pytorch-semseg and Fast-SCNN-pytorch
The architectures implemented in the first tool could be trained with the fast semantic segmentation network implemented in the second tool, making them complements.
About pytorch-semseg
meetps/pytorch-semseg
Semantic Segmentation Architectures Implemented in PyTorch
Implements 8+ segmentation architectures (PSPNet, FCN, U-Net, SegNet, LinkNet, ICNet, FRRN) with pretrained weights and integrated support for 7 major datasets (Pascal VOC, Cityscapes, ADE20K, CamVid, NYUDv2, etc.). Provides YAML-based configuration for training with modular components including multiple optimizers, learning rate schedules, data augmentation pipelines, and loss functions. Includes utilities for validation with flip augmentation, inference on custom images with optional DenseCRF post-processing, and real-time FPS measurement.
About Fast-SCNN-pytorch
Tramac/Fast-SCNN-pytorch
A PyTorch Implementation of Fast-SCNN: Fast Semantic Segmentation Network
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work