NEW RELEASE: AI inference optimized for amazing with OpenVINO™ 2022.1 release

[JesusE_Intel]

This release comes with expanded NLP support, added device portability on your hardware, and higher inferencing performance—all with less code changes.

• New download experience: now it’s easier to customize your selection based on Dev Tools vs Runtime
• Upgrade to the latest version of Intel® Distribution of OpenVINO™ toolkit 2022.1 for new capabilities and performance improvements
• Updated, cleaner API:
• Introducing OpenVINO API 2.0. Better align inputs/outputs with frameworks. Tensors use native framework layouts and element types.
• Model Optimizer’s API parameters have been reduced to minimize complexity. Performance and has been significantly improved for model conversion on ONNX models.
• Portability and Performance: AUTO-Batching functionality automatically select the proper number batch increasing devices efficiency specially GPUs.
• New AUTO plugin self-discovers available system inferencing capacity based on model requirements, so applications no longer need to know their compute environment in advance.
• Automatic batching functionality via code hints will automatically scale batch size based on XPU and available memory.
• Built with 12th Gen Intel® Core™ “Alder Lake” in mind. Supports the hybrid architecture to deliver enhancements for high performance inferencing on CPU & integrated GPU.
• Broader Model Support: With Dynamic Input Shapes capabilities on CPU, OpenVINO will be able to adapt to multiple input dimensions in a single model providing more complete NLP support.  Dynamic Shapes support on additional XPUs expected in a future dot release.
• New Models with focus on NLP and a new category, Anomaly detection:
• Pre-trained Models: Anomaly segmentation with a focus on industrial inspection making Speech denoising trainable.  Plus, updates on speech recognition and speech synthesis.
• Combined demos include noise reduction + speech recognition + question answering + translation+ text to speech.
• Public Models: Focus on NLP ContextNet, Speech-Transformer,  HiFi-GAN,  Glow-TTS, FastSpeech2, and Wav2Vec to name a few.

RESOURCES

• Product Page
• Get Started
• Release Notes
• Documentation
• Learning Resources