Published inOpenVINO-toolkit·3 days agoAccelerate Big Transfer (BiT) Model Even More with Quantization using OpenVINO and Neural Network Compression Framework (NNCF)Authors: Pradeep Sakhamoori, Ravi Panchumarthy, Nico Galoppo. 1. Introduction In the first part of this blog series, we discussed how to use Intel®’s OpenVINO™ toolkit to accelerate inference of the Big Transfer (BiT) model for computer vision tasks. We covered the process of importing the BiT model into the OpenVINO environment, leveraging…Model7 min readModel7 min read
Published inOpenVINO-toolkit·4 days agoUnleashing the Power of Model Optimization and Benchmarking with Intel® Deep Learning Workbench on Intel® Developer Cloud for The EdgeAuthor: Başak Çaprak Şenzeybek- Edge Software Architect In the ever-evolving landscape of AI and machine learning, data scientists, application developers, and sales managers are constantly seeking ways to maximize the potential of their models. Enter Intel® Deep Learning Workbench, designed to streamline the process of model optimization and analysis on…Model7 min readModel7 min read
Published inOpenVINO-toolkit·4 days agoImporting PyTorch and TensorFlow Models Into OpenVINOAuthor: Ryan Loney, Product Manager, OpenVINO™ Toolkit Executive Summary It is simple to import PyTorch and TensorFlow models into OpenVINO with only a few lines of code. Models that have been developed in PyTorch or TensorFlow can easily be integrated into an OpenVINO inference pipeline for best-in-class performance on a wide variety…AI11 min readAI11 min read
Published inOpenVINO-toolkit·Nov 22Think, say, see it! Chaining Multi-Modal Generative AI models on CPUs and GPUsFrom Speech Transcription to Image Generation in Seconds — Author: Ria Cheruvu — AI SW Architect and Gen AI Evangelist Credits: Paula Ramos, Raymond Lo, and the OpenVINO Notebooks team! Generative AI models are increasingly getting better at achieving complex functionalities. With the creation of more efficient and responsive computing ecosystems, exciting opportunities are quickly being unlocked. …AI6 min readAI6 min read
Published inOpenVINO-toolkit·Nov 21Automated Self-CheckoutAuthor: Ria Cheruvu, AI Software Evangelist Artificial Intelligence revolutionizes the store experience — from automating inventory tasks to improving the efficiency of retail processes — ultimately providing deeper insights into retailers’ decision-making. Across the retail sector, businesses struggle to keep up with labor shortages, rising costs, and customer expectations. AI…Retail5 min readRetail5 min read
Published inOpenVINO-toolkit·Nov 17Introducing OpenVINO 2023.2Author: Yury Gorbachev — Intel Fellow, OpenVINO Product Architecture AI is evolving at an ever-increasing pace in the past year, fueled by the introduction of Generative AI models and the evolution of scenarios that benefit from it. We acknowledge this and have decided to release new versions of OpenVINO™ quicker…Openvino7 min readOpenvino7 min read
Published inOpenVINO-toolkit·Oct 31Edge Insights for Vision — an automatic way to install Intel GPU drivers for AI application developmentUsing Intel GPUs for AI software development requires drivers to be installed. In order to make your work more efficient, we have created a solution that allows you to install them automatically. Find out what Edge Insights for Vision is and how it can help you in your daily work. …Edge Ai3 min readEdge Ai3 min read
Published inOpenVINO-toolkit·Oct 25Accelerate Inference of Hugging Face Transformer Models with Optimum Intel and OpenVINO™Authors: Xiake Sun, Kunda Xu 1. Introduction Hugging Face is a large open-source community that quickly became an enticing hub for pre-trained deep learning models across Natural Language Processing (NLP), Automatic Speech Recognition(ASR), and Computer Vision (CV) domains. Optimum Intel provides a simple interface to optimize Transformer models and convert them to…AI6 min readAI6 min read
Published inOpenVINO-toolkit·Oct 25Joint Pruning, Quantization and Distillation for Efficient Inference of TransformersIntroduction Pre-trained transformer models are widely deployed for various NLP tasks such as text classification, question answering, and generation tasks. The recent trend is that models continue to scale while yielding improved performance. However, the growth of transformers also leads to a great amount of compute resources and energy needed for…Artificial Intelligence8 min readArtificial Intelligence8 min read
Published inOpenVINO-toolkit·Oct 25Enable LoRA weights with Stable Diffusion Controlnet PipelineAuthors: Zhen Zhao(Fiona), Kunda Xu — Low-Rank Adaptation(LoRA) is a novel technique introduced to deal with the problem of fine-tuning Diffusers and Large Language Models (LLMs). In the case of Stable Diffusion fine-tuning, LoRA can be applied to the cross-attention layers for the image representations with the latent described. …Stable Diffusion9 min readStable Diffusion9 min read
