#quantization.hbdk4.export

#horizon_plugin_pytorch.quantization.hbdk4.export(model: Module, example_inputs: Any, *, name: str = 'forward', input_names: Any | None = None, output_names: Any | None = None, input_descs: Any | None = None, output_descs: Any | None = None)

Export nn.Module to hbir model.

• Parameters:
  • model – Input model.
  • example_inputs – Example input for tracing.
  • name – The name of func in exported module. Users can get the func by getattr(hbir_module, name).
  • input_names – Set hbir inputs with given names, should have the same structure with example_inputs.
  • output_names – Set hbir outputs with given names, should have the same structure with model output.
  • input_descs – Set hbir inputs with given descriptions, should have the same structure with example_inputs.
  • output_descs – Set hbir outputs with given descriptions, should have the same structure with model output.
• Returns: Hbir model wrapped with Module.