Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

Feature Pyramid Networks for Object Detection

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.

R2CNN: Rotational Region CNN Based on FPN (Tensorflow)

A Tensorflow implementation of FPN detection framework.

A semantic segmentation toolbox based on PyTorch

This is a tensorflow re-implementation of Feature Pyramid Networks for Object Detection.

Implement of paper 《Attention-guided Context Feature Pyramid Network for Object Detection》

Faster R-CNN / R-FCN 💡 C++ version based on Caffe

A Python Library for High-Level Semantic Segmentation Models based on TensorFlow and Keras with pretrained backbones.

Scalable Instance Segmentation using PyTorch & PyTorch Lightning.

FasterRCNN is implemented in VGG, ResNet and FPN base.

An easy implementation of FPN (https://arxiv.org/pdf/1612.03144.pdf) in PyTorch.

R-DFPN: Rotation Dense Feature Pyramid Networks (Tensorflow)

[BMVC-20] Official PyTorch implementation of PPDet.

QuarkDet lightweight object detection in PyTorch .Real-Time Object Detection on Mobile Devices.

Mask R-CNN, FPN, LinkNet, PSPNet and UNet with multiple backbone architectures support readily available

PyTorch implementations of some FPN-based semantic segmentation architectures: vanilla FPN, Panoptic FPN, PANet FPN; with ResNet and EfficientNet backbones.

Caffe version Generalized & Distance & Complete Iou loss Implementation for Faster RCNN/FPN bbox regression