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.tf.util Namespace Reference

Functions

def load_graph (path)
 
def find_nodes_by_ops (graphdef, ops)
 
def map_node_outputs (graphdef)
 
def get_tensor_metadata (tensors)
 
def get_input_metadata (graph)
 
def get_output_metadata (graph, layerwise=False)
 
def get_graph_output_names (graph)
 
def str_from_graph (graph, mode)
 

Function Documentation

◆ load_graph()

def polygraphy.backend.tf.util.load_graph (   path)
Loads a TensorFlow frozen model.

Args:
    path (Union[str, tf.Graph, tf.GraphDef]):
            A path to the frozen model, or a frozen TensorFlow graph or graphdef.

Returns:
    tf.Graph: The TensorFlow graph

◆ find_nodes_by_ops()

def polygraphy.backend.tf.util.find_nodes_by_ops (   graphdef,
  ops 
)
Here is the caller graph for this function:

◆ map_node_outputs()

def polygraphy.backend.tf.util.map_node_outputs (   graphdef)
Here is the caller graph for this function:

◆ get_tensor_metadata()

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

◆ get_input_metadata()

def polygraphy.backend.tf.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.tf.util.get_output_metadata (   graph,
  layerwise = False 
)
Here is the call graph for this function:
Here is the caller graph for this function:

◆ get_graph_output_names()

def polygraphy.backend.tf.util.get_graph_output_names (   graph)
Here is the call graph for this function:

◆ str_from_graph()

def polygraphy.backend.tf.util.str_from_graph (   graph,
  mode 
)
Here is the call graph for this function: