liangheming / maskrcnn
pytorch mask rcnn 736px,box mAP 39.0, seg mAP 33.7 (COCO val) 23.64fps(RTX 2080Ti)
☆10Updated 4 years ago
Alternatives and similar repositories for maskrcnn:
Users that are interested in maskrcnn are comparing it to the libraries listed below
- pytorch implement of CascadeRCNN,736px(max side),41.2mAP(COCO),21.94fps(RTX 2080TI)☆20Updated 11 months ago
- YOLOv4/v5, clean code, good performance,easy to understand.☆14Updated 4 years ago
- pytorch implement of FreeAnchor(not strict),640 px(max side),39.5mAP on COCO,43.18fps(RTX 2080TI)☆14Updated 4 years ago
- ATSS (retina) 39.6mAP on COCO,640px(max side),42.95fps(RTX 2080TI)<<Bridging the Gap Between Anchor-based and Anchor-free Detection via A…☆20Updated 4 years ago
- pytorch implement of retinanet,37.4 mAp(coco) at 640px(max side) ,44.24fps(RTX2080TI)☆18Updated 4 years ago
- Some Top-Down 2D Pose Estimation☆17Updated 4 years ago
- 这是一个retinanet-pytorch的源码,可以用于训练自己的模型。☆179Updated last year
- An unofficial pytorch implementation of <<AutoAssign: Differentiable Label Assignment for Dense Object Detection>>☆17Updated 4 years ago
- detector for rotated-object based on CenterNet/基于CenterNet的旋转目标检测☆400Updated 3 years ago
- ☆106Updated 2 years ago
- rotation detection based on yolov5☆375Updated last year
- 这是一个centernet-pytorch的源码,可以用于训练自己的模型。☆373Updated last year
- Trans DOTA OBB format(poly format) to YOLO format.☆202Updated 3 years ago
- GFocal 40.6mAP(COCO) 640px(max side) 44.05 fps(rtx 2080ti)☆11Updated 4 years ago
- ☆68Updated 3 years ago
- YOLOv7+KLD☆38Updated last year
- 这是一个efficientnet-yolo3-pytorch的源码,将yolov3的主干特征提取网络修改成了efficientnet☆146Updated last year
- ☆76Updated 3 years ago
- https://zhuanlan.zhihu.com/p/430850089☆149Updated 2 years ago
- FCOS ,640px(max side),mAP 38.2,fps45.45(RTX 2080TI).faster! better! <<Fully Convolutional One-Stage Object Detection>>☆19Updated 4 years ago
- 这里面存放了一些目标检测算法的数据增强方法。如mosaic、mixup。☆157Updated 2 years ago
- yolov5的注释版本☆270Updated 4 years ago
- NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite☆15Updated 4 months ago
- 这是一个efficientdet-pytorch的源码,可以用于训练自己的模型。☆313Updated last year
- 规范化管理labelme数据集并生成coco数据集☆85Updated 4 years ago