furiosa.quantizer.frontend.onnx.utils package
Submodules
furiosa.quantizer.frontend.onnx.utils.check_model module
- furiosa.quantizer.frontend.onnx.utils.check_model.check_model(model: onnx.onnx_ml_pb2.ModelProto, check_runnable: bool = True) None
Check if model’s well-defined and executable on onnxruntime
furiosa.quantizer.frontend.onnx.utils.inference_shape module
- class furiosa.quantizer.frontend.onnx.utils.inference_shape.InferenceShape(model: onnx.onnx_ml_pb2.ModelProto)
Bases:
object
Replace former InferenceShape with ONNX_Simplifier https://github.com/daquexian/onnx-simplifier
- inference_shape(input_shapes: Optional[Dict[str, List[int]]] = None) onnx.onnx_ml_pb2.ModelProto
furiosa.quantizer.frontend.onnx.utils.version_checker module
- class furiosa.quantizer.frontend.onnx.utils.version_checker.CheckVersion(*args, **kwds)
Bases:
furiosa.quantizer.interfaces.transformer.Transformer
[onnx.onnx_ml_pb2.ModelProto
]Convert an ONNX model to ONNX opset 12
- transform(model: onnx.onnx_ml_pb2.ModelProto) onnx.onnx_ml_pb2.ModelProto