Pipeline Builder [Experimental]
The Pipeline Builder is the Pythonic API for building ML inference pipelines on the Axelera Metis AIPU. Where YAML pipelines give you optimized GStreamer throughput for production deployment, the Pipeline Builder gives you composable Python operators for custom inter-stage logic, rapid prototyping, and workflows that go beyond standard detect-and-track patterns.
Experimental
Core operators (detection, classification, pose, segmentation, tracking) are stable. Cascade (op.foreach, op.croproi) and streaming APIs are still in development. Optimized fused kernels from the YAML pipeline path have not yet been ported — each release closes this gap.
Start here
- Quickstart — your first pipeline in under a minute
- Model Compilation — compile your model to
.axm(Ultralytics, ONNX, or PyTorch) - Pipeline Overview — full reference with examples for every task type
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 — BBox, DetectedObject, PoseObject, SegmentedObject, TrackedObject, Classification