07-14-2020 09:48 AM
What’s New in the Release
- Improves performance while maintaining accuracy close to full precision (for example, FP32 data type) by introducing support for the Bfloat16 data type for inferencing using the 3rd generation Intel® Xeon® Scalable processor (formerly code-named Cooper Lake).
- Increases accuracy when layers have varying bit-widths by extending the Post-Training Optimization Tool to support mixed-precision quantization.
- Allows greater compatibility of models by supporting directly reading Open Neural Network Exchange (ONNX*) model format to the Inference Engine.
- For users looking to take full advantage of Intel® Distribution of OpenVINO™ toolkit, it is recommended to follow the native workflow of using the Intermediate Representation from the Model Optimizer as input to the Inference Engine.
- For users looking to more easily take a converted model in ONNX model format (for example, PyTorch to ONNX using torch.onnx), they are now able to input the ONNX format directly to the Inference Engine to run models on Intel architecture.
- Enables initial support for TensorFlow* 2.2.0 for computer vision use cases.
- Enables users to connect to and profile multiple remote hosts; collect and store data in one place for further analysis by extending the Deep Learning Workbench with remote profiling capability.
- Support for additional public models, which includes:
- Original models: DeepSpeech, GPT-2, 3D U-Net and PRNet models
- Low precision (that is, int8) models: MTCNN, 3D U-Net, BERT model, PRNet 3D, DCSCN, and support for quantization of cascaded models for improved performance when converting models into a pipeline
- Introduces new and updated pretrained models on Open Model Zoo that improves accuracy and performance trade-off and reduces time to production, which includes:
- Weld porosity detection new model and demo
- Person in-painting trainable model and demo
- Open-closed eye new and trainable models
- Published new performance benchmarks based on release improvements