1 topk_accuracy_from_probs

rri_metrics.topk_accuracy_from_probs(probs, labels, *, top_k)

Compute top-k accuracy from class probabilities.

1.1 Parameters

Name	Type	Description	Default
probs	Tensor	`Tensor["N K"]` class probabilities.	required
labels	Tensor	`Tensor["N"]` integer class labels.	required
top_k	int	Number of highest-probability classes to consider.	required

1.2 Returns

Name	Type	Description
	Tensor	`Tensor[""]` scalar accuracy in `[0, 1]`.

# topk_accuracy_from_probs { #aria_nbv.rri_metrics.topk_accuracy_from_probs }

```python
rri_metrics.topk_accuracy_from_probs(probs, labels, *, top_k)
```

Compute top-k accuracy from class probabilities.

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

| Name   | Type   | Description                                        | Default    |
|--------|--------|----------------------------------------------------|------------|
| probs  | Tensor | ``Tensor["N K"]`` class probabilities.             | _required_ |
| labels | Tensor | ``Tensor["N"]`` integer class labels.              | _required_ |
| top_k  | int    | Number of highest-probability classes to consider. | _required_ |

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

| Name   | Type   | Description                                   |
|--------|--------|-----------------------------------------------|
|        | Tensor | ``Tensor[""]`` scalar accuracy in ``[0, 1]``. |