songwsx

东北大学

Pinned Repositories

person-detection
TensorRT person tracking RFBNet300
Language:C++1 1 00
person_search_demo
利用YOLOv3结合行人重识别模型，实现行人的检测识别，查找特定行人
Language:Python531 9 29135
product_detection
Working with scale: 2nd place solution to Product Detection in Densely Packed Scenes
Language:Python0 1 00
RFB-Person
利用RFB进行行人检测的基线代码
Language:Python16 1 14
RFBNet
Receptive Field Block Net for Accurate and Fast Object Detection, ECCV 2018
Language:Python2 1 00
RFSong-779
重新设计的RFBNet300,模型参数量只有0.99MB，AP达到0.78，200FPS
Language:Python99 7 1026
RFSong-7993
设计的轻量级RFB进行行人检测，AP达到0.7993，参数量仅有3.1MB，200 FPS
Language:Python174 9 950
steel-detect
数钢筋demo，IOU 0.7 下，AP 90.6。训练只要不到十分钟，可以非常愉快的玩耍
Language:Python32 3 26
Ultra-Light-Fast-Generic-Face-Detector-1MB
一款超轻量级通用人脸检测模型，模型参数量1MB，320x240输入下计算量仅90MFlops，适用于边缘计算设备、低算力设备以及PC
Language:Python7 1 01

songwsx/person_search_demo
利用YOLOv3结合行人重识别模型，实现行人的检测识别，查找特定行人
Language:Python531 9 29135
songwsx/RFSong-7993
设计的轻量级RFB进行行人检测，AP达到0.7993，参数量仅有3.1MB，200 FPS
Language:Python174 9 950
songwsx/RFSong-779
重新设计的RFBNet300,模型参数量只有0.99MB，AP达到0.78，200FPS
Language:Python99 7 1026
songwsx/steel-detect
数钢筋demo，IOU 0.7 下，AP 90.6。训练只要不到十分钟，可以非常愉快的玩耍
Language:Python32 3 26
songwsx/RFB-Person
利用RFB进行行人检测的基线代码
Language:Python16 1 14
songwsx/Ultra-Light-Fast-Generic-Face-Detector-1MB
一款超轻量级通用人脸检测模型，模型参数量1MB，320x240输入下计算量仅90MFlops，适用于边缘计算设备、低算力设备以及PC
Language:Python7 1 01
songwsx/RFBNet
Receptive Field Block Net for Accurate and Fast Object Detection, ECCV 2018
Language:Python2 1 00
songwsx/person-detection
TensorRT person tracking RFBNet300
Language:C++1 1 00
songwsx/product_detection
Working with scale: 2nd place solution to Product Detection in Densely Packed Scenes
Language:Python0 1 00