TensorRT  7.2.1.6
NVIDIA TensorRT
Looking for a C++ dev who knows TensorRT?
I'm looking for work. Hire me!
All Classes Namespaces Functions Variables Typedefs Enumerations Enumerator Friends Pages
onnx_graphsurgeon.exporters.onnx_exporter Namespace Reference

Classes

class  OnnxExporter
 

Functions

int dtype_to_onnx (np.dtype dtype)
 
"onnx.ModelProto" export_onnx (Graph graph, do_type_check=True, **kwargs)
 

Function Documentation

◆ dtype_to_onnx()

int onnx_graphsurgeon.exporters.onnx_exporter.dtype_to_onnx ( np.dtype  dtype)
Here is the caller graph for this function:

◆ export_onnx()

"onnx.ModelProto" onnx_graphsurgeon.exporters.onnx_exporter.export_onnx ( Graph  graph,
  do_type_check = True,
**  kwargs 
)
Exports an onnx-graphsurgeon Graph to an ONNX model.

Args:
    graph (Graph): The graph to export

    do_type_check (bool): Whether to check that input and output tensors have data types defined, and fail if not.
    kwargs: Additional arguments to onnx.helper.make_model

Returns:
    onnx.ModelProto: A corresponding ONNX model.