<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/neural-structured-learning/blob/v1.4.0/neural_structured_learning/lib/distances.py#L115-L182) |

Adds a Jensen-Shannon divergence to the training procedure.

    nsl.lib.jensen_shannon_divergence(
        labels,
        predictions,
        axis=None,
        weights=1.0,
        scope=None,
        loss_collection=tf.compat.v1.GraphKeys.LOSSES,
        reduction=tf.compat.v1.losses.Reduction.SUM_BY_NONZERO_WEIGHTS
    )

For brevity, let `P = labels`, `Q = predictions`, `KL(P||Q)` be the
Kullback-Leibler divergence as defined in the description of the
[`nsl.lib.kl_divergence`](https://www.tensorflow.org/neural_structured_learning/api_docs/python/nsl/lib/kl_divergence) function.". The Jensen-Shannon divergence (JSD) is

    M = (P + Q) / 2
    JSD(P||Q) = KL(P||M) / 2 + KL(Q||M) / 2

This function assumes that `predictions` and `labels` are the values of a
multinomial distribution, i.e., each value is the probability of the
corresponding class.

For the usage of `weights` and `reduction`, please refer to `tf.losses`.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `labels` | `Tensor` of type `float32` or `float64`, with shape `[d1, ..., dN, num_classes]`, represents the target distribution. |
| `predictions` | `Tensor` of the same type and shape as `labels`, represents the predicted distribution. |
| `axis` | The dimension along which the Jensen-Shannon divergence is computed. The values of `labels` and `predictions` along `axis` should meet the requirements of a multinomial distribution. |
| `weights` | (optional) `Tensor` whose rank is either 0, or the same as that of `labels`, and must be broadcastable to `labels` (i.e., all dimensions must be either `1`, or the same as the corresponding `losses` dimension). |
| `scope` | The scope for the operations performed in computing the loss. |
| `loss_collection` | Collection to which the loss will be added. |
| `reduction` | Type of reduction to apply to the loss. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| Weighted loss `float` `Tensor`. If `reduction` is [`tf.compat.v1.losses.Reduction.MEAN`](https://www.tensorflow.org/api_docs/python/tf/compat/v1/losses/Reduction#MEAN), this has the same shape as `labels`, otherwise, it is a scalar. ||

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `InvalidArgumentError` | If `labels` or `predictions` don't meet the requirements of a multinomial distribution. |
| `ValueError` | If `axis` is `None`, the shape of `predictions` doesn't match that of `labels`, or if the shape of `weights` is invalid. |

<br />