1f065da49aa991c7feaf0e4a
BLAKE2b-256 dc379ea614096e2c0abded306382a977c9988d19f2657036b57cc4d126e3a8b9

See more details on using hashes here.

File details

Details for the file template_nn-0.2.1-py3-none-any.whl.

File metadata

File hashes

Hashes for template_nn-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 5f84f516a6a6dcb04ec282e414e3f3b4009605bd35f4031e59a54d257e17b040
MD5 5a45948847d6451beb0b2144edf12433
BLAKE2b-256 e038542efa19c3eedfb978643fab88f99c715b2ec157c8cd7e20ef9eab64ad7f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page