Development machine setup

Start with the AOT flow on the development machine.

Note

If you have not set up your development machine, follow the Module 1 development machine setup through creating and activating .cpu_aot_venv, then return here.

If you have not done so already, clone the repository and enter the directory:

    

        
        
git clone https://github.com/ArmDeveloperEcosystem/arm-courses-code-executorch.git ~/executorch_on_arm
cd ~/executorch_on_arm

Use Python 3.12.14, matching Modules 1 and 2. Activate .cpu_aot_venv and install the pinned Module 3 requirements:

    

        
        
cd ~/executorch_on_arm
source .cpu_aot_venv/bin/activate
python -m pip install -r module-3-executorch-on-android-semantic-segmentation/requirements.txt

The tested environment uses ExecuTorch 1.3.1, PyTorch 2.12.1, TorchVision 0.27.1, and torchao 0.17.0, which supplies the PT2E quantization APIs used later in this module.

Development machine setup

Nice work