Introduction and guide on how to use the KSNN conversion tool.

The conversion tool is integrated in the NPU SDK.

$ git clone --recursive https://github.com/khadas/aml_npu_sdk.git

The KSNN conversion tool is under acuity-toolkit/python,

$ cd aml_npu_sdk/acuity-toolkit/python && ls
$ convert  data  outputs

Choose tensorflow Inception V3 as a exmple.

1. Get forzen model,

$ cd aml_npu_sdk/acuity-toolkit/python
$ wget https://github.com/yan-wyb/models-zoo/raw/master/tensonrflow/inception/inception_v3_2016_08_28_frozen.pb

2. Convert,

$ ./convert --model-name inception \
>           --platform tensorflow \
>           --model /home/yan/yan/Yan/models-zoo/tensorflow/inception/inception_v3_2016_08_28_frozen.pb \
>           --input-size-list '299,299,3' \
>           --inputs input \
>           --outputs InceptionV3/Predictions/Reshape_1 \
>           --mean-values '128 128 128 0.0078125' \
>           --quantized-dtype asymmetric_affine \
>           --source-files ./data/dataset/dataset0.txt \
>           --kboard VIM3 --print-level 0

During conversion, if you need to view detailed information, you can modify –print-level 0 to –print-level 1.

3. File generated after conversion.

$ cd aml_npu_sdk/acuity-toolkit/python
$ ls outputs/inception/
inception.nb  libnn_inception.so

1. KSNN Usage
2. KSNN API Documentation