ShuffleNetV2 for the ncnn framework
Papers
https://arxiv.org/pdf/1807.11164.pdf
Training set: ImageNet 2012
Size: 224x224
Prediction time: 22 mSec (RPi 4)
Special made for a bare Raspberry Pi see: https://qengineering.eu/opencv-c-examples-on-raspberry-pi.html
To extract and run the network in Code::Blocks
$ mkdir MyDir
$ cd MyDir
$ wget https://github.com/Qengineering/ShuffleNetV2-ncnn/archive/master.zip
$ unzip -j master.zip
Remove master.zip and README.md as they are no longer needed.
$ rm master.zip
$ rm README.md
Your MyDir folder must now look like this:
cat.jpg
vulture.jpg
shufflenet.bin
shufflenet.param
ShuffleNet.cpb
shufflenetv2.cpp
Run ShuffleNet.cpb with Code::Blocks. Remember, you also need a working OpenCV 4 on your Raspberry.