VGG16 is a convolution neural net architecture that’s used for image recognition. It utilizes 16 layers with weights and is considered one of the best vision model architectures to date.

Daipuwei/Mini-VGG-CIFAR10

$ git clone https://github.com/Daipuwei/Mini-VGG-CIFAR10

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

Then fetch the prebuilt NPU Docker Container and run it.

$ 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

Download Tool from khadas/vim4_npu_sdk.

$ git clone https://gitlab.com/khadas/vim4_npu_sdk

We first need to convert the Keras model(.h5) into a TensorFlow model (.pb). We use this tool to convert amir-abdi/keras_to_tensorflow

$ git clone https://github.com/amir-abdi/keras_to_tensorflow

Then we need to convert the Tensorflow model to an ADLA model (.adla)

Enter vim4_npu_sdk/demo and overwrite convert_adla.sh as follows.

convert_adla.sh

#!/bin/bash
 
ACUITY_PATH=../bin/
#ACUITY_PATH=../python/tvm/
adla_convert=${ACUITY_PATH}adla_convert
 
 
if [ ! -e "$adla_convert" ]; then
    adla_convert=${ACUITY_PATH}adla_convert.py
fi
 
$adla_convert --model-type tensorflow \
        --model ./model_source/vgg16/vgg16.pb \
        --inputs image_input --input-shapes 32,32,3 \
        --outputs dense_2/Softmax \
        --inference-input-type float32 \
		--inference-output-type float32 \
        --quantize-dtype int8 --outdir tensorflow_output \
        --channel-mean-value "0,0,0,255" \
        --source-file vgg16_dataset.txt \
        --iterations 500 \
        --batch-size 1 \
        --target-platform PRODUCT_PID0XA003

Run convert_adla.sh to generate VIM4 model. The converted model is xxx.adla in tensorflow_output.

$ bash convert_adla.sh

Clone the source code from our khadas/vim4_npu_applications.

$ git clone https://github.com/khadas/vim4_npu_applications

$ sudo apt update
$ sudo apt install libopencv-dev python3-opencv cmake

Put vgg16_int8.adla in vim4_npu_applications/vgg16/data/.

# Compile
$ cd vim4_npu_applications/vgg16
$ mkdir build
$ cd build
$ cmake ..
$ make
 
# Run
$ sudo ./vgg16 -m ../data/vgg16_int8.adla -p ../data/airplane.jpeg