Stay organized with collections
Save and categorize content based on your preferences.
tensorflow::tensorrt
Summary
Functions
|
ConvertAndBuild(const GraphDef & frozen_graph_def, const std::vector< string > & input_names, const std::vector< string > & output_names, const std::vector< std::vector< tensorflow::Tensor >> & inputs, const TfTrtConversionParams & conv_params)
|
StatusOr< GraphDef >
Converts the graph with TF-TRT.
|
ConvertAndBuild(SavedModelBundle *bundle, const std::string & signature_key, const std::vector< std::vector< tensorflow::Tensor >> & inputs, const TfTrtConversionParams & conversion_params)
|
StatusOr< GraphDef >
|
Functions
ConvertAndBuild
StatusOr< GraphDef > ConvertAndBuild(
const GraphDef & frozen_graph_def,
const std::vector< string > & input_names,
const std::vector< string > & output_names,
const std::vector< std::vector< tensorflow::Tensor >> & inputs,
const TfTrtConversionParams & conv_params
)
Converts the graph with TF-TRT.
Performs TF-TRT conversion and returns the converted GraphDef. If inputs is not empty and convert_to_static_engine is requested, we also build the engines and convert the engines to static engines.
Arguments:
- frozen_graph_def input graph, it is assumed to be frozen
- input_names names of the input tensors
- output_names names of the output tensors
- inputs tensors that we will use as input while building the TRT engines
- conv_params parameters for the TF-TRT conversion
Returns the converted graph_def.
ConvertAndBuild
StatusOr< GraphDef > ConvertAndBuild(
SavedModelBundle *bundle,
const std::string & signature_key,
const std::vector< std::vector< tensorflow::Tensor >> & inputs,
const TfTrtConversionParams & conversion_params
)
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.
Last updated 2022-09-07 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2022-09-07 UTC."],[],[],null,["# tensorflow::tensorrt Namespace\n\ntensorflow::tensorrt\n====================\n\nSummary\n-------\n\n| ### Functions ||\n|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------|\n| [ConvertAndBuild](#namespacetensorflow_1_1tensorrt_1a55199c84554c7fb2e748893246e9810a)`(const GraphDef & frozen_graph_def, const std::vector\u003c string \u003e & input_names, const std::vector\u003c string \u003e & output_names, const std::vector\u003c std::vector\u003c `[tensorflow::Tensor](/versions/r2.10/api_docs/cc/class/tensorflow/tensor#classtensorflow_1_1_tensor)` \u003e\u003e & inputs, const TfTrtConversionParams & conv_params)` | `StatusOr\u003c GraphDef \u003e` Converts the graph with TF-TRT. |\n| [ConvertAndBuild](#namespacetensorflow_1_1tensorrt_1a59ab051eabcf87e6f96e401fd72f0cf1)`(SavedModelBundle *bundle, const std::string & signature_key, const std::vector\u003c std::vector\u003c `[tensorflow::Tensor](/versions/r2.10/api_docs/cc/class/tensorflow/tensor#classtensorflow_1_1_tensor)` \u003e\u003e & inputs, const TfTrtConversionParams & conversion_params)` | `StatusOr\u003c GraphDef \u003e` |\n\n| ### Structs ||\n|--------------------------------------------------------------------------------------------------------------------------------|---|\n| [tensorflow::tensorrt::TfTrtConversionParams](/versions/r2.10/api_docs/cc/struct/tensorflow/tensorrt/tf-trt-conversion-params) | |\n\nFunctions\n---------\n\n### ConvertAndBuild\n\n```gdscript\nStatusOr\u003c GraphDef \u003e ConvertAndBuild(\n const GraphDef & frozen_graph_def,\n const std::vector\u003c string \u003e & input_names,\n const std::vector\u003c string \u003e & output_names,\n const std::vector\u003c std::vector\u003c tensorflow::Tensor \u003e\u003e & inputs,\n const TfTrtConversionParams & conv_params\n)\n``` \nConverts the graph with TF-TRT.\n\nPerforms TF-TRT conversion and returns the converted GraphDef. If inputs is not empty and convert_to_static_engine is requested, we also build the engines and convert the engines to static engines.\n\nArguments:\n\n- frozen_graph_def input graph, it is assumed to be frozen\n- input_names names of the input tensors\n- output_names names of the output tensors\n- inputs tensors that we will use as input while building the TRT engines\n- conv_params parameters for the TF-TRT conversion\n\n\u003cbr /\u003e\n\nReturns the converted graph_def. \n\n### ConvertAndBuild\n\n```gdscript\nStatusOr\u003c GraphDef \u003e ConvertAndBuild(\n SavedModelBundle *bundle,\n const std::string & signature_key,\n const std::vector\u003c std::vector\u003c tensorflow::Tensor \u003e\u003e & inputs,\n const TfTrtConversionParams & conversion_params\n)\n```"]]