Follow Docker official docs to install: Install Docker Engine on Ubuntu.

$ git clone https://gitlab.com/khadas/vim4npu_sdk.git
$ cd vim4npu_sdk & ls
bin  demo  docs  README.md

• docs: SDK documentation.
• bin: All compilation tools required for model conversion.
• demo: Conversion examples for different platforms.

Get Docker,

$ cd vim4npu_sdk
$ docker pull yanwyb/npu:v1
$ docker run -it --name vim4-npu1 -v $(pwd):/home/khadas/npu \
				-v /etc/localtime:/etc/localtime:ro \
				-v /etc/timezone:/etc/timezone:ro \
				-v $HOME/.ccache:/home/khadas/.ccache --privileged \
				--device=/dev/loop-control:/dev/loop-control \
				--device=/dev/loop0:/dev/loop0 --cap-add SYS_ADMIN yanwyb/npu:v1

Run in docker,

khadas@2655b6cbbc01:~/npu$ cd demo/
khadas@2655b6cbbc01:~/npu/demo$ bash convert_adla.sh

Each platform will generate an adla file according to the demo.

khadas@2655b6cbbc01:~/npu/demo$ ls
caffe_output     darknet_output  dataset.txt   libstdc++_so  mxnet_output  paddle_output   quantized_tflite_output  tflite_output
convert_adla.sh  data            keras_output  model_source  onnx_output   pytorch_output  tensorflow_output