kerrgarr/SemanticSegmentationCityscapes
A simple image segmentation model called ‘my_FCN’ is compared with a conventional U-Net architecture and DeepLabV3+ on a subset of the Cityscapes dataset.
This project helps urban planners, autonomous vehicle engineers, or smart city developers understand street scenes by segmenting images into meaningful categories like roads, cars, and pedestrians. It takes raw street view images and their corresponding pixel-level annotations as input, and outputs a trained model capable of identifying different objects within new urban images. The target user is anyone who needs to analyze or classify elements within urban street photography.
No commits in the last 6 months.
Use this if you need to experiment with and compare different semantic segmentation models for urban street scenes using readily available computational resources.
Not ideal if you need a pre-trained model for immediate deployment without model comparison or if your primary interest is object detection or instance segmentation.
Stars
12
Forks
2
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Dec 04, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kerrgarr/SemanticSegmentationCityscapes"
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.