ABBYY recently announced the launch of NeoML, an open-source library for building, training, and deploying machine learning models. NeoML is a cross-platform framework optimized for applications that run in cloud environments, on desktop and mobile devices. It supports both deep learning and traditional machine learning algorithms.
NeoML framework is used by ABBYY engineers for computer vision and natural language processing tasks, including image preprocessing, classification, document layout analysis, OCR, and data extraction from structured and unstructured documents.
In terms of performance, “NeoML offers 15-20% faster performance for pre-trained image processing models running on any device*.” NeoML has been designed as a universal tool to process and analyze data in a variety of formats, including text, image, video, and others. It supports C++, Java, and Objective-C programming languages; Python will be added shortly.
- It comprises of neural networks with support for over 100 layer types
- It supports traditional machine learning: 20+ algorithms (classification, regression, clustering, etc.)
- It supports CPU and GPU along with the fast inference
- It supports ONNX (The Open Neural Network Exchange)
- It supports languages like C++, Java, Objective-C. Python will be added shortly
- It supports cross-platform. the same code can be run on Windows, Linux, macOS, iOS, and Android