# @tensorleap\_custom\_metric

The purpose of the `tensorleap_custom_metric` decorator is to add a [custom metric ](https://docs.tensorleap.ai/tensorleap-integration/writing-integration-code/custom-metrics)suited to your needs to the tensorleap platform.

```python
@tensorleap_custom_metric(name='metrics',
                          direction=MetricDirection.Downward,
                          compute_insights=None)
def metrics(
    tensor_1: npt.NDArray[np.float32],
    tensor_2: npt.NDArray[np.float32],
    ...
) -> Union[npt.NDArray[np.float32], Dict[str, npt.NDArray[np.float32]]]:
    pass
```

<table><thead><tr><th width="158.46928201888204">Args</th><th></th></tr></thead><tbody><tr><td><code>name</code></td><td>The name of the the metric</td></tr><tr><td><code>direction</code></td><td><p>(optional, defaults to<code>MetricDirection.Downward</code>)</p><ul><li>For a metric where lower values are better use <code>MetricDirection.Downward</code></li><li>For a metric where higher values are better use <code>MetricDirection.Upward</code></li></ul></td></tr><tr><td><code>compute_insights</code></td><td><p>(optional, defaults to None). Specify metrics that should not have insights computed on them:<br></p><ul><li>in case the metric function returns a dictionary, compute_insights should return a dictionary as well, mapping metric names to booleans.</li><li>otherwise, compute_insights=False if this metric should be ommited when computing insights</li></ul></td></tr></tbody></table>

#### Metric Function inputs:

np.ndarray tensors with a batch dimension

#### Metric Function outputs:

np.ndarray batched metric values

### Examples

#### Basic Usage

```python
import numpy as np
import numpy.typing as npt
from code_loader.inner_leap_binder.leapbinder_decorators import tensorleap_custom_metric


@tensorleap_custom_metric(name='metrics',
                          direction=MetricDirection.Downward,
                          compute_insights=None)
def custom_metric_distances(
    y_true: npt.NDArray[np.float32],
    y_pred: npt.NDArray[np.float32]
) -> dict[str, npt.NDArray[np.float32]]:
    diff = y_true - y_pred
    axis = tuple(range(1, diff.ndim))

    return {
        "mean_difference": np.mean(diff, axis=axis),
        "mean_absolute_difference": np.mean(np.abs(diff), axis=axis)
    }

```

Full script usage can be found at [**Integration Script**](https://docs.tensorleap.ai/writing-integration-code#dataset-script).