YooSungHyun/pytorch-lightning-template

my useful torch lightning training template

32
/ 100
Emerging

This project provides a robust template for training deep learning models using PyTorch Lightning, specifically focusing on how to dynamically adjust dropout rates during training. It takes your raw data and model configuration, then outputs a trained model and detailed training logs in tools like Weights & Biases. This is designed for machine learning practitioners and researchers who build and train neural networks.

No commits in the last 6 months.

Use this if you are a machine learning practitioner who wants a standardized, efficient, and well-structured way to train PyTorch models, especially if you're interested in experimenting with dynamic dropout schedules to prevent underfitting.

Not ideal if you are looking for a pre-trained model or a simple script for a one-off task, as this project focuses on providing a framework for developing and training your own models.

deep-learning neural-network-training machine-learning-research model-optimization pytorch
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

32

Forks

3

Language

Python

License

MIT

Last pushed

Mar 12, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YooSungHyun/pytorch-lightning-template"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.