![]() ![]() Parametersįrozen_file ( str) – The path to the frozen TensorFlow graph to convert. from_tensorflow_frozen_model ( frozen_file, output_nodes =, preprocessor = None, ** kwargs ) Ĭonverts a TensorFlow frozen graph to a UFF model. Tensorflow Frozen Protobuf Model to UFF uff. Serialized UFF MetaGraph (str), graph inputs (list(tensorflow.NodeDef)), graph outputs (list(tensorflow.NodeDef)) Return_graph_info ( bool) – If set to True, this function returns the graph input and output nodes in addition to the serialized UFF graph. Errors may still be printed.ĭebug_mode ( bool) – If set to True, the converter prints verbose debug messages. Quiet ( bool) – If set to True, suppresses informational messages. Must be used in conjunction with output_filename. Text ( bool) – If set to True, the converter will also write out a human readable UFF file. Write_preprocessed ( bool) – If set to True, the converter will write out the preprocessed graph as well as a TensorBoard visualization. This script should define a preprocess function which accepts a graphsurgeon DynamicGraph and modifies it in place. Preprocessor ( str) – The path to a preprocessing script that will be executed before the converter. Output_filename ( str) – The UFF file to write. If not provided, graphsurgeon is used to automatically deduce output nodes. ![]() Output_nodes ( list ( str )) – The names of the outputs of the graph. ![]() ![]() Graphdef ( tensorflow.GraphDef) – The TensorFlow graph to convert. from_tensorflow ( graphdef, output_nodes =, preprocessor = None, ** kwargs ) Ĭonverts a TensorFlow GraphDef to a UFF model. ![]()
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |