qualia_core.postprocessing.QualiaCodeGen module

class qualia_core.postprocessing.QualiaCodeGen.QualiaCodeGen(quantize: str, long_width: int | None = None, outdir: str | None = None, metrics: list[str] | None = None)

Bases: Converter[Any]

deployers: ModuleType | None = <module 'qualia_core.deployment.qualia_codegen' from '/home/runner/work/qualia-core/qualia-core/src/qualia_core/deployment/qualia_codegen/__init__.py'>

Suggested deployers

convert_model_to_modelgraph(model: nn.Module | keras.Model) → ModelGraph | None

convert_modelgraph_to_c(modelgraph: ModelGraph, output_path: Path) → str | None

convert_metrics_to_cpp(metrics: list[str], output_path: Path) → str | None

convert(framework: LearningFramework[nn.Module | keras.Model], model: nn.Module | keras.Model, model_name: str, representative_dataset: numpy.typing.NDArray[Any]) → QualiaCodeGen | None

property h: str | None

property name: str | None

property directory: Path | None

process_mem_params(mem_params: int) → Callable[[LearningFramework[nn.Module | keras.Model], nn.Module | keras.Model], int]