CVNets: High Performance Library for Computer Vision
This provides a high-performance library for researchers and practitioners in computer vision, but it is incremental as it builds on existing methods.
The authors tackled the need for efficient deep learning tools in computer vision by introducing CVNets, an open-source library that achieves similar or better performance than previous studies in tasks like classification, detection, and segmentation.
We introduce CVNets, a high-performance open-source library for training deep neural networks for visual recognition tasks, including classification, detection, and segmentation. CVNets supports image and video understanding tools, including data loading, data transformations, novel data sampling methods, and implementations of several standard networks with similar or better performance than previous studies. Our source code is available at: \url{https://github.com/apple/ml-cvnets}.