Release 0.2.0
Release Date: 2020-11-20
Compatibility: The functional interfaces of Adlik r0.2 are compatible with r0.1.
Feature List
New Model Compiler
- Support DAG generation for end-to-end compilation of models with different representation.
- Source representation: H5, Ckpt, Pb, Pth, Onnx and SavedModel.
- Target representation: SavedModel, OpenVINO IR, TensorRT Plan and Tflite.
- Support model quantization for TfLite and TensorRT.
- Int8 quantization for TfLite.
- Int8 and fp16 quantization for TensorRT.
Inference Engine
- Support hybrid scheduling of ML and DL inference jobs.
- Support image based deployment of Adlik compiler and inference engine in cloud native environment.
- Deployment and functions has been tested in docker (V19.03.12) and Kubernetes (V1.13).
- Support Adlik running in RaspberryPi and JetsonNano.
- Support the newest version of OpenVINO (2021.1.110) and TensorFlow (2.3.1).
Benchmark Test
- Support benchmark test for models including ResNet-50, Inception V3, Yolo V3 and Bert with 4 devices and 5 runtimes
supported by Adlik.
Fixed issues
- Can Not Convert Yolo.h5 To Openvino Runtime.
- gRPC:Received message larger than max.
- Return Message Is Wrong When cudaMalloc() Failed In initializeOutputBindings() Method.
- Can Not Do Predict With Following Transferred YoloV3 Model.
- "adlik_serving --help" should exit successfully.
- benchmark cant auto infer by tensorflow gpu image.
- Prediction will fail if information in model.pbtxt and model representation not consistent in tensorflowLite runtime.