Skip to content

DL TCN Wave (f8.dl.tcnwave)

ONNXRuntime temporal convolution wave inference service (port output).

  • Service class: f8.dl.tcnwave
  • Version: 0.0.1
  • Source directory: f8/dl/tcnwave
  • Tags: onnx, vision, temporal, wave, signal

When to Use

  • Use f8.dl.tcnwave when you want to map temporal features into a continuous waveform-like output.
  • It is a good fit for learned audio-to-control or rhythm-to-wave generation.
  • Reach for it when handcrafted rules are becoming too brittle or too fragmented.

Common Wiring Patterns

  • It commonly follows audio features, rhythm features, or another temporal summary path.
  • Output is usually forwarded into f8.pyengine, TCode-related operators, or visualization.
  • Keep a waveform or text inspection branch attached while validating the model behavior.

Pitfalls / Gotchas

  • Output quality depends strongly on how close live inputs are to the model's training distribution.
  • Verify time windows, feature ordering, and sampling assumptions before tuning downstream thresholds.
  • It is best used for learned style and shaping, not as a blanket replacement for all explicit logic.

Service Reference

How to Run

pixi run -e onnx f8pydl_tcnwave
  • Workdir: ../../../../
  • Environment overrides: none

Typical Inputs / Outputs

  • Data inputs: none
  • Data outputs: predictedChange, monitor
  • Commands: none

Service State Fields

Name Access Required On Node Schema Description
shmName rw true true string / default= Video SHM mapping name (e.g. shm.implayer.video).
weightsDir rw true true string / default=services/f8/dl/weights Directory containing .yaml + .onnx model files. Reset to the default relative path when exporting publish JSON.
modelId rw true true string / default= Model id selected from weightsDir (ignored if modelYamlPath is set).
modelYamlPath rw true false string / default= Optional explicit model yaml path (overrides modelId). Cleared when exporting publish JSON.
ortProvider rw true true string / enum[auto, cuda, cpu] / default=auto auto prefers CUDAExecutionProvider when available.
autoDownloadWeights rw true false boolean / default=True When model file is missing, download from onnxUrl in model yaml.
inferEveryN rw true true integer / default=1 Run model inference every N frames (>=1).
availableModels ro true false array[string] List of model ids discovered from weightsDir.
loadedModel ro true false string / default= Current loaded model id/task.
ortActiveProviders ro true false string / default= JSON list of active ONNX Runtime providers for this session.
lastError ro true false string / default= Last runtime error string (best-effort).
outputScale rw true false number / default=10.0 Denormalization scale applied to raw model output values.
outputBias rw true false number / default=0.0 Denormalization bias applied after outputScale.
useVrFocusCrop rw true false boolean / default=False Apply focus crop before inference. This assumes SHM already provides the target eye view and crops top 20% + left/right 10%.
active rw true false boolean / default=True Service lifecycle state (activate/deactivate).
svcId ro true false string Readonly: current service instance id (svcId).

Key Fields That Matter

  • shmName (Video SHM, rw): Video SHM mapping name (e.g. shm.implayer.video). Schema: string / default=.
  • weightsDir (Weights Dir, rw): Directory containing .yaml + .onnx model files. Reset to the default relative path when exporting publish JSON. Schema: string / default=services/f8/dl/weights.
  • modelId (Model Id, rw): Model id selected from weightsDir (ignored if modelYamlPath is set). Schema: string / default=.
  • modelYamlPath (Model YAML Path, rw): Optional explicit model yaml path (overrides modelId). Cleared when exporting publish JSON. Schema: string / default=.
  • ortProvider (ONNX Runtime Provider, rw): auto prefers CUDAExecutionProvider when available. Schema: string / enum[auto, cuda, cpu] / default=auto.
  • autoDownloadWeights (Auto Download Weights, rw): When model file is missing, download from onnxUrl in model yaml. Schema: boolean / default=True.
  • inferEveryN (Infer Every N Frames, rw): Run model inference every N frames (>=1). Schema: integer / default=1.
  • availableModels (Available Models, ro): List of model ids discovered from weightsDir. Schema: array[string].

Service Commands

None

Service Data Input Ports

None

Service Data Output Ports

Name Required On Node Schema Description
predictedChange true true number Temporal model output value per frame.
monitor true false object{active, alive, cpu, error, ...} Unified runtime monitor snapshots (health/resource/perf/error).

Operators

None

  • No bundled scenario references this node yet.