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

$ git clone https://gitlab.com/khadas/vim4_npu_sdk.git
$ cd vim4_npu_sdk
$ ls
bin  demo  docs  README.md

• docs: SDK documentations
• bin: SDK tools required for model conversion
• demo: Conversion examples

Get Docker:

$ cd vim4_npu_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 \
				yanwyb/npu:v1

Convert the demo model in docker:

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

If everything works well you will find the converted files below:

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

• model-type - Model type used in the conversion.
• model(model files)/weights(model weights file) - model parameter must be set. weights needs to be set when model-type is caffe/darknet/mxnet.
• inputs/input-shapes - inputs: Input node names. input-shapes: The sizes of input nodes. Need to be set when model-type is pytorch/onnx/mxnet/tensorflow/ tflite/paddle.
• outputs - Output node names. When model-type is tensorflow, outputs needs to be set.
• dtypes - Input type, set the type information corresponding to the input (optional).Default: float32.
• quantize-dtype - quantization type. Currently, it supports int8, int16 and uint8 quantization types. –source-file: dataset.txt. The txt file contains paths to the images that need to be quantitated. it supports image and npy files.
• channel-mean-value - the pre-processing parameters are set according to the pre processing methods used during model training. It includes four values, m1, m2, m3, and scale. The first three are mean-value parameters and the last one is the scale parameter. For the input data with three channels (data1, data2, data3), the pre-processing steps are:
  • Out1 = (data1-m1)/scale
  • Out2 = (data2-m2)/scale
  • Out3 = (data3-m3)/scale
• batch-size - Set the batch-size for the adla file after conversion. Currently, the default value is 1. –iterations: Optional parameter, if dataset.txt provides data for multi-groups, and needs to use all data provided for quantization, set –iterations and make sure iterations*batch size= Number of data in the multi-groups.
• outdir - Directory for the generated. The default value is the current directory:”./”.
• target-platform - specify the target platform for the adla file, it should be PRODUCT_PID0XA003 for VIM4

For more information, please check docs/model_conversion_user_guide_1.2.pdf.