ChainerCV: a Library for Deep Learning in Computer Vision

Abstract

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.

Accepted to ACM MM 2017 Open Source Software Competition

References in corpus (3)

• DSSD : Deconvolutional Single Shot Detector
• Speed/accuracy trade-offs for modern convolutional object detectors
• An Implementation of Faster RCNN with Study for Region Sampling

Cited by in corpus (7)

• Recent Advances in Deep Learning: An Overview
• PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track
• Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions
• Parallel Grid Pooling for Data Augmentation
• Performance, Successes and Limitations of Deep Learning Semantic Segmentation of Multiple Defects in Transmission Electron Micrographs
• Data-parallel distributed training of very large models beyond GPU capacity
• LoANs: Weakly Supervised Object Detection with Localizer Assessor Networks