Deep Learning & GPU Implementation Proposal

by Yida Wang for Open Source Computer Vision Library (OpenCV)

Both class and pose label are in consideration in the triplet loss of CNN. About the training and feature extraction process, it is a rough implementation by using OpenCV and Caffe from the idea of Paul Wohlhart. The principal purpose of this API is constructing a well labeled database from .ply models for CNN training with triplet loss and extracting features with the constructed model for prediction or other purpose of pattern recognition.