PyTorch Template for DL projects

About • Examples • Installation • How To Use • Useful Links • Credits • License

About

This repository contains a template for PyTorch-based Deep Learning projects.

The template utilizes different python-dev techniques to improve code readability. Configuration methods enhance reproducibility and experiments control.

Repository is released as a part of HSE DLA course, however, can easily be adopted for any DL-task.

Examples

Important

The main branch leaves some of the code parts empty or fills them with dummy examples, showing just the base structure. The final users can add code required for their own tasks.

You can find examples of this template completed for different tasks in other branches:

• Image classification: simple classification problem on MNIST and CIFAR-10 datasets.

• ASR: template for the automatic speech recognition (ASR) task. Some of the parts (for example, collate_fn) are missing for studying purposes of HSE DLA course.

Installation

Installation may depend on your task. The general steps are the following:

0. (Optional) Create and activate new environment using conda or venv (+pyenv).

   a. conda version:

   # create env
   conda create -n project_env python=PYTHON_VERSION
   
   # activate env
   conda activate project_env

   b. venv (+pyenv) version:

   # create env
   ~/.pyenv/versions/PYTHON_VERSION/bin/python3 -m venv project_env
   
   # alternatively, using default python version
   python3 -m venv project_env
   
   # activate env
   source project_env

1. Install all required packages

   pip install -r requirements.txt

2. Install pre-commit:

   pre-commit install

How To Use

To train a model, run the following command:

python3 train.py -cn=CONFIG_NAME HYDRA_CONFIG_ARGUMENTS

Where CONFIG_NAME is a config from src/configs and HYDRA_CONFIG_ARGUMENTS are optional arguments.

Useful Links:

You may find the following liks useful:

• Python Dev Tips: information about pre-commits, Hydra, and other stuff for better python code development.

• Awesome README: a list of awesome README files for inspiration. Check the basics here.

• Report branch: Guidelines for writing a scientific report/paper (with an emphasis on DL projects).

Credits

This repository is based on a heavily modified fork of pytorch-template and asr_project_template repositories.

License