Mode-analysis suite¶
Beyond segmentation, tokeye bundles the analyses DIII-D researchers usually reach for separate tools to get. Each is a subcommand; --help on any of them shows the full flags.
| Command | What it does |
|---|---|
tokeye elmspec INPUTS... |
ELM detection from the segmentation model's transient channel: per-event time intervals (column times from the first sample) plus per-shot count, ELM frequency (with --fs or --dt), and duty cycle, written to elm_events.csv / elm_summary.csv. |
tokeye alfvenspec INPUTS... |
Alfvén-eigenmode detection with the ae_tf_maskrcnn instance model (needs tokeye[ae]): per-detection boxes/scores (ae_detections.csv) and a per-input instance map (<stem>_ae_instances.npy, i + 1 = detection i). Wide spectrograms are processed in training-width windows automatically. Unwindowed inputs also get the deprecated <stem>_ae_masks.npy (per-detection soft masks), no longer written from 2.0. |
elmspec and alfvenspec take --key as tokeye run does.