Illustrated C/C++ source sheets, symbol index, API relationship graph, compiler console and debug trace

LIVE AI / FLEXIBLE SENSING / FLIGHT CONTEXT

Sensoraia API

Live AI and sensing, connected to the flight.
See, listen, inspect and return supported results while airborne.

Loading...
Searching...
No Matches
dipla::Network::State::ConditioningCache Struct Reference

Own the paired encoder and cached denoiser plus their bound tensors. More...

Collaboration diagram for dipla::Network::State::ConditioningCache:

Public Member Functions

 ConditioningCache (const std::string &directory, const std::string &source, const onnx_tensor *inputs, const onnx_tensor *outputs, const onnx_session_options &options)
 Validate the split model contract and open both runtime sessions.
 ~ConditioningCache ()
 Release sessions before their borrowed tensor storage is destroyed.

Data Fields

onnx_session encoder {}
onnx_session denoiser {}
inference_model encoder_model {}
inference_model denoiser_model {}
std::array< std::vector< float >, ONNX_TENSOR_LIMIT > values

Detailed Description

Own the paired encoder and cached denoiser plus their bound tensors.

Definition at line 199 of file dipla_planner.cpp.

Constructor & Destructor Documentation

◆ ConditioningCache()

dipla::Network::State::ConditioningCache::ConditioningCache ( const std::string & directory,
const std::string & source,
const onnx_tensor * inputs,
const onnx_tensor * outputs,
const onnx_session_options & options )
inline

Validate the split model contract and open both runtime sessions.

Parameters
directoryDirectory containing split graphs and their descriptors.
sourceSource graph path used to validate the cache identity.
inputsCanonical model inputs against which the split bindings are checked.
outputsCanonical model outputs against which the split bindings are checked.
optionsRuntime options shared by both sessions.
Exceptions
std::runtime_errorOn identity, binding or runtime initialization failure.

Check that the artifacts belong together before binding shared buffers. Close the encoder explicitly if the second session cannot open.

Definition at line 213 of file dipla_planner.cpp.

◆ ~ConditioningCache()

dipla::Network::State::ConditioningCache::~ConditioningCache ( )
inline

Release sessions before their borrowed tensor storage is destroyed.

Definition at line 303 of file dipla_planner.cpp.

Field Documentation

◆ denoiser

onnx_session dipla::Network::State::ConditioningCache::denoiser {}

Definition at line 200 of file dipla_planner.cpp.

◆ denoiser_model

inference_model dipla::Network::State::ConditioningCache::denoiser_model {}

Definition at line 201 of file dipla_planner.cpp.

◆ encoder

onnx_session dipla::Network::State::ConditioningCache::encoder {}

Definition at line 200 of file dipla_planner.cpp.

◆ encoder_model

inference_model dipla::Network::State::ConditioningCache::encoder_model {}

Definition at line 201 of file dipla_planner.cpp.

◆ values

std::array<std::vector<float>, ONNX_TENSOR_LIMIT> dipla::Network::State::ConditioningCache::values

Definition at line 202 of file dipla_planner.cpp.


The documentation for this struct was generated from the following file: