We propose a scalable, efficient and accurate approach to retrieve 3D models for objects in the wild. Our contri- bution is twofold. We first present a 3D pose estimation approach for object categories which significantly outper- forms the state-of-
HandPose_Detection
使用卷积神经网络进行姿态检测的背景减法这项工作的灵感来自
数据集准备
Run python2 dataset.py to prepare the dataset
Classes=Super,Palm,Fist,Thumbs_up,Victory,Why
run the code after 30 frame pose your hand in the bounding box displayed on the video
训练
Then Resize th
