gpleiss/efficient_densenet_pytorch

A memory-efficient implementation of DenseNets

51
/ 100
Established

This project helps deep learning engineers and researchers train DenseNet models more efficiently on GPUs. It takes your existing DenseNet architecture and reduces the GPU memory needed, making it possible to train deeper models or larger batches than before. This is ideal for those working on computer vision tasks like image classification.

1,539 stars. No commits in the last 6 months.

Use this if you are training DenseNets and repeatedly encounter 'out of memory' errors on your GPU, limiting the complexity or scale of your models.

Not ideal if your GPU memory is abundant and you prioritize the absolute fastest training speed over memory efficiency.

deep-learning-engineering computer-vision neural-network-training image-classification
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,539

Forks

321

Language

Python

License

MIT

Last pushed

Jun 01, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gpleiss/efficient_densenet_pytorch"

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