`fastvideo.eval.metrics.physics_iq.mse.metric.BaseMetric`

BaseMetric()

Abstract base class for all eval metrics.

Two execution shapes:

Per-sample (is_set_metric=False, default) — implement :meth:compute. The Evaluator calls it once per input sample and returns one :class:MetricResult per sample.
Set-vs-set (is_set_metric=True) — implement :meth:accumulate (called once per sample to buffer features) and :meth:finalize (called once after all samples to compute the corpus-level result). Use :meth:reset to clear buffers and :meth:merge_from to fold multi-GPU per-worker state together.

Optionally override :meth:setup to eagerly load models. Metrics that chunk along the time dim for memory hardcode their own chunk size in __init__ (see optical_flow for the canonical example). Eval always processes one video per :meth:Evaluator.evaluate call; compute / accumulate receive a single sample, not a batch.

`fastvideo.eval.metrics.physics_iq.mse.metric.BaseMetric.to`

to(device: str | torch.device) -> BaseMetric

Move metric (and its internal models) to device.

`fastvideo.eval.metrics.physics_iq.mse.metric.BaseMetric.setup`

setup() -> None

Eagerly load models. Called once by :class:EvalWorker.

Default is a no-op; metrics with no eager state (pixel math, closed-form ops) inherit this. Override only if your metric needs to load weights.

`fastvideo.eval.metrics.physics_iq.mse.metric.BaseMetric.compute`

compute(sample: dict) -> MetricResult

Per-sample metrics: compute the score for one sample.

sample["video"] is (T, C, H, W) float in [0, 1]. sample["reference"] (if used) has the same shape. Return self._skip(sample, reason) for missing inputs.

`fastvideo.eval.metrics.physics_iq.mse.metric.BaseMetric.reset`

reset() -> None

Clear accumulator state at the start of each evaluate() call.

`fastvideo.eval.metrics.physics_iq.mse.metric.BaseMetric.accumulate`

accumulate(sample: dict) -> None

Buffer per-sample features for a corpus-level metric.

`fastvideo.eval.metrics.physics_iq.mse.metric.BaseMetric.finalize`

finalize() -> MetricResult

Compute the corpus-level result from buffered state.

`fastvideo.eval.metrics.physics_iq.mse.metric.BaseMetric.merge_from`

merge_from(other: BaseMetric) -> None

Multi-GPU: fold another worker's accumulator state into this one.

`fastvideo.eval.metrics.physics_iq.mse.metric.register`

register(name: str)

Decorator to register a metric class.

Usage::

@register("ssim")
class SSIMMetric(BaseMetric):
    ...

`fastvideo.eval.metrics.physics_iq.mse.metric.MetricResult`

MetricResult(name: str, score: float | None, details: dict[str, Any] = dict())

Standard result container returned by all metrics.

score is None when the metric was skipped (e.g. missing required input). Check details["skipped"] for the reason.

`fastvideo.eval.metrics.physics_iq.mse.metric.compute_mse`

compute_mse(video1_frames: np.ndarray, video2_frames: np.ndarray) -> list[float]

`fastvideo.eval.metrics.physics_iq.mse.metric.prepare_pair`

prepare_pair(sample: dict[str, Any], *, prep_kwargs: dict[str, Any] | None = None) -> PreparedPhysicsIQPair

Resolve a sample into a prepared (gen, ref) pair.

Caches the result on sample['_physics_iq_pair'] so other physics_iq sub-metrics on the same sample reuse it instead of re-decoding.

`fastvideo.eval.metrics.physics_iq.mse.metric.PhysicsIQMSEMetric`

PhysicsIQMSEMetric(**kwargs: Any)

Source

@register("physics_iq.mse")
class PhysicsIQMSEMetric(BaseMetric):
    name = "physics_iq.mse"
    requires_reference = True
    higher_is_better = False

    def __init__(self, **kwargs: Any) -> None:
        super().__init__()
        self._kwargs = kwargs

    def compute(self, sample: dict) -> MetricResult:
        prepared = prepare_pair(sample, prep_kwargs=self._kwargs)
        per_frame = compute_mse(prepared.reference_quarter, prepared.generated_quarter)
        score = sum(per_frame) / len(per_frame)
        return MetricResult(name=self.name, score=score, details={"per_frame": per_frame})

`fastvideo.eval.metrics.physics_iq.mse.metric.PhysicsIQMSEMetric.compute`

compute(sample: dict) -> MetricResult

Source

def compute(self, sample: dict) -> MetricResult:
    prepared = prepare_pair(sample, prep_kwargs=self._kwargs)
    per_frame = compute_mse(prepared.reference_quarter, prepared.generated_quarter)
    score = sum(per_frame) / len(per_frame)
    return MetricResult(name=self.name, score=score, details={"per_frame": per_frame})