Pipeline runtime

Session, PipelineRun, options, reports, errors. More...

Classes Index

struct	DebugOptions
	Tunables for debug-mode pipeline dumps. More...
struct	DebugOutput
	One captured pipeline output (single-shot dump result). More...
struct	DebugStream
	Streaming iterator over debug-mode pipeline outputs. More...
struct	Box
	One axis-aligned detection produced by BoxDecode. More...
struct	BoxDecodeResult
	Parsed BoxDecode output paired with its raw byte buffer. More...
struct	FormatSpec
	Thin wrapper around FormatTag with implicit string conversions. More...
struct	ProfilerKernelInvocation
	One kernel-invocation telemetry event. More...
struct	ProfilerMemcpySite
	Aggregate counters for one instrumented memcpy site. More...
struct	ProfilerKernelAggregate
	Aggregated timings for one (backend, kernel, stage, slot) tuple. More...
struct	ProfilerReport
	Snapshot bundle returned by LatencyProfiler::finalize(). More...
struct	LatencyProfilerOptions
	Construction options for LatencyProfiler. More...
class	LatencyProfiler
	Per-sample latency tracker; attach to a Run to capture timing telemetry. More...
struct	RunOptions
	Per-Run runtime options. More...
class	Run
	Live pipeline handle: push inputs in, pull outputs out. More...
class	RtspServerHandle
	Live handle for a Session running in RTSP server mode. More...
class	Session
	The assembly stage — turns a list of Nodes into a runnable, deterministic pipeline. More...
struct	BuiltState
	Opaque state carried by a built (not yet running) Session. More...
struct	GroupMeta
	Per-NodeGroup metadata captured during build. More...
struct	RtspServerOptions
	Options for Session::run_rtsp() — controls the RTSP server's mount point and ports. More...
struct	SessionOptions
	Per-Session construction options. More...
struct	OutputTensorOptions
	Options for Session::add_output_tensor() — the tensor-friendly output helper. More...
struct	Sample
	Typed payload returned by Run::pull() and consumed by Run::push(). More...
struct	BoxDecodeOptions
	Options driving a standalone BoxDecode invocation. More...

Enumerations Index

enum class	BoxDecodeType : std::int32_t { ... }
	Decode families accepted by the BoxDecode backend. More...
enum class	BoxDecodeTypeOption : std::int32_t { ... }
	Tensor packing/layout option within a decode family. More...
enum class	FormatTag { ... }
	Identifies a media or tensor payload format. More...
enum class	OverflowPolicy { ... }
	What push() does when the input queue is full. More...
enum class	RunPreset { ... }
	Convenience preset bundles for RunOptions. More...
enum class	OutputMemory { ... }
	How output Tensors relate to the underlying GStreamer buffers. More...
enum class	RunMode { ... }
	Timing mode a Run operates in. More...
enum class	SampleKind { ... }
	What kind of payload a Sample carries. More...
enum class	PullStatus { ... }
	Result status of Run::pull(). More...

Description

Session, PipelineRun, options, reports, errors.

Enumerations

BoxDecodeType

enum class simaai::neat::BoxDecodeType : std::int32_t

strong

Decode families accepted by the BoxDecode backend.

Enumeration values

Unspecified	Sentinel: no decode family selected (fails fast at runtime) (= 0)
Yolo	Generic YOLO family token (= 1)
YoloV5	YOLOv5 detection (= 2)
YoloV5Seg	YOLOv5 segmentation (= 3)
YoloV7	YOLOv7 detection (= 4)
YoloV7Seg	YOLOv7 segmentation (= 5)
YoloV8	YOLOv8 detection (= 6)
YoloV8Seg	YOLOv8 segmentation (= 7)
YoloV8Pose	YOLOv8 pose-estimation heads (= 8)
YoloV9	YOLOv9 detection (= 9)
YoloV9Seg	YOLOv9 segmentation (= 10)
YoloV10	YOLOv10 detection (= 11)
YoloV10Seg	YOLOv10 segmentation (= 12)
Detr	DETR-style transformer detection (= 13)
EffDet	EfficientDet detection (= 14)
RcnnStage1	Region-proposal stage of two-stage R-CNN models (= 15)
Centernet	CenterNet keypoint-style detection (= 16)
YoloV26	YOLO26 detection (raw l/t/r/b distance heads) (= 17)

Unspecified is an internal unset sentinel and must fail fast before runtime decode. Most YOLO-family variants share the same class-inference contract in genericboxdecode_v2:

• decoupled heads: repeated class-depth tensors, class depth > 4
• packed heads: depth = 3 * (num_classes + 5), consistent across heads YoloV26 uses decoupled 4-channel raw l/t/r/b bbox heads paired with class heads.

Definition at line 33 of file BoxDecodeType.h.

33enum class BoxDecodeType : std::int32_t {

34 // Internal sentinel; runtime decode requires a concrete value.

35 Unspecified = 0,

36 // YOLO-family (generic token).

37 Yolo = 1,

38 YoloV5 = 2,

39 YoloV5Seg = 3,

40 YoloV7 = 4,

41 YoloV7Seg = 5,

42 YoloV8 = 6,

43 YoloV8Seg = 7,

44 YoloV8Pose = 8,

45 YoloV9 = 9,

46 YoloV9Seg = 10,

47 YoloV10 = 11,

48 YoloV10Seg = 12,

49 Detr = 13,

50 EffDet = 14,

51 RcnnStage1 = 15,

52 Centernet = 16,

53 YoloV26 = 17,

54};

BoxDecodeTypeOption

enum class simaai::neat::BoxDecodeTypeOption : std::int32_t

strong

Tensor packing/layout option within a decode family.

Enumeration values

Auto	Backend infers the layout from tensor shapes (= 0)
PackedPerHead	Each head holds a single packed tensor (box+obj+cls) (= 1)
InterleavedByHead	Heads interleaved within tensors (= 2)
GroupedByRole	Tensors grouped by role (box, score, class) (= 3)
Split3Interleaved	Three split tensors, head-interleaved (= 4)
Split3Grouped	Three split tensors, grouped by role (= 5)
InterleavedByHeadProbability	Interleaved-by-head, class scores as probabilities (= 6)
InterleavedByHeadLogit	Interleaved-by-head, class scores as logits (= 7)
GroupedByRoleProbability	Grouped-by-role, class scores as probabilities (= 8)
GroupedByRoleLogit	Grouped-by-role, class scores as logits (= 9)

Some families admit multiple equivalent head layouts (packed vs interleaved, grouped by role, probability vs logit class scores). Auto lets the planner pick from observed tensor geometry; the explicit values force a particular decoding contract for ambiguous models.

Definition at line 66 of file BoxDecodeType.h.

66enum class BoxDecodeTypeOption : std::int32_t {

67 Auto = 0,

68 PackedPerHead = 1,

69 InterleavedByHead = 2,

70 GroupedByRole = 3,

71 Split3Interleaved = 4,

72 Split3Grouped = 5,

73 InterleavedByHeadProbability = 6,

74 InterleavedByHeadLogit = 7,

75 GroupedByRoleProbability = 8,

76 GroupedByRoleLogit = 9,

77};

FormatTag

enum class simaai::neat::FormatTag

strong

Identifies a media or tensor payload format.

Enumeration values

Auto	Unset / framework decides (= 0)
RGB	Packed RGB, 8 bits per channel
BGR	Packed BGR, 8 bits per channel (OpenCV default)
GRAY8	Single-plane 8-bit grayscale
NV12	YUV 4:2:0, Y plane + interleaved UV plane
I420	YUV 4:2:0, three planes (Y, U, V)
YUYV	YUV 4:2:2 packed (Y0 U Y1 V)
ENCODED	Generic encoded payload (codec from caps)
H264	H.264 access unit / NAL stream
ByteStream	Opaque byte stream; downstream interprets bytes by contract
MLA	MLA-tessellated tensor payload
BBOX	Decoded bounding-box byte stream
ARGMAX	Argmax/segmentation map
DETESSDEQUANT	Detessellated + dequantized tensor payload
FP32	IEEE-754 32-bit float tensor
INT8	Signed 8-bit integer tensor
UINT8	Unsigned 8-bit integer tensor
BF16	bfloat16 tensor
EVXX_FLOAT32	EV-side alias for FP32
EVXX_INT8	EV-side alias for INT8
EVXX_BFLOAT16	EV-side alias for BF16

Used in caps strings and option fields throughout the pipeline. Auto is the unset sentinel (let the framework pick or sniff). The EVXX_ variants are aliases preferred by the EV74 caps surface.

See Also

FormatSpec

Definition at line 36 of file FormatSpec.h.

36enum class FormatTag {

37 Auto = 0,

38 RGB,

39 BGR,

40 GRAY8,

41 NV12,

42 I420,

43 YUYV,

44 ENCODED,

45 H264,

46 ByteStream,

47 MLA,

48 BBOX,

49 ARGMAX,

50 DETESSDEQUANT,

51 FP32,

52 INT8,

53 UINT8,

54 BF16,

55 EVXX_FLOAT32,

56 EVXX_INT8,

57 EVXX_BFLOAT16,

58};

OutputMemory

enum class simaai::neat::OutputMemory

strong

How output Tensors relate to the underlying GStreamer buffers.

Enumeration values

Auto	(= 0)
ZeroCopy
Owned

Auto lets the framework pick based on platform and pipeline shape. ZeroCopy shares storage with GStreamer (faster but lifetime-coupled to the Run). Owned copies into a framework-owned buffer (safer, slightly slower).

Definition at line 88 of file Run.h.

88enum class OutputMemory {

89 Auto = 0,

90 ZeroCopy,

91 Owned,

92};

OverflowPolicy

enum class simaai::neat::OverflowPolicy

strong

What push() does when the input queue is full.

Enumeration values

Block	push() blocks until queue space frees up. Lossless. Use for batch processing (= 0)
KeepLatest	Drop the oldest queued frame to make room
DropIncoming	Drop the new frame; keep what's queued

The right choice depends on the input source — file batches want lossless, live cameras want freshness, network feeds with chokepoint pipelines want bounded memory.

Definition at line 59 of file Run.h.

59enum class OverflowPolicy {

60 Block = 0,

61 KeepLatest,

63 DropIncoming,

65};

PullStatus

enum class simaai::neat::PullStatus

strong

Result status of Run::pull().

Enumeration values

Ok	A sample is available in the output parameter
Timeout	The wait elapsed without a sample arriving
Closed	The pipeline has reached EOS; no more samples will come
Error	A runtime error occurred; check the optional PullError

Definition at line 349 of file SessionOptions.h.

349enum class PullStatus {

350 Ok,

351 Timeout,

352 Closed,

353 Error,

354};

RunMode

enum class simaai::neat::RunMode

strong

Timing mode a Run operates in.

Enumeration values

Async	Continuous pipeline; user pushes/pulls asynchronously
Sync	One frame in, one result out, synchronously

Async runs the pipeline continuously with internal worker threads; user code pushes and pulls at its own pace. Sync runs one frame at a time on the calling thread. Choose based on the input source: streaming sources → Async; one-shot/batch → Sync.

See Also

Run

Definition at line 192 of file SessionOptions.h.

192enum class RunMode {

193 Async,

194 Sync,

195};

RunPreset

enum class simaai::neat::RunPreset

strong

Convenience preset bundles for RunOptions.

Enumeration values

Realtime	Low-latency; small queues; KeepLatest overflow; metrics off
Balanced	Default; moderate queues; Block overflow; metrics off
Reliable	Lossless; deeper queues; Block overflow; metrics on

Each preset adjusts queue depth, overflow policy, and metrics flags to a profile that's known to work well for one workload class.

Definition at line 74 of file Run.h.

74enum class RunPreset {

75 Realtime,

76 Balanced,

77 Reliable,

78};

SampleKind

enum class simaai::neat::SampleKind

strong

What kind of payload a Sample carries.

Enumeration values

Tensor	Single tensor payload (the tensor field is set)
TensorSet	Multiple tensors at one logical output index (the tensors field is set)
Bundle	Recursive: payload is a vector of Samples (the fields field is set)
Unknown	Default/uninitialized

The framework's outputs come in three shapes depending on the model's output topology: a single Tensor, a flat list of Tensors (TensorSet), or a recursive Bundle of Samples (Bundle, used by multi-logical-output models).

See Also

Sample

Definition at line 338 of file SessionOptions.h.

338enum class SampleKind {

339 Tensor,

340 TensorSet,

341 Bundle,

342 Unknown,

343};

---

Generated via doxygen2docusaurus 2.0.0 by Doxygen 1.9.8.