shipra25jain/ESSNet

Embedding-based Scalable Segmentation Network

39
/ 100
Emerging

This project helps machine learning engineers and researchers scale semantic image segmentation models. It takes large image datasets, potentially with thousands of object classes, and outputs a trained, memory-efficient segmentation model. The primary users are deep learning practitioners working with computer vision models on resource-constrained hardware.

No commits in the last 6 months.

Use this if you need to train or fine-tune semantic segmentation models on datasets with many object classes (hundreds to over a thousand) using a single GPU, while maintaining high accuracy.

Not ideal if your segmentation tasks involve only a small number of classes, or if you have access to ample computational resources like multiple high-end GPUs.

semantic-segmentation computer-vision deep-learning image-analysis model-optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

28

Forks

6

Language

Python

License

MIT

Last pushed

Oct 15, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/shipra25jain/ESSNet"

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