shipra25jain/ESSNet
Embedding-based Scalable Segmentation Network
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.
Stars
28
Forks
6
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
mims-harvard/ClinVec
ClinVec: Unified Embeddings of Clinical Codes Enable Knowledge-Grounded AI in Medicine
NYUMedML/DeepEHR
Chronic Disease Prediction Using Medical Notes
mims-harvard/SHEPHERD
SHEPHERD: Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases
biocentral/biocentral_server
Compute functionality for biocentral.
nomic-ai/contrastors
Train Models Contrastively in Pytorch