1 ordinal_labels_to_levels

rri_metrics.ordinal_labels_to_levels(labels, *, num_classes)

Convert ordinal labels to CORAL level targets.

CORAL represents a K-class ordinal label y ∈ {0, ..., K-1} as K-1 binary targets:

levels[k] = 1  if y > k
          = 0  otherwise

1.1 Parameters

Name	Type	Description	Default
labels	Tensor	`Tensor["...", int64]` with values in `[0, num_classes-1]`.	required
num_classes	int	Number of ordinal classes `K`.	required

1.2 Returns

Name	Type	Description
	Tensor	`Tensor["... K-1", float32]` of binary level targets.

# ordinal_labels_to_levels { #aria_nbv.rri_metrics.ordinal_labels_to_levels }

```python
rri_metrics.ordinal_labels_to_levels(labels, *, num_classes)
```

Convert ordinal labels to CORAL level targets.

CORAL represents a K-class ordinal label ``y ∈ {0, ..., K-1}`` as ``K-1``
binary targets:

    levels[k] = 1  if y > k
              = 0  otherwise

## Parameters {.doc-section .doc-section-parameters}

| Name        | Type   | Description                                                     | Default    |
|-------------|--------|-----------------------------------------------------------------|------------|
| labels      | Tensor | ``Tensor["...", int64]`` with values in ``[0, num_classes-1]``. | _required_ |
| num_classes | int    | Number of ordinal classes ``K``.                                | _required_ |

## Returns {.doc-section .doc-section-returns}

| Name   | Type   | Description                                             |
|--------|--------|---------------------------------------------------------|
|        | Tensor | ``Tensor["... K-1", float32]`` of binary level targets. |