QualityMonitoringLarIqaConfig
No-reference ML-based image quality assessment. Three model architectures are supported; pick one via the oneof. All produce a single quality score on a normalised [0..100] scale. The Spectrum preprocessor takes care of the per-model resize + ImageNet-normalisation; multi-input models (LAR-IQA, MUSIQ) get one tensor per scale built behind the scenes.
Field |
Type |
Repeated |
Description |
sample_every_n_frames |
Run inference on every Nth frame (1 = every frame). |