Deep Learning Project Template

This template offers a lightweight yet functional project template for various deep learning projects. The template assumes PyTorch as the deep learning framework. However, one can easily transfer and utilize the template to any project implemented with other frameworks.

Table of Contents

• Getting Started
• Template Layout
• Resources
• Authors
• License

Getting Started

You can fork this repo and use it as a template when creating a new repo on Github like this:

Or directly use the template from the forked template repo like this:

Alternatively, you can simply download this repo in zipped format and get started:

Next, you can install all the libraries. Check out the Extra Packages writeup for some awesome packages.

To export and install the dependencies, you can use the following command:

make freeze
make install

There are some other useful commands automated with the makefile. Please check out the usage with the following command:

make help

Template Layout

dl-project-template
.
├── configs             # configuration files (for conda, flake8, etc.)
├── data
│   ├── ...             # data reference files (index, readme, etc.)
│   ├── raw             # untreated data directly downloaded from source
│   ├── interim         # intermediate data processing results
│   └── processed       # processed data (features and targets) ready for learning
├── docs                # documentation files (*.txt, *.doc, *.jpeg, etc.)
├── exps                # experiments with configuration files
├── logs                # logs for deep learning experiments
├── models              # saved models with optimizer states 
├── notebooks           # Jupyter Notebooks (mostly for data processing and visualization)
├── src    
│   ├── data            # data processing classes, functions, and scripts
│   ├── eval            # evaluation classes and functions (metrics, visualization, etc.)
│   ├── modules         # activations, layers, modules, and networks (subclass of torch.nn.Module)
│   └── utils           # other useful functions and classes
├── tests               # unit tests module for ./src
├── makefile            # makefile for various commands (install, test, check, etc.) 
├── license.md
└── readme.md

Resources

The resources file includes packages, datasets, readings, and other templates.

Authors

• Xiaotian Duan (Email: xduan7 at gmail.com)

License

This project is licensed under the MIT License. Check LICENSE.md for more details.