quark.onnx.utils.model_utils

Contents

`quark.onnx.utils.model_utils`#

Utility functions.

Module Contents#

Functions#

`get_tensor_value`(→ numpy.ndarray[Any, ...)	Convert TensorProto to numpy array.
`generate_initializer`(→ onnx.TensorProto)	Generate initializers from numpy array.
`save_model`(→ None)	Save onnx model to disk.

quark.onnx.utils.model_utils.get_tensor_value(initializer: onnx.TensorProto) → numpy.ndarray[Any, numpy.dtype[numpy.float32]]#: Convert TensorProto to numpy array.

quark.onnx.utils.model_utils.generate_initializer(tensor_array: numpy.ndarray[Any, numpy.dtype[numpy.float32]], dtype: Any, name: str) → onnx.TensorProto#: Generate initializers from numpy array.

quark.onnx.utils.model_utils.save_model(model: onnx.ModelProto, path: str, as_text: bool = False) → None#: Save onnx model to disk.