fregu856/deeplabv3

PyTorch implementation of DeepLabV3, trained on the Cityscapes dataset.

51
/ 100
Established

This project helps urban planners, autonomous vehicle researchers, and GIS specialists analyze street-level imagery by automatically identifying and outlining objects like roads, buildings, pedestrians, and vehicles. It takes raw street photos or video frames as input and produces a detailed segmentation map, where each pixel is classified and colored according to the object it represents.

816 stars. No commits in the last 6 months.

Use this if you need to accurately segment urban scenes from image data for tasks like mapping, scene understanding, or training autonomous systems.

Not ideal if you are looking to segment images from different domains, such as medical scans or satellite imagery, as it is specifically trained for urban environments.

urban-planning autonomous-vehicles GIS street-level-mapping computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

816

Forks

181

Language

Python

License

MIT

Last pushed

Feb 09, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/fregu856/deeplabv3"

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