目录

6.1.17 Index

优质
小牛编辑
128浏览
2023-12-01

TensorFlow's public C++ API includes only the API for executing graphs, as of version 0.5. To control the execution of a graph from C++:

  1. Build the computation graph using the Python API.
  2. Use tf.train.write_graph() to write the graph to a file.
  3. Load the graph using the C++ Session API. For example:

    // Reads a model graph definition from disk, and creates a session object you
    // can use to run it.
    Status LoadGraph(string graph_file_name, Session** session) {
     GraphDef graph_def;
     TF_RETURN_IF_ERROR(
         ReadBinaryProto(Env::Default(), graph_file_name, &graph_def));
     TF_RETURN_IF_ERROR(NewSession(SessionOptions(), session));
     TF_RETURN_IF_ERROR((*session)->Create(graph_def));
     return Status::OK();
    }
    
  4. Run the graph with a call to session->Run()

Classes

Structs

<!-- -->