saturncloud/dask-pytorch-ddp

dask-pytorch-ddp is a Python package that makes it easy to train PyTorch models on dask clusters using distributed data parallel.

48
/ 100
Emerging

This tool helps machine learning engineers and data scientists train PyTorch models more efficiently using large datasets, particularly for computer vision tasks. It takes your existing PyTorch model and training script, along with large image datasets stored in cloud storage like S3, and enables distributed training across multiple machines. The output is a trained PyTorch model, but achieved much faster than with a single machine.

No commits in the last 6 months. Available on PyPI.

Use this if you need to train PyTorch models on very large datasets that don't fit on a single machine, or if you want to speed up training by utilizing multiple GPUs or machines.

Not ideal if your dataset is small enough to train efficiently on a single GPU or CPU, or if you are not already using PyTorch for your deep learning tasks.

deep-learning computer-vision large-scale-training image-classification distributed-machine-learning
Stale 6m
Maintenance 0 / 25
Adoption 8 / 25
Maturity 25 / 25
Community 15 / 25

How are scores calculated?

Stars

59

Forks

10

Language

Python

License

BSD-3-Clause

Last pushed

Apr 05, 2021

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/saturncloud/dask-pytorch-ddp"

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