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
polygraphy.backend.onnx.util Namespace Reference

Functions

def check_model (model)
 
def infer_shapes (model)
 
def all_tensor_names (model)
 
def check_outputs_not_found (not_found, all_outputs)
 
def mark_outputs (model, outputs)
 
def mark_layerwise (model)
 
def unmark_outputs (model, outputs)
 
def get_shape (tensor)
 
def get_dtype (tensor)
 
def get_values (tensor)
 
def get_tensor_metadata (tensors)
 
def get_input_metadata (graph)
 
def get_output_metadata (graph)
 
def str_from_onnx (model, mode="full")
 
def str_from_onnx_graph (graph, mode, tensors, indent_level=0)
 

Function Documentation

◆ check_model()

def polygraphy.backend.onnx.util.check_model (   model)

◆ infer_shapes()

def polygraphy.backend.onnx.util.infer_shapes (   model)

◆ all_tensor_names()

def polygraphy.backend.onnx.util.all_tensor_names (   model)
Here is the caller graph for this function:

◆ check_outputs_not_found()

def polygraphy.backend.onnx.util.check_outputs_not_found (   not_found,
  all_outputs 
)
Here is the caller graph for this function:

◆ mark_outputs()

def polygraphy.backend.onnx.util.mark_outputs (   model,
  outputs 
)
Here is the call graph for this function:
Here is the caller graph for this function:

◆ mark_layerwise()

def polygraphy.backend.onnx.util.mark_layerwise (   model)
Here is the call graph for this function:

◆ unmark_outputs()

def polygraphy.backend.onnx.util.unmark_outputs (   model,
  outputs 
)
Here is the call graph for this function:

◆ get_shape()

def polygraphy.backend.onnx.util.get_shape (   tensor)
Here is the caller graph for this function:

◆ get_dtype()

def polygraphy.backend.onnx.util.get_dtype (   tensor)
Here is the caller graph for this function:

◆ get_values()

def polygraphy.backend.onnx.util.get_values (   tensor)
Here is the caller graph for this function:

◆ get_tensor_metadata()

def polygraphy.backend.onnx.util.get_tensor_metadata (   tensors)
Here is the call graph for this function:
Here is the caller graph for this function:

◆ get_input_metadata()

def polygraphy.backend.onnx.util.get_input_metadata (   graph)
Here is the call graph for this function:
Here is the caller graph for this function:

◆ get_output_metadata()

def polygraphy.backend.onnx.util.get_output_metadata (   graph)
Here is the call graph for this function:
Here is the caller graph for this function:

◆ str_from_onnx()

def polygraphy.backend.onnx.util.str_from_onnx (   model,
  mode = "full" 
)
Converts an ONNX Graph to a human-readable representation

Args:
    graph (onnx.GraphProto): The onnx graph.
    mode (str): Controls what is displayed. Choices: ["none", "basic", "attrs", "full"]

Returns:
    str
Here is the call graph for this function:

◆ str_from_onnx_graph()

def polygraphy.backend.onnx.util.str_from_onnx_graph (   graph,
  mode,
  tensors,
  indent_level = 0 
)
Here is the call graph for this function:
Here is the caller graph for this function: