Release Notes for Intel® Distribution of OpenVINO™ toolkit 2019のupdated July 24, 2019にて、
・Added Deep Learning Workbench Profiler for neural network topologies and layers ・Added new non-vision topologies: GNMT, BERT, TDNN (NNet3), ESPNet ・Introduced new Inference Engine Core APIs. Core APIs automate direct mapping to devices, provide Query API for configuration and metrics to determine best deployment platform. ・Added Multi Device Inference with automatic load-balancing across available devices for higher throughput. ・Serialized FP16 Intermediate Representation to work uniformly across all platforms to reduce model size by 2x compared to FP32, improve utilization of device memory and portability of models. ・Model Optimizer Renamed Intel® experimental layer Quantize to FakeQuantize and ONNX Intel® experimental operator Quantize to FakeQuantize. ・Multi-Device plugin Automatic inference load-balancing between multiple devicesなどなど。。。
ブラウザベースのプロファイラなんだね。。。