artificial intelligence artificial intelligenceartificial intelligenceartificial intelligenceartificial intelligenceartificial intelligence artificial intelligenceartificial intelligenceartificial intelligenceartificial intelligenceartificial intelligence artificial intelligenceartificial intelligenceartificial intelligenceartificial intelligence

Neural Network Compression Framework for fast model inference

In this work we present a new framework for neural networks compression with fine-tuning, which we called Neural Network Compression Framework (NNCF). It leverages recent advances of various network compression methods and implements some of them, such as sparsity, quantization, and binarization. These methods allow getting more hardware-friendly models which can be efficiently run on general-purpose hardware computation units (CPU, GPU) or special Deep Learning accelerators. We show that the developed methods can be successfully applied to a wide range of models to accelerate the inference time while keeping the original accuracy. The framework can be used within the training samples, which are supplied with it, or as a standalone package that can be seamlessly integrated into the existing training code with minimal adaptations. Currently, a PyTorch version of NNCF is available as a part of OpenVINO Training Extensions at this https URL.


Automated Decision   Support & Scoring    Natural Language Processing    Computer Vision     Automated Decision   Support & Scoring    Natural Language Processing     Computer Vision     speech analytics
Ask a question
The message has been successfully sent
Got it!
To become a partner of AI Journey 2020
Attach file
*Maximum size for downloaded file 7 MB in txt, jpg, rtf, doc, docx, pdf, png.
The request has been successfully sent