Despite significant progress of deep learning in the field of computer vision, there has not been a software library that covers these methods in a unifying manner. We introduce ChainerCV, a software library that is intended to fill this gap. ChainerCV supports numerous neural network models as well as software components needed to conduct research in computer vision. These implementations emphasize simplicity, flexibility and good software engineering practices. The library is designed to perform on par with the results reported in published papers and its tools can be used as a baseline for future research in computer vision. Our implementation includes sophisticated models like Faster R-CNN and SSD, and covers tasks such as object detection and semantic segmentation.
@article{arxiv.1708.08169,
title = {ChainerCV: a Library for Deep Learning in Computer Vision},
author = {Yusuke Niitani and Toru Ogawa and Shunta Saito and Masaki Saito},
journal= {arXiv preprint arXiv:1708.08169},
year = {2017}
}
Comments
Accepted to ACM MM 2017 Open Source Software Competition