What will you be able to do?

By the end of this module, you will be able to:

  • export MobileNetV2 to ExecuTorch and lower supported regions to XNNPACK

  • benchmark PyTorch eager and ExecuTorch with XNNPACK on a Raspberry Pi

  • create an INT8 MobileNetV2 .pte artifact with the XNNPACK post-training quantization flow

  • compare FP32 and INT8 artifact size, latency, and top-5 classification output

  • explain how model structure, delegation, quantization, and classification results affect deployment

Previous page Complete and continue