Modifiedpanopticquality

---
name: modifiedpanopticquality
description: Compute the ModifiedPanopticQuality metric — provided by torchmetrics. Use when the user has predictions and ground-truth and needs to compute ModifiedPanopticQuality, or asks how to score with ModifiedPanopticQuality.
metadata:
  skill_kind: metric
  source_lib: torchmetrics
  import_path: torchmetrics.ModifiedPanopticQuality
  source: library_introspection
---

# modifiedpanopticquality

> Metric `ModifiedPanopticQuality` from `torchmetrics` (torchmetrics.ModifiedPanopticQuality)

## When to invoke this skill

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

## Reference signature

```python
from torchmetrics import ModifiedPanopticQuality

# _ModifiedPanopticQuality(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([[[0, 0], [0, 1], [6, 0], [7, 0], [0, 2], [1, 0]]])
>>> target = tensor([[[0, 1], [0, 0], [6, 0], [7, 0], [6, 0], [255, 0]]])
>>> pq_modified = _ModifiedPanopticQuality(things = {0, 1}, stuffs = {6, 7})
>>> pq_modified(preds, target)
tensor(0.7667, dtype=torch.float64)
```

## Quick recipe

```python
import torchmetrics as _m
score = _m.ModifiedPanopticQuality(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)`.