Modified Panoptic Quality¶
Module Interface¶
- class torchmetrics.detection.ModifiedPanopticQuality(things, stuffs, allow_unknown_preds_category=False, **kwargs)[source]
Compute Modified Panoptic Quality for panoptic segmentations.
The metric was introduced in Seamless Scene Segmentation paper, and is an adaptation of the original Panoptic Quality where the metric for a stuff class is computed as
where IOU_c is the sum of the intersection over union of all matching segments for a given class, and |S_c| is the overall number of segments in the ground truth for that class.
- Parameters:
things¶ (
Collection
[int
]) – Set ofcategory_id
for countable things.stuffs¶ (
Collection
[int
]) – Set ofcategory_id
for uncountable stuffs.allow_unknown_preds_category¶ (
bool
) – Boolean flag to specify if unknown categories in the predictions are to be ignored in the metric computation or raise an exception when found.
- Raises:
ValueError – If
things
,stuffs
have at least one commoncategory_id
.TypeError – If
things
,stuffs
contain non-integercategory_id
.
Example
>>> from torch import tensor >>> from torchmetrics.detection import ModifiedPanopticQuality >>> 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)
- plot(val=None, ax=None)[source]
Plot a single or multiple values from the metric.
- Parameters:
val¶ (
Union
[Tensor
,Sequence
[Tensor
],None
]) – Either a single result from calling metric.forward or metric.compute or a list of these results. If no value is provided, will automatically call metric.compute and plot that result.ax¶ (
Optional
[Axes
]) – An matplotlib axis object. If provided will add plot to that axis
- Return type:
- Returns:
Figure object and Axes object
- Raises:
ModuleNotFoundError – If matplotlib is not installed
>>> from torch import tensor >>> from torchmetrics.detection import ModifiedPanopticQuality >>> 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]]]]) >>> metric = ModifiedPanopticQuality(things = {0, 1}, stuffs = {6, 7}) >>> metric.update(preds, target) >>> fig_, ax_ = metric.plot()
>>> # Example plotting multiple values >>> from torch import tensor >>> from torchmetrics.detection import ModifiedPanopticQuality >>> 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]]]]) >>> metric = ModifiedPanopticQuality(things = {0, 1}, stuffs = {6, 7}) >>> vals = [] >>> for _ in range(20): ... vals.append(metric(preds, target)) >>> fig_, ax_ = metric.plot(vals)
Functional Interface¶
- torchmetrics.functional.detection.modified_panoptic_quality(preds, target, things, stuffs, allow_unknown_preds_category=False)[source]
Compute Modified Panoptic Quality for panoptic segmentations.
The metric was introduced in Seamless Scene Segmentation paper, and is an adaptation of the original Panoptic Quality where the metric for a stuff class is computed as
where IOU_c is the sum of the intersection over union of all matching segments for a given class, and |S_c| is the overall number of segments in the ground truth for that class.
- Parameters:
preds¶ (
Tensor
) – torch tensor with panoptic detection of shape [height, width, 2] containing the pair (category_id, instance_id) for each pixel of the image. If the category_id refer to a stuff, the instance_id is ignored.target¶ (
Tensor
) – torch tensor with ground truth of shape [height, width, 2] containing the pair (category_id, instance_id) for each pixel of the image. If the category_id refer to a stuff, the instance_id is ignored.things¶ (
Collection
[int
]) – Set ofcategory_id
for countable things.stuffs¶ (
Collection
[int
]) – Set ofcategory_id
for uncountable stuffs.allow_unknown_preds_category¶ (
bool
) – Boolean flag to specify if unknown categories in the predictions are to be ignored in the metric computation or raise an exception when found.
- Raises:
ValueError – If
things
,stuffs
have at least one commoncategory_id
.TypeError – If
things
,stuffs
contain non-integercategory_id
.TypeError – If
preds
ortarget
is not antorch.Tensor
.ValueError – If
preds
ortarget
has different shape.ValueError – If
preds
has less than 3 dimensions.ValueError – If the final dimension of
preds
has size != 2.
- Return type:
Example
>>> 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]]]) >>> modified_panoptic_quality(preds, target, things = {0, 1}, stuffs = {6, 7}) tensor(0.7667, dtype=torch.float64)