Runtime-owned ONNX session and reusable input/output storage. More...

Data Structures | |
| struct | ConditioningCache |
| Own the paired encoder and cached denoiser plus their bound tensors. More... | |
Public Member Functions | |
| State (const std::string &model, const std::string &metadata, const NetworkOptions &policy) | |
| Validate the export contract before binding a reusable ONNX session. | |
| ~State () | |
| Close the session while every borrowed member buffer is still alive. | |
Data Fields | |
| std::unique_ptr< ConditioningCache > | conditioning_cache |
| onnx_session | session {} |
| unsigned | timeout_ms = 0 |
| std::array< float, DIPLA_COORDINATE_COUNT *points > | candidate {} |
| std::array< float, DIPLA_COORDINATE_COUNT *points > | predicted {} |
| std::array< float, DIPLA_MAP_CHANNEL_COUNT *cells > | maps {} |
| std::array< float, 3 > | position {} |
| std::array< float, 1 > | total {} |
| std::array< int64_t, 1 > | timestep {} |
| std::array< double, DIPLA_DIFFUSION_STEPS > | alpha {} |
| Normalization | mean_normalization |
| Normalization | variance_normalization |
| Normalization | total_normalization |
Detailed Description
Runtime-owned ONNX session and reusable input/output storage.
Bind once and reuse across all twenty denoising calls and later plans. This avoids rebuilding application-side tensors in the hot loop; it does not promise allocation-free execution inside ONNX Runtime.
- Invariant
- The session borrows member buffers whose addresses remain stable until the session is closed by the destructor.
- Warning
- A State is single-owner mutable workspace, not a concurrent sampler.
Definition at line 197 of file dipla_planner.cpp.
Constructor & Destructor Documentation
◆ State()
|
inline |
Validate the export contract before binding a reusable ONNX session.
Reject mismatched geometry, schedules, and tensors at startup, when there is still a useful file error to report, rather than after a plausible-looking but mis-scaled route reaches the application.
- Parameters
-
[in] model ONNX graph path. [in] metadata Deployment JSON describing training-time preprocessing. [in] policy Optional integrity descriptor, thread count, and deadline policy.
- Precondition
- initialize_runtime() has successfully selected a compatible runtime.
- Exceptions
-
std::exception If reading, allocation, validation, or session creation fails.
- Note
- Parser views are temporary. Copy only checked numeric values into members; nothing in the session may borrow the constructor's JSON arena.
- Todo
- Centralize the supported world and schedule contract. Changing these checks alone is not model support: update the public sizes, tensor shapes, grid indexing, sampler loop, and coordinate transforms together, then rerun the reference cases. Until then, reject drift.
- Todo
- Derive this shape from the same supported-grid contract as maps and Belief; do not independently make only the binding dynamic.
Definition at line 343 of file dipla_planner.cpp.
◆ ~State()
|
inline |
Close the session while every borrowed member buffer is still alive.
Destructor bodies run before member destruction. Explicit closure here preserves that order even though session is declared before its buffers.
Definition at line 455 of file dipla_planner.cpp.
Field Documentation
◆ alpha
| std::array<double, DIPLA_DIFFUSION_STEPS> dipla::Network::State::alpha {} |
Trained cumulative-alpha schedule used by the deterministic DDIM update.
Definition at line 326 of file dipla_planner.cpp.
◆ candidate
| std::array<float, DIPLA_COORDINATE_COUNT * points> dipla::Network::State::candidate {} |
Float32 graph input: eight X values, then eight Y, then eight Z, not interleaved XYZ.
Definition at line 314 of file dipla_planner.cpp.
◆ conditioning_cache
| std::unique_ptr<ConditioningCache> dipla::Network::State::conditioning_cache |
Definition at line 308 of file dipla_planner.cpp.
◆ maps
| std::array<float, DIPLA_MAP_CHANNEL_COUNT * cells> dipla::Network::State::maps {} |
NCHW map input: mean, variance, marker; each channel uses row * 51 + column.
Definition at line 318 of file dipla_planner.cpp.
◆ mean_normalization
| Normalization dipla::Network::State::mean_normalization |
Center/scale pairs for mean, variance, and log1p(total variance), in that order.
Definition at line 328 of file dipla_planner.cpp.
◆ position
| std::array<float, 3> dipla::Network::State::position {} |
Normalized current pose tensor, ordered east/north/altitude.
Definition at line 320 of file dipla_planner.cpp.
◆ predicted
| std::array<float, DIPLA_COORDINATE_COUNT * points> dipla::Network::State::predicted {} |
Noise prediction written by the ONNX graph for each reverse step.
Definition at line 316 of file dipla_planner.cpp.
◆ session
| onnx_session dipla::Network::State::session {} |
Shared session borrowing this state's fixed buffers.
Definition at line 310 of file dipla_planner.cpp.
◆ timeout_ms
| unsigned dipla::Network::State::timeout_ms = 0 |
Whole-plan cooperative deadline; zero disables the local timer.
Definition at line 312 of file dipla_planner.cpp.
◆ timestep
| std::array<int64_t, 1> dipla::Network::State::timestep {} |
Current reverse-diffusion step.
Definition at line 324 of file dipla_planner.cpp.
◆ total
| std::array<float, 1> dipla::Network::State::total {} |
Normalized scalar total-variance tensor.
Definition at line 322 of file dipla_planner.cpp.
◆ total_normalization
| Normalization dipla::Network::State::total_normalization |
Definition at line 328 of file dipla_planner.cpp.
◆ variance_normalization
| Normalization dipla::Network::State::variance_normalization |
Definition at line 328 of file dipla_planner.cpp.
The documentation for this struct was generated from the following file:
- modules/dipla_cam/dipla_planner.cpp