Skip to content
FastVideo
Esc
↑↓navigate↵open⌘Jpreview
On this page

metric

VBench Appearance Style — CLIP ViT-B/32 text-image alignment.

Per-frame cosine similarity between CLIP image features and a text prompt describing the expected style. Requires sample["text_prompt"].

fastvideo.eval.metrics.vbench.appearance_style.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.vbench.appearance_style.metric.BaseMetric.to

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

Move metric (and its internal models) to device.

fastvideo.eval.metrics.vbench.appearance_style.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.vbench.appearance_style.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.vbench.appearance_style.metric.BaseMetric.reset

reset() -> None

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

fastvideo.eval.metrics.vbench.appearance_style.metric.BaseMetric.accumulate

accumulate(sample: dict) -> None

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

fastvideo.eval.metrics.vbench.appearance_style.metric.BaseMetric.finalize

finalize() -> MetricResult

Compute the corpus-level result from buffered state.

fastvideo.eval.metrics.vbench.appearance_style.metric.BaseMetric.merge_from

merge_from(other: BaseMetric) -> None

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

fastvideo.eval.metrics.vbench.appearance_style.metric.register

register(name: str)

Decorator to register a metric class.

Usage::

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

fastvideo.eval.metrics.vbench.appearance_style.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.vbench.appearance_style.metric.AppearanceStyleMetric

AppearanceStyleMetric()
Source
@register("vbench.appearance_style")
class AppearanceStyleMetric(BaseMetric):

name = "vbench.appearance_style"
requires_reference = False
higher_is_better = True
needs_gpu = True
dependencies = ["clip"]
backbone = "clip_vit_b32"

def __init__(self) -> None:
    super().__init__()
    self._model: Any = None

def to(self, device):
    super().to(device)
    if self._model is not None:
        self._model = self._model.to(self.device)
    return self

def setup(self) -> None:
    if self._model is not None:
        return
    import clip
    from fastvideo.eval.models import get_cache_dir
    self._model, _ = clip.load(
        "ViT-B/32",
        device=self.device,
        download_root=str(get_cache_dir() / "clip"),
    )
    self._model.eval()

@torch.no_grad()
def compute(self, sample: dict) -> MetricResult:
    import clip

    video = sample["video"]  # (T, C, H, W)
    text_prompt = sample.get("text_prompt")
    if text_prompt is None:
        return self._skip(sample, "missing text_prompt")

    frames = _clip_transform(video.to(self.device))

    chunk = self._chunk_size or 64
    img_feats = []
    for i in range(0, frames.shape[0], chunk):
        f = self._model.encode_image(frames[i:i + chunk]).float()
        f = F.normalize(f, dim=-1, p=2)
        img_feats.append(f)
    img_feats = torch.cat(img_feats, dim=0)  # (T, D)

    # truncate=True: CLIP context length is 77 tokens; long prompts
    # truncate instead of raising. Matches CLIP's documented convention.
    text_tokens = clip.tokenize([text_prompt], truncate=True).to(self.device)
    text_feat = self._model.encode_text(text_tokens).float()
    text_feat = F.normalize(text_feat, dim=-1, p=2)  # (1, D)

    sims = (img_feats @ text_feat.T).squeeze(-1)  # (T,)
    return MetricResult(
        name=self.name,
        score=float(sims.mean().item()),
        details={"per_frame": sims.tolist()},
    )</code></pre></details>


fastvideo.eval.metrics.vbench.appearance_style.metric.AppearanceStyleMetric.to


to(device)


Source
def to(self, device):
    super().to(device)
    if self._model is not None:
        self._model = self._model.to(self.device)
    return self


fastvideo.eval.metrics.vbench.appearance_style.metric.AppearanceStyleMetric.setup


setup() -> None


Source
def setup(self) -> None:
    if self._model is not None:
        return
    import clip
    from fastvideo.eval.models import get_cache_dir
    self._model, _ = clip.load(
        "ViT-B/32",
        device=self.device,
        download_root=str(get_cache_dir() / "clip"),
    )
    self._model.eval()


fastvideo.eval.metrics.vbench.appearance_style.metric.AppearanceStyleMetric.compute


compute(sample: dict) -> MetricResult


Source
@torch.no_grad()
def compute(self, sample: dict) -> MetricResult:
    import clip

video = sample&#91;&quot;video&quot;&#93;  # (T, C, H, W)
text_prompt = sample.get(&quot;text_prompt&quot;)
if text_prompt is None:
    return self._skip(sample, &quot;missing text_prompt&quot;)

frames = _clip_transform(video.to(self.device))

chunk = self._chunk_size or 64
img_feats = &#91;&#93;
for i in range(0, frames.shape&#91;0&#93;, chunk):
    f = self._model.encode_image(frames&#91;i:i + chunk&#93;).float()
    f = F.normalize(f, dim=-1, p=2)
    img_feats.append(f)
img_feats = torch.cat(img_feats, dim=0)  # (T, D)

# truncate=True: CLIP context length is 77 tokens; long prompts
# truncate instead of raising. Matches CLIP&#x27;s documented convention.
text_tokens = clip.tokenize(&#91;text_prompt&#93;, truncate=True).to(self.device)
text_feat = self._model.encode_text(text_tokens).float()
text_feat = F.normalize(text_feat, dim=-1, p=2)  # (1, D)

sims = (img_feats @ text_feat.T).squeeze(-1)  # (T,)
return MetricResult(
    name=self.name,
    score=float(sims.mean().item()),
    details=&#123;&quot;per_frame&quot;: sims.tolist()&#125;,
)</code></pre></details>

Was this page helpful?