stages Namespace

Definition

namespace simaai::neat::stages { ... }

Classes Index

struct	BoxDecodeOptions
	Options driving a standalone BoxDecode invocation. More...

Functions Index

TensorList	Tensors (const simaai::neat::Sample &sample)
	Extract the tensor list embedded in a single Sample. More...
TensorList	Preproc (const std::vector< cv::Mat > &inputs, const simaai::neat::Model &model)
	Run only the preprocessing stage on raw cv::Mat inputs. More...
TensorList	Preproc (const std::vector< cv::Mat > &inputs, const simaai::neat::Model &model, const std::vector< PreprocessRoi > &rois)
	Run preprocessing for a list of ROI windows over a batch of raw cv::Mat inputs. More...
TensorList	Infer (const TensorList &inputs, const simaai::neat::Model &model)
	Run only the inference stage on already-preprocessed tensors. More...
TensorList	MLA (const TensorList &inputs, const simaai::neat::Model &model)
	Run only the MLA leg on already-prepared tensors. More...
TensorList	Postprocess (const TensorList &inputs, const simaai::neat::Model &model)
	Run only the model's postprocessing stage on inference outputs. More...
Sample	Preproc (const Sample &inputs, const simaai::neat::Model &model)
	Sample-list overload of the preprocessing stage. More...
Sample	Infer (const Sample &inputs, const simaai::neat::Model &model)
	Sample-list overload of the inference stage. More...
Sample	MLA (const Sample &inputs, const simaai::neat::Model &model)
	Sample-list overload of the MLA stage. More...
Sample	Postprocess (const Sample &inputs, const simaai::neat::Model &model)
	Sample-list overload of the postprocessing stage. More...
Sample	BoxDecode (const Sample &inputs, const simaai::neat::Model &model, const BoxDecodeOptions &opt)
	Run the BoxDecode stage on inference outputs. More...
BoxDecodeResultList	BoxDecodeResults (const Sample &inputs, const simaai::neat::Model &model, const BoxDecodeOptions &opt)
	Run BoxDecode and parse each output into typed bounding boxes. More...
FeaturePointTensorList	SuperPointResults (const Sample &inputs, const simaai::neat::Model &model, const BoxDecodeOptions &opt)
	Run SuperPoint BoxDecode and parse every output as feature-point tensors. More...

Functions

BoxDecode()

Sample simaai::neat::stages::BoxDecode (const Sample & inputs, const simaai::neat::Model & model, const BoxDecodeOptions & opt)

Run the BoxDecode stage on inference outputs.

Parameters

inputs	Inference output samples to decode.
model	Model providing anchors/strides/class metadata.
opt	Decode-family selection and filtering thresholds.

Returns

Sample list whose payloads carry decoded detections.

Definition at line 78 of file StageRun.h.

BoxDecodeResults()

BoxDecodeResultList simaai::neat::stages::BoxDecodeResults (const Sample & inputs, const simaai::neat::Model & model, const BoxDecodeOptions & opt)

Run BoxDecode and parse each output into typed bounding boxes.

This is the structured-result companion to BoxDecode(...). It preserves the list-only public API rule: pass Sample{sample} for a single inference output, and read results.front() when only one result is expected.

Definition at line 88 of file StageRun.h.

Infer()

TensorList simaai::neat::stages::Infer (const TensorList & inputs, const simaai::neat::Model & model)

Run only the inference stage on already-preprocessed tensors.

Definition at line 57 of file StageRun.h.

Infer()

Sample simaai::neat::stages::Infer (const Sample & inputs, const simaai::neat::Model & model)

Sample-list overload of the inference stage.

Definition at line 65 of file StageRun.h.

MLA()

TensorList simaai::neat::stages::MLA (const TensorList & inputs, const simaai::neat::Model & model)

Run only the MLA leg on already-prepared tensors.

Definition at line 59 of file StageRun.h.

MLA()

Sample simaai::neat::stages::MLA (const Sample & inputs, const simaai::neat::Model & model)

Sample-list overload of the MLA stage.

Definition at line 67 of file StageRun.h.

Postprocess()

TensorList simaai::neat::stages::Postprocess (const TensorList & inputs, const simaai::neat::Model & model)

Run only the model's postprocessing stage on inference outputs.

Definition at line 61 of file StageRun.h.

Postprocess()

Sample simaai::neat::stages::Postprocess (const Sample & inputs, const simaai::neat::Model & model)

Sample-list overload of the postprocessing stage.

Definition at line 69 of file StageRun.h.

Preproc()

TensorList simaai::neat::stages::Preproc (const std::vector< cv::Mat > & inputs, const simaai::neat::Model & model)

Run only the preprocessing stage on raw cv::Mat inputs.

Definition at line 52 of file StageRun.h.

Preproc()

TensorList simaai::neat::stages::Preproc (const std::vector< cv::Mat > & inputs, const simaai::neat::Model & model, const std::vector< PreprocessRoi > & rois)

Run preprocessing for a list of ROI windows over a batch of raw cv::Mat inputs.

Definition at line 54 of file StageRun.h.

Preproc()

Sample simaai::neat::stages::Preproc (const Sample & inputs, const simaai::neat::Model & model)

Sample-list overload of the preprocessing stage.

Definition at line 63 of file StageRun.h.

SuperPointResults()

FeaturePointTensorList simaai::neat::stages::SuperPointResults (const Sample & inputs, const simaai::neat::Model & model, const BoxDecodeOptions & opt)

Run SuperPoint BoxDecode and parse every output as feature-point tensors.

Definition at line 92 of file StageRun.h.

Tensors()

TensorList simaai::neat::stages::Tensors (const simaai::neat::Sample & sample)

Extract the tensor list embedded in a single Sample.

Definition at line 50 of file StageRun.h.

---

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

• StageRun.h

---

Generated via doxygen2docusaurus 2.0.0 by Doxygen 1.9.8.