MobileNet

Environment Setup

info

Follow RKNN Installation to set up the environment.

Follow RKNN Model Zoo to download the example files.

Model Download

Download the ONNX model file.

X64 Linux PC

cd rknn_model_zoo/examples/mobilenet/model/
bash download_model.sh

Model Conversion

Select the target platform.

rk3588

X64 Linux PC

export TARGET_PLATFORM=rk3588

rk356x

X64 Linux PC

export TARGET_PLATFORM=rk356x

rk3576

X64 Linux PC

export TARGET_PLATFORM=rk3576

Convert the ONNX model to an RKNN model.

tip

After running the conversion script, you can see the model output.

X64 Linux PC

cd ../python/
python mobilenet.py --model ../model/mobilenetv2-12.onnx --target ${TARGET_PLATFORM}

Model output:

-----TOP 5-----
[494] score=0.98 class="n03017168 chime, bell, gong"
[653] score=0.01 class="n03764736 milk can"
[469] score=0.00 class="n02939185 caldron, cauldron"
[505] score=0.00 class="n03063689 coffeepot"
[463] score=0.00 class="n02909870 bucket, pail"

C API

Build the Example

Go to the rknn_model_zoo directory and run build-linux.sh to build.

X64 Linux PC

cd ../../..
bash build-linux.sh -t ${TARGET_PLATFORM} -a aarch64 -d mobilenet

Sync Files to the Device

Copy the built demo directory under the install folder to the device.

X64 Linux PC

cd install/${TARGET_PLATFORM}_linux_aarch64/
scp -r rknn_mobilenet_demo/ user@your_device_ip:target_directory

Run the Example

Export the runtime libraries to the environment variable.

Device

cd rknn_mobilenet_demo/
export LD_LIBRARY_PATH=./lib

Run the example.

Device

./rknn_mobilenet_demo ./model/mobilenet_v2.rknn ./model/bell.jpg

$ ./rknn_mobilenet_demo ./model/mobilenet_v2.rknn ./model/bell.jpg
num_lines=1001
model input num: 1, output num: 1
input tensors:
  index=0, name=input, n_dims=4, dims=[1, 224, 224, 3], n_elems=150528, size=150528, fmt=NHWC, type=INT8, qnt_type=AFFINE, zp=-14, scale=0.018658
output tensors:
  index=0, name=output, n_dims=2, dims=[1, 1000, 0, 0], n_elems=1000, size=1000, fmt=UNDEFINED, type=INT8, qnt_type=AFFINE, zp=-55, scale=0.141923
model is NHWC input fmt
model input height=224, width=224, channel=3
origin size=500x333 crop size=496x320
input image: 500 x 333, subsampling: 4:4:4, colorspace: YCbCr, orientation: 1
src width is not 4/16-aligned, convert image use cpu
finish
rknn_run
[494] score=0.993227 class=n03017168 chime, bell, gong
[469] score=0.002560 class=n02939185 caldron, cauldron
[747] score=0.000466 class=n04023962 punching bag, punch bag, punching ball, punchball
[792] score=0.000466 class=n04208210 shovel
[618] score=0.000405 class=n03633091 ladle

This output indicates the model classifies the image as bell, gong.

Test Image

Python API

This example does not provide a standalone Python API script; you can implement one yourself.