This is a simple C++ demo application that uses the ExecuTorch library for MobileNetV2 model inference.

0. Export the model. See mv2/python/README.md

1. The ExecuTorch repository is already configured as a git submodule at ~/executorch-examples/mv2/cpp/executorch/. To initialize it:

    cd ~/executorch-examples/
    git submodule sync
    git submodule update --init --recursive

2. Install dev requirements for ExecuTorch

   cd ~/executorch-examples/mv2/cpp/executorch
   pip install -r requirements-dev.txt

3. Build the project:

   cd ~/executorch-examples/mv2/cpp
   chmod +x build.sh
   ./build.sh

4. Run the demo application:

   ./build/bin/executorch_mv2_demo_app

• CMake 3.18 or higher
• C++17 compatible compiler
• ExecuTorch library (release/0.6)

• Make sure you have the correct model file (.pte) compatible with ExecuTorch.
• This demo currently initializes the input tensor with random data. In a real application, you would replace this with actual input data.