liangheming / atssv1
ATSS (retina) 39.6mAP on COCO,640px(max side),42.95fps(RTX 2080TI)<<Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection>>
☆20Updated 4 years ago
Alternatives and similar repositories for atssv1:
Users that are interested in atssv1 are comparing it to the libraries listed below
- pytorch implement of retinanet,37.4 mAp(coco) at 640px(max side) ,44.24fps(RTX2080TI)☆18Updated 4 years ago
- An unofficial pytorch implementation of <<AutoAssign: Differentiable Label Assignment for Dense Object Detection>>☆17Updated 4 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
- pytorch implement of FreeAnchor(not strict),640 px(max side),39.5mAP on COCO,43.18fps(RTX 2080TI)☆14Updated 4 years ago
- YOLOv4/v5, clean code, good performance,easy to understand.☆14Updated 4 years ago
- GFocal 40.6mAP(COCO) 640px(max side) 44.05 fps(rtx 2080ti)☆11Updated 4 years ago
- Some Top-Down 2D Pose Estimation☆17Updated 4 years ago
- pytorch mask rcnn 736px,box mAP 39.0, seg mAP 33.7 (COCO val) 23.64fps(RTX 2080Ti)☆10Updated 4 years ago
- pytorch implement of CascadeRCNN,736px(max side),41.2mAP(COCO),21.94fps(RTX 2080TI)☆20Updated last year
- Convert YOLOv3 and YOLOv3-tiny (PyTorch version) into TensorRT models.☆61Updated 5 years ago
- A real-time version of FCOS, inspired by FCOSv2.☆49Updated 3 years ago
- SOLOv2 on onnx & tensorRT☆54Updated 3 years ago
- RepVGG TensorRT int8 量化,实测推理不到1ms一帧!☆63Updated 3 years ago
- ☆25Updated 2 years ago
- 使用retinaface完成车牌关键点检测,并在tensorRT下部署☆40Updated 3 years ago
- Sparse R-CNN 38.9 mAP, 640px(max side), 30.95fps(RTX 2080TI)☆30Updated 4 years ago
- A Simple Baseline for Object Detection☆56Updated 3 years ago
- A pytorch re-implementation of Real-time Scene Text Detection with Differentiable Binarization☆22Updated 4 years ago
- A resnet18 version of CenterNet(objects as points)☆124Updated 3 years ago
- tensorrt wheels (API)☆77Updated 4 years ago
- Pytorch复现YOLOv3,使用最新的DIOU loss训练☆70Updated 4 years ago
- 对 YOLOv3 做模型剪枝(network slimming),对于 oxford hand 数据集(因项目需要),模型剪枝后的参数量减少 80%,Infer 的速度达到原来 2 倍,mAP 基本不变☆12Updated 5 years ago
- ☆13Updated 3 years ago
- You Only Look At Face☆35Updated 4 years ago
- my_custom_mmdetection☆59Updated 4 years ago
- fcos implementation in pytorch1.x☆99Updated 4 years ago
- Scaled-YOLOv4训练自己的数据集详细教程PDF,关于paper解读请联系小编获取PDF文档☆73Updated 4 years ago
- EfficientNetv2 TensorRT int8☆45Updated 3 years ago
- NVIDIA-阿里2021 TRT比赛 `二等奖` 代码提交 团队:美迪康 AI Lab☆170Updated 2 years ago
- Implement CondInst which is a instances segmentation method on YOLOX☆17Updated 2 years ago