VBench Human Action — UMT ViT-L/16 action classification (Kinetics-400).

Classifies human actions in 16-frame clips. Top-5 predictions with confidence >= 0.85 are compared against the ground-truth action label. Score = 1.0 if match found, 0.0 otherwise.

`fastvideo.eval.metrics.vbench.human_action.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.human_action.metric.BaseMetric.to`

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

Move metric (and its internal models) to device.

`fastvideo.eval.metrics.vbench.human_action.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.human_action.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.human_action.metric.BaseMetric.reset`

reset() -> None

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

`fastvideo.eval.metrics.vbench.human_action.metric.BaseMetric.accumulate`

accumulate(sample: dict) -> None

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

`fastvideo.eval.metrics.vbench.human_action.metric.BaseMetric.finalize`

finalize() -> MetricResult

Compute the corpus-level result from buffered state.

`fastvideo.eval.metrics.vbench.human_action.metric.BaseMetric.merge_from`

merge_from(other: BaseMetric) -> None

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

`fastvideo.eval.metrics.vbench.human_action.metric.register`

register(name: str)

Decorator to register a metric class.

Usage::

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

`fastvideo.eval.metrics.vbench.human_action.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.human_action.metric.extract_frames`

extract_frames(video: torch.Tensor, n_frames: int | None = None) -> torch.Tensor

Uniformly sample n_frames from a (T, C, H, W) video tensor.

`fastvideo.eval.metrics.vbench.human_action.metric.HumanActionMetric`

HumanActionMetric()

Source

@register("vbench.human_action")
class HumanActionMetric(BaseMetric):

    name = "vbench.human_action"
    requires_reference = False
    higher_is_better = True
    needs_gpu = True
    dependencies = ["timm"]

    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
        from timm.models import create_model
        from fastvideo.eval.models import ensure_checkpoint

        ckpt_path = ensure_checkpoint(
            "umt_l16_kinetics400.pth",
            source="OpenGVLab/VBench_Used_Models",
            filename="l16_ptk710_ftk710_ftk400_f16_res224.pth",
        )

        import vbench.third_party.umt.models.modeling_finetune  # noqa: F401

        self._model = create_model(
            "vit_large_patch16_224",
            pretrained=False,
            num_classes=400,
            all_frames=16,
            tubelet_size=1,
            use_learnable_pos_emb=False,
            fc_drop_rate=0.0,
            drop_rate=0.0,
            drop_path_rate=0.2,
            attn_drop_rate=0.0,
            drop_block_rate=None,
            use_checkpoint=False,
            checkpoint_num=16,
            use_mean_pooling=True,
            init_scale=0.001,
        )
        state_dict = torch.load(ckpt_path, map_location="cpu", weights_only=False)
        self._model.load_state_dict(state_dict, strict=False)
        self._model.to(self.device)
        self._model.eval()

    @torch.no_grad()
    def compute(self, sample: dict) -> MetricResult:
        video = sample["video"]  # (T, C, H, W) [0, 1]
        text_prompt = sample.get("text_prompt")
        if text_prompt is None:
            return self._skip(sample, "missing text_prompt with action labels")

        cat_dict = _load_cat_dict()

        frames = extract_frames(video, 16)  # (16, C, H, W)
        frames = resize(frames, 256, antialias=True)
        frames = center_crop(frames, 224)
        frames = normalize(frames, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
        # UMT expects (C, T, H, W); add a leading batch dim of 1.
        clip_in = frames.permute(1, 0, 2, 3).unsqueeze(0).to(self.device)

        logits = torch.sigmoid(self._model(clip_in))  # (1, 400)
        top_scores, top_indices = torch.topk(logits[0], 5)
        top_indices = top_indices.tolist()
        top_scores = top_scores.tolist()

        predictions = [
            cat_dict.get(str(idx), "") for idx, score in zip(top_indices, top_scores, strict=False) if score >= 0.85
        ]
        gt_label = text_prompt.lower().strip()
        match = any(pred == gt_label for pred in predictions)
        return MetricResult(
            name=self.name,
            score=1.0 if match else 0.0,
            details={
                "predictions": predictions,
                "ground_truth": gt_label
            },
        )

`fastvideo.eval.metrics.vbench.human_action.metric.HumanActionMetric.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.human_action.metric.HumanActionMetric.setup`

setup() -> None

Source

def setup(self) -> None:
    if self._model is not None:
        return
    from timm.models import create_model
    from fastvideo.eval.models import ensure_checkpoint

    ckpt_path = ensure_checkpoint(
        "umt_l16_kinetics400.pth",
        source="OpenGVLab/VBench_Used_Models",
        filename="l16_ptk710_ftk710_ftk400_f16_res224.pth",
    )

    import vbench.third_party.umt.models.modeling_finetune  # noqa: F401

    self._model = create_model(
        "vit_large_patch16_224",
        pretrained=False,
        num_classes=400,
        all_frames=16,
        tubelet_size=1,
        use_learnable_pos_emb=False,
        fc_drop_rate=0.0,
        drop_rate=0.0,
        drop_path_rate=0.2,
        attn_drop_rate=0.0,
        drop_block_rate=None,
        use_checkpoint=False,
        checkpoint_num=16,
        use_mean_pooling=True,
        init_scale=0.001,
    )
    state_dict = torch.load(ckpt_path, map_location="cpu", weights_only=False)
    self._model.load_state_dict(state_dict, strict=False)
    self._model.to(self.device)
    self._model.eval()

`fastvideo.eval.metrics.vbench.human_action.metric.HumanActionMetric.compute`

compute(sample: dict) -> MetricResult

Source

@torch.no_grad()
def compute(self, sample: dict) -> MetricResult:
    video = sample["video"]  # (T, C, H, W) [0, 1]
    text_prompt = sample.get("text_prompt")
    if text_prompt is None:
        return self._skip(sample, "missing text_prompt with action labels")

    cat_dict = _load_cat_dict()

    frames = extract_frames(video, 16)  # (16, C, H, W)
    frames = resize(frames, 256, antialias=True)
    frames = center_crop(frames, 224)
    frames = normalize(frames, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
    # UMT expects (C, T, H, W); add a leading batch dim of 1.
    clip_in = frames.permute(1, 0, 2, 3).unsqueeze(0).to(self.device)

    logits = torch.sigmoid(self._model(clip_in))  # (1, 400)
    top_scores, top_indices = torch.topk(logits[0], 5)
    top_indices = top_indices.tolist()
    top_scores = top_scores.tolist()

    predictions = [
        cat_dict.get(str(idx), "") for idx, score in zip(top_indices, top_scores, strict=False) if score >= 0.85
    ]
    gt_label = text_prompt.lower().strip()
    match = any(pred == gt_label for pred in predictions)
    return MetricResult(
        name=self.name,
        score=1.0 if match else 0.0,
        details={
            "predictions": predictions,
            "ground_truth": gt_label
        },
    )