segmentation_models.pytorch
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
- 12k
- Python
- MIT
- 6 h ago
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
A c++ trainable semantic segmentation library based on libtorch (pytorch c++). Backbone: VGG, ResNet, ResNext. Architecture: FPN, U-Net, PAN, LinkNet, PSPNet, DeepLab-V3, DeepLab-V3+ by now.
Scalable Instance Segmentation using PyTorch & PyTorch Lightning.
A production-ready, scalable multi-task perception system for autonomous vehicles, capable of handling multiple tasks simultaneously.
MobileNetV2 architecture combined with a dynamically generated Feature Pyramid Network
QuarkDet lightweight object detection in PyTorch .Real-Time Object Detection on Mobile Devices.