Skip to main content

Pipeline Builder API

Preview

Core operators (detection, classification, pose, segmentation, tracking) are stable. Cascade (op.foreach, op.croproi) and streaming APIs are still in development.

The Pipeline Builder API is the Pythonic interface for building ML inference pipelines on the Axelera Metis AIPU. It replaces YAML-based pipeline configuration with composable Python operators.

Getting started

Operator Reference

  • Transforms — Image preprocessing (resize, letterbox, normalize, color convert)
  • Postprocess — Decode raw model output, NMS, coordinate transform, filter
  • Results — Convert arrays to typed objects (DetectedObject, PoseObject, etc.)
  • Inference — Model loading (op.load, op.onnx_model)
  • Tracker — Multi-object tracking (ByteTrack, OC-SORT, SORT, TrackTrack)
  • Combinators — Pipeline composition (op.seq, op.par, op.foreach)

Type Reference

  • Types — Data types: BBox, DetectedObject, PoseObject, SegmentedObject, TrackedObject, Classification