mahdizynali/SegLight
Seglight is super fast and real-time semantic segmentation (cpu only) that would be inferenced on 1 core
SegLight helps researchers and robotics teams quickly identify different objects or regions within images using minimal computing power. It takes in collections of images with corresponding labeled segmentation masks and outputs a trained, lightweight model. This tool is ideal for developers working on real-time image analysis for robotics or other CPU-constrained applications.
Use this if you need to perform semantic segmentation very quickly on a single CPU core, especially for applications like humanoid soccer robots or other embedded systems.
Not ideal if you require high-accuracy segmentation that benefits from powerful GPUs or have vast, diverse datasets that need complex, larger models.
Stars
12
Forks
2
Language
Python
License
MIT
Category
Last pushed
Nov 27, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mahdizynali/SegLight"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MLSTRUCT/MLStructFP
Multi-unit floor plan dataset for architectural analysis and recognition
yassouali/pytorch-segmentation
:art: Semantic segmentation models, datasets and losses implemented in PyTorch.
wkentaro/pytorch-fcn
PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original...
meetps/pytorch-semseg
Semantic Segmentation Architectures Implemented in PyTorch
fregu856/deeplabv3
PyTorch implementation of DeepLabV3, trained on the Cityscapes dataset.