pytorch-semseg and pytorch_tiramisu
Both tools offer PyTorch implementations of semantic segmentation architectures, making them **competitors** for users seeking a framework for this task.
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 pytorch_tiramisu
bfortuner/pytorch_tiramisu
FC-DenseNet in PyTorch for Semantic Segmentation
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work