liangheming / free_anchorv1Links
pytorch implement of FreeAnchor(not strict),640 px(max side),39.5mAP on COCO,43.18fps(RTX 2080TI)
☆14Updated 4 years ago
Alternatives and similar repositories for free_anchorv1
Users that are interested in free_anchorv1 are comparing it to the libraries listed below
Sorting:
- pytorch implement of retinanet,37.4 mAp(coco) at 640px(max side) ,44.24fps(RTX2080TI)☆18Updated 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
- YOLOv4/v5, clean code, good performance,easy to understand.☆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 mask rcnn 736px,box mAP 39.0, seg mAP 33.7 (COCO val) 23.64fps(RTX 2080Ti)☆10Updated 4 years ago
- An unofficial pytorch implementation of <<AutoAssign: Differentiable Label Assignment for Dense Object Detection>>☆17Updated 4 years ago
- tensorrt5 , centernet , centerface, deform conv, int8☆772Updated 2 years ago
- This repo is implemented based on detectron2 and centernet☆558Updated 4 years ago
- Some Top-Down 2D Pose Estimation☆17Updated 4 years ago
- TensorRT ONNX Plugin、Inference、Compile☆469Updated 4 years ago
- Replication of MOT project - DeepSort with attention blocks.☆220Updated 3 years ago
- convert mmdetection model to tensorrt, support fp16, int8, batch input, dynamic shape etc.☆599Updated last year
- yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝,通道剪枝,知识蒸馏☆1,515Updated 5 years ago
- TensorRT-7 Network Lib 包括常用目标检测、关键点检测、人脸检测、OCR等 可训练自己数据☆533Updated 4 years ago
- Two-stage CenterNet☆1,223Updated 2 years ago
- mobilev2-yolov5s剪枝、蒸馏,支持ncnn,tensorRT部署。ultra-light but better performence!☆854Updated 2 years ago
- reproduce the YOLO series of papers in pytorch, including YOLOv4, PP-YOLO, YOLOv5,YOLOv3, etc.☆389Updated 4 years ago
- Real time one-stage multi-class & multi-object tracking based on anchor-free detection and ReID☆402Updated 3 years ago
- realtime multiple people tracking (centerNet based person detector + deep sort algorithm with pytorch)☆597Updated 5 years ago
- Cross Stage Partial Networks☆906Updated 5 years ago
- detector for rotated-object based on CenterNet/基于CenterNet的旋转目标检测☆399Updated 4 years ago
- pytorch implement of CascadeRCNN,736px(max side),41.2mAP(COCO),21.94fps(RTX 2080TI)☆19Updated last year
- training for VOC dataset☆11Updated 5 years ago
- ☆718Updated 2 years ago
- yolov3 with mobilenet v2 and ASFF☆1,071Updated 4 years ago
- support deepsort and bytetrack MOT(Multi-object tracking) using yolov5 with C++☆937Updated 2 years ago
- Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection, CVPR, Oral, 2020☆1,086Updated 4 years ago
- ☆12Updated 4 years ago
- An implementation of YOLOv1 for object detection in TensorFlow.☆12Updated 4 years ago
- YOLO ModelCompression MultidatasetTraining☆444Updated 3 years ago