amberwalker-ds/u-net_semantic_segmentation
This project demonstrates the use of a U-Net neural network for segmenting building footprints from aerial images. It explores data preprocessing, model architecture, training, and evaluation while achieving high performance (94.7% accuracy and a Dice score of 76.7%). Note: A GPU is required to run the model.
No commits in the last 6 months.
Stars
4
Forks
1
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/amberwalker-ds/u-net_semantic_segmentation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
gradio-app/gradio
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
opengeos/segment-geospatial
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
wkentaro/osam
Get up and running with SAM1-3, EfficientSAM, YOLO-World, and other promptable vision models locally.
juglab/EmbedSeg
Code Implementation for EmbedSeg, an Instance Segmentation Method for Microscopy Images
coolzhao/Geo-SAM
A QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating...