FrancescoSaverioZuppichini/non-max-suppression-in-pytorch
How to implement Non Max Suppression (NMS) in PyTorch
This project helps computer vision practitioners refine the output of object detection models. It takes a list of bounding boxes, each with a confidence score and class label, and removes redundant, overlapping boxes, keeping only the most confident ones for each detected object. This is essential for anyone developing or deploying object detection systems to ensure clear and accurate results.
No commits in the last 6 months.
Use this if your object detection model is identifying the same object multiple times with slightly different bounding boxes and you need to consolidate them into a single, high-confidence detection.
Not ideal if you need a pre-built, production-ready non-maximum suppression component that handles multi-class scenarios directly, or if you are not working within the PyTorch ecosystem.
Stars
17
Forks
—
Language
—
License
—
Category
Last pushed
Oct 27, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/FrancescoSaverioZuppichini/non-max-suppression-in-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kk7nc/RMDL
RMDL: Random Multimodel Deep Learning for Classification
MaximeVandegar/Papers-in-100-Lines-of-Code
Implementation of papers in 100 lines of code.
OML-Team/open-metric-learning
Metric learning and retrieval pipelines, models and zoo.
miguelvr/dropblock
Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.
DLTK/DLTK
Deep Learning Toolkit for Medical Image Analysis