Snapdragon Neural Processing Engine (SNPE) and Tiny Yolo on Android App

Question

for my final university exam I am trying to use SNPE with Tiny YOLO for real time object detection in an Android App. I succesfully converted model to DLC format, but i can't understand how to prepare input tensors and how to process output tensors. Can sameone help me? Thanks.

Answer 1

Steps to build SNPE neural network and get the output FloatTensor:

1. Create an asset folder in Android/app directory and keep the model file(.dlc) in the asset folder.

   // assetFileName is the file name of .dlc
   InputStream assetInputStream = application.getAssets().open(assetFileName); // Create and build the neural network
   NeuralNetwork network = new SNPE.NeuralNetworkBuilder(application)
           .setDebugEnabled(false)
   //outputLayerNames can be got while converted model to DLC format
           .setOutputLayers(outputLayerNames)
           .setModel(assetInputStream, assetInputStream.available())
           .setPerformanceProfile(NeuralNetwork.PerformanceProfile.DEFAULT)
           .setRuntimeOrder(selectedRuntime) // Runtime.DSP, Runtime.GPU_FLOAT16, Runtime.GPU, Runtime.CPU
           .setCpuFallbackEnabled(needsCpuFallback)
           .build();
   // Close input
   assetInputStream.close();
   

2. Create an Input Tensor

3. Propagate Input Tensors Through the Network
4. Process the Neural Network Output

Please follow the link below and find sections mentioned in steps 2,3 and 4 for preparing input Tensors and processing output tensors https://developer.qualcomm.com/docs/snpe/android_tutorial.html