setup-ml-framework
Supported Information
This version of the Qualcomm® Neural Processing SDK has been verified to work with the following versions of ML training frameworks:
Framework Version TensorFlow v2.10.1 TFLite v2.3.0 TFLite v1.13.1 ONNX v1.12.0
Download and install the corresponding frameworks on your host machine.
# Install tensorflow

pip install tensorflow==2.10.1
# Install tflite
pip install tflite==2.3.0
# Install PyTorch
pip install torch==1.13.1+cpu torchvision==0.14.1+cpu torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cpu
# Install Onnx
pip install onnx==1.12.0 onnxruntime==1.17.1 onnxsim==0.4.36
Note: This process also takes considerable time, please be patient.
Set Up SNPE SDK Environment
Import the environment setup script provided by the SNPE SDK to ensure all tools and libraries required for the workflow are in your $PATH. Once this is done, you are ready to begin conversion.
source ${SNPE_ROOT}/bin/envsetup.sh
