Panopticquality

panopticquality

Metric PanopticQuality from torchmetrics (torchmetrics.PanopticQuality)

When to invoke this skill

The user has predictions + ground truth and asks to evaluate with PanopticQuality, or mentions torchmetrics.PanopticQuality directly, or wants the standard torchmetrics implementation.

Reference signature

from torchmetrics import PanopticQuality

# _PanopticQuality(things: collections.abc.Collection[int], stuffs: collections.abc.Collection[int], allow_unknown_preds_category: bool = False, **kwargs: Any) -> None

Library docstring

Wrapper for deprecated import.

>>> from torch import tensor
>>> preds = tensor([[[[6, 0], [0, 0], [6, 0], [6, 0]],
...                  [[0, 0], [0, 0], [6, 0], [0, 1]],
...                  [[0, 0], [0, 0], [6, 0], [0, 1]],
...                  [[0, 0], [7, 0], [6, 0], [1, 0]],
...                  [[0, 0], [7, 0], [7, 0], [7, 0]]]])
>>> target = tensor([[[[6, 0], [0, 1], [6, 0], [0, 1]],
...                   [[0, 1], [0, 1], [6, 0], [0, 1]],
...                   [[0, 1], [0, 1], [6, 0], [1, 0]],
...                   [[0, 1], [7, 0], [1, 0], [1, 0]],
...                   [[0, 1], [7, 0], [7, 0], [7, 0]]]])
>>> panoptic_quality = _PanopticQuality(things = {0, 1}, stuffs = {6, 7})
>>> panoptic_quality(preds, target)
tensor(0.5463, dtype=torch.float64)

Quick recipe

import torchmetrics as _m
score = _m.PanopticQuality(y_true, y_pred)

Don'ts

• Don't reimplement when the library version handles edge cases (NaN, ties, empty inputs) better than a hand-rolled formula.
• Always check the library version's argument order — sklearn is (y_true, y_pred) while torchmetrics is (preds, target).