Beit Example

This document describes how to use the QAI AppBuilder Python API to run inference with the Beit object recognition model on Qualcomm® Hexagon™ Processor (NPU).

Supported Devices

Device	SoC
Fogwise® AIRbox Q900	QCS9075

Install QAI AppBuilder

tip

1. Please install QAI AppBuilder according to QAI AppBuilder Installation Guide.

2. Please configure ADSP environment variables according to Create ADSP Environment Variables.

Run the Example

Install Dependencies

Device

pip3 install requests tqdm qai-hub py3_wget opencv-python torch torchvision

Run the Script

• Navigate to the example directory

  QCS9075

  Device

  cd ai-engine-direct-helper/samples/python

• Prepare input image. The following image is used as an example:

  

  input image

• Run inference

  Device

  python3 beit/beit.py

  $ python3 beit/beit.py
       0.0ms [WARNING]  <W> Initializing HtpProvider
  
  /prj/qct/webtech_scratch20/mlg_user_admin/qaisw_source_repo/rel/qairt-2.37.1/point_release/SNPE_SRC/avante-tools/prebuilt/dsp/hexagon-sdk-5.5.5/ipc/fastrpc/rpcmem/src/rpcmem_android.c:38:dummy call to rpcmem_init, rpcmem APIs will be used from libxdsprpc
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
     179.0ms [WARNING] Time: Read model file to memory. 60.05
  
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
     284.7ms [WARNING] Time: contextCreateFromBinary. 105.62
  
     284.8ms [WARNING] Time: UnmapViewOfFile. 0.00
  
     288.1ms [WARNING] Time: model_initialize beit 288.01
  
     365.3ms [WARNING] Time: model_inference beit 17.72
  
  Top 5 predictions for image:
  
  "Samoyed", 0.6322221756
  "Pomeranian", 0.1098636836
  "Keeshond", 0.0410530604
  "Japanese Chin", 0.0093044275
  "Chow Chow", 0.0058453484
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
       0.0ms [WARNING]  <W> This META does not have Alloc2 Support
  
  /prj/qct/webtech_scratch20/mlg_user_admin/qaisw_source_repo/rel/qairt-2.37.1/point_release/SNPE_SRC/avante-tools/prebuilt/dsp/hexagon-sdk-5.5.5/ipc/fastrpc/rpcmem/src/rpcmem_android.c:42:dummy call to rpcmem_deinit, rpcmem APIs will be used from libxdsprpc
     483.8ms [WARNING] Time: model_destroy beit 113.14

  The output shows that Samoyed has the highest confidence score, which matches the content of the input image.