Machine Learning Messages

The ML message types (TensorData, Predictions, Classification, FeatureVector, ModelInfo, ModelFormat, InferenceMetrics, TrainingMetrics, MlTrajectoryPoint, DeploymentConfig, ChatMessage, LLMRequest, LLMResponse) have been removed from horus_library.

For ML inference pipelines, use the zero-copy Tensor and TensorPool APIs to transport model inputs and outputs between nodes. For structured inference results, use the Pod detection types:

Detection / Detection3D -- Object detection results with bounding boxes
BoundingBox2D / BoundingBox3D -- Bounding box types
SegmentationMask -- Semantic, instance, and panoptic segmentation masks
GenericMessage -- Flexible cross-language messaging for custom ML outputs

SegmentationMask

Pod segmentation mask header (64 bytes). The actual pixel data follows the header in shared memory -- each pixel is a u8 class/instance ID.

use horus::prelude::*;

// Create semantic segmentation mask header
let mask = SegmentationMask::semantic(640, 480, 21)
    .with_frame_id("camera_front")
    .with_timestamp(1234567890);

println!("Mask: {}x{}, {} classes", mask.width, mask.height, mask.num_classes);
println!("Data size: {} bytes", mask.data_size());

// Create instance segmentation mask
let instance_mask = SegmentationMask::instance(640, 480);

// Create panoptic segmentation mask
let panoptic_mask = SegmentationMask::panoptic(640, 480, 80);

Fields (64 bytes, #[repr(C)]):

Field	Type	Description
`width`	`u32`	Mask width in pixels
`height`	`u32`	Mask height in pixels
`num_classes`	`u32`	Number of semantic classes
`mask_type`	`u32`	0=semantic, 1=instance, 2=panoptic
`timestamp_ns`	`u64`	Nanoseconds since epoch
`seq`	`u64`	Sequence number
`frame_id`	`[u8; 32]`	Camera frame identifier

Methods:

Method	Returns	Description
`semantic(w, h, num_classes)`	`SegmentationMask`	Create semantic mask header
`instance(w, h)`	`SegmentationMask`	Create instance mask header
`panoptic(w, h, num_classes)`	`SegmentationMask`	Create panoptic mask header
`with_frame_id(id)`	`Self`	Set frame ID (builder)
`with_timestamp(ts)`	`Self`	Set timestamp (builder)
`frame_id()`	`&str`	Get frame ID as string
`data_size()`	`usize`	Mask data size in bytes (w * h)

Machine Learning Messages

SegmentationMask

See Also