ResNet

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/resnet/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 resnet.py ../model/resnet50-v2-7.onnx ${TARGET_PLATFORM}

Model output:

-----TOP 5-----
[155] score=0.83 class="n02086240 Shih-Tzu"
[154] score=0.14 class="n02086079 Pekinese, Pekingese, Peke"
[262] score=0.02 class="n02112706 Brabancon griffon"
[283] score=0.00 class="n02123394 Persian cat"
[152] score=0.00 class="n02085782 Japanese spaniel"

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 resnet

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_resnet_demo/ user@your_device_ip:target_directory

Run the Example

Export the runtime libraries to the environment variable.

Device

cd rknn_resnet_demo/
export LD_LIBRARY_PATH=./lib

Run the example.

Device

./rknn_resnet_demo ./model/resnet50-v2-7.rknn ./model/dog_224x224.jpg

$ ./rknn_resnet_demo ./model/resnet50-v2-7.rknn ./model/dog_224x224.jpg
num_lines=1001
model input num: 1, output num: 1
input tensors:
  index=0, name=data, 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=resnetv24_dense0_fwd, n_dims=2, dims=[1, 1000, 0, 0], n_elems=1000, size=1000, fmt=UNDEFINED, type=INT8, qnt_type=AFFINE, zp=-62, scale=0.146746
model is NHWC input fmt
model input height=224, width=224, channel=3
origin size=224x224 crop size=224x224
input image: 224 x 224, subsampling: 4:2:0, colorspace: YCbCr, orientation: 1
rga_api version 1.10.1_[0]
rknn_run
[155] score=0.792182 class=n02086240 Shih-Tzu
[154] score=0.182606 class=n02086079 Pekinese, Pekingese, Peke
[262] score=0.013012 class=n02112706 Brabancon griffon
[152] score=0.002237 class=n02085782 Japanese spaniel
[283] score=0.001931 class=n02123394 Persian cat

This output indicates the model classifies this image as Shih-Tzu.

Test Image

Python API

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