版本指路：https://github.com/Adlik/Adlik/releases/tag/v1.0.0

中文版：Release Fox版本特性

Compiler

  • Spport compiling ONNX model to the data format which can be accelerated by Cloudblazer Yunsui i20 with a Suixi 2.5 chip of Enflame company
  • Upgrade OpenVINO to 2022.3.0
  • Upgrade TensorFlow to 2.10.1
  • Upgrade TensorRT to 8.4.3.1
  • Upgrade Ubuntu to 20.04, Python to 3.8 and CUDA to 11.6 in the base docker images

Inference Engine

  • Support model inference on Cloudblazer Yunsui i20
  • Upgrade OpenVINO to 2022.3.0
  • Upgrade TensorFlow to 2.10.1
  • Upgrade TensorRT to 8.4.3.1
  • Upgrade Ubuntu to 20.04, Python to 3.8 and CUDA to 11.6 in the base docker images

Model Zoo:

  • Add MobileNet v2 series model, with 72.396% accuracy on the imagenet-1k dataset

Benchmark Test:

  • Complete Benchmark tests of YOLOv5m and MaskRcnn on the Intel 8260 CPU, including accuracy, performance indicators such as throughput
  • No labels