mmontielpz/jetseg
NeurIPS 2023
This project offers a highly efficient way to quickly identify and segment different objects within images or video streams, even on devices with limited processing power. It takes visual input and outputs a pixel-level map showing exactly where various objects are located, making it useful for applications requiring real-time object recognition. Field technicians, robotics engineers, or anyone deploying computer vision on edge devices would find this beneficial.
Use this if you need to perform accurate, real-time object segmentation on devices like drones, embedded systems, or mobile robots with low-power GPUs.
Not ideal if your primary goal is offline, high-accuracy segmentation on powerful cloud GPUs where efficiency constraints are not a major concern.
Stars
26
Forks
3
Language
Jupyter Notebook
License
CC-BY-SA-4.0
Category
Last pushed
Jan 21, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mmontielpz/jetseg"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepinv/deepinv
DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning
yjxiong/tsn-pytorch
Temporal Segment Networks (TSN) in PyTorch
mhamilton723/STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
fidler-lab/polyrnn-pp
Inference Code for Polygon-RNN++ (CVPR 2018)
pyxu-org/pyxu
Modular and scalable computational imaging in Python with GPU/out-of-core computing.