yzqxy / yolov5_obb_prune_tracking
☆38Updated last year
Alternatives and similar repositories for yolov5_obb_prune_tracking:
Users that are interested in yolov5_obb_prune_tracking are comparing it to the libraries listed below
- ☆191Updated last year
- Make it easier for yolov6 to change the network structure☆70Updated 5 months ago
- 🚀🚀🚀YOLOC is Combining different modules to build an different Object detection model.Including YOLOv3、YOLOv4、Scaled_YOLOv4、YOLOv5、YOLO…☆72Updated 2 years ago
- 可以训练yolov5(v6.0)、yolox、小型网络，添加注意力机制☆66Updated 3 years ago
- YOLOv7+KLD☆38Updated last year
- 在YOLOv7的基础上使用KLD损失修改为旋转目标检测yolov7-obb☆186Updated last year
- ☆105Updated 3 years ago
- ☆95Updated last year
- Pytorch implementation of the 'Slim-neck by GSConv: a lightweight-design for real-time detector architectures'☆215Updated 3 weeks ago
- KLD实现旋转目标检测☆47Updated 2 years ago
- ☁️💡🎈专注于改进YOLOv7，Support to improve Backbone, Neck, Head, Loss, IoU, NMS and other modules☆203Updated last year
- https://zhuanlan.zhihu.com/p/430850089☆151Updated 2 years ago
- CoordAttention_YOLOX(基于CoordAttention坐标注意力机制的改进版YOLOX目标检测平台）☆49Updated 2 years ago
- ☆63Updated 4 years ago
- Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism☆78Updated last year
- ☆27Updated 2 years ago
- ☆55Updated last year
- 本项目支持对剪枝后的yolov5模型进行知识蒸馏训练(This project supports knowledge distillation training for the pruned YOLOv5 model)☆100Updated last year
- rotated bbox detection. inspired by https://github.com/hukaixuan19970627/YOLOv5_DOTA_OBB, thanks hukaixuan19970627.☆89Updated 2 years ago
- ☆140Updated 3 years ago
- [T-PAMI'23] PAGCP for the compression of YOLOv5☆116Updated 2 years ago
- ☆29Updated 2 years ago
- YOLOv5的轻量化改进(蜂巢检测项目)☆73Updated 2 years ago
- ☆78Updated 3 years ago
- 实现对YOLOX的剪枝操作，添加了卷积层和BN层融合推理，添加中间层可视化功能，可实现预测和训练日志保存☆45Updated 2 years ago
- 基于YoloV5的一些魔改及相关部署方案☆63Updated 3 years ago
- yolov5实现基于kld的旋转目标检测☆27Updated 2 years ago
- ☆38Updated last year
- Multi-backbone, Prune, Quantization, KD☆158Updated 2 years ago
- 知识蒸馏复现相关☆25Updated 2 years ago