基于 PyTorch 和 MMCV 的通用目标检测平台。支撑了 3D 目标检测、旋转框检测、场景文字识别、姿态估计、目标跟踪等算法库中检测算法的实现;支持 2D 目标检测、实例分割、全景分割任务;支持算法多样,涵盖了单阶段、双阶段和级联模型等各任务中的典型算法和各类训练技术;为通用目标检测算法的研发提供了高性能基准
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection.
EfficientDet (Scalable and Efficient Object Detection) implementation in Keras and Tensorflow
This is a tensorflow re-implementation of Feature Pyramid Networks for Object Detection.
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
Faster R-CNN R-101-FPN model was implemented with tensorflow eager execution.