# KLDivLoss¶

class `paddle.nn.` `KLDivLoss` ( reduction='mean' ) [source]

This interface calculates the Kullback-Leibler divergence loss between Input(X) and Input(Target). Notes that Input(X) is the log-probability and Input(Target) is the probability.

KL divergence loss is calculated as follows:

\$\$l(x, y) = y * (log(y) - x)\$\$

Parameters

reduction (Tensor) – Indicate how to average the loss, the candicates are `'none'` | `'batchmean'` | `'mean'` | `'sum'`. If reduction is `'mean'`, the reduced mean loss is returned; If reduction is `'batchmean'`, the sum loss divided by batch size is returned; if reduction is `'sum'`, the reduced sum loss is returned; if reduction is `'none'`, no reduction will be apllied. Default is `'mean'`.

Shape:

• input (Tensor): (N, *), where * means, any number of additional dimensions.

System Message: WARNING/2 (/usr/local/lib/python3.8/site-packages/paddle/nn/layer/loss.py:docstring of paddle.nn.layer.loss.KLDivLoss, line 20); backlink

Inline emphasis start-string without end-string.

• label (Tensor): (N, *), same shape as input.

System Message: WARNING/2 (/usr/local/lib/python3.8/site-packages/paddle/nn/layer/loss.py:docstring of paddle.nn.layer.loss.KLDivLoss, line 22); backlink

Inline emphasis start-string without end-string.

• output (Tensor): tensor with shape:  by default.

Examples

```import paddle
import numpy as np
import paddle.nn as nn

shape = (5, 20)
x = np.random.uniform(-10, 10, shape).astype('float32')
target = np.random.uniform(-10, 10, shape).astype('float32')

# 'batchmean' reduction, loss shape will be 
kldiv_criterion = nn.KLDivLoss(reduction='batchmean')
pred_loss = kldiv_criterion(paddle.to_tensor(x),
paddle.to_tensor(target))
# shape=

# 'mean' reduction, loss shape will be 
kldiv_criterion = nn.KLDivLoss(reduction='mean')
pred_loss = kldiv_criterion(paddle.to_tensor(x),
paddle.to_tensor(target))
# shape=

# 'sum' reduction, loss shape will be 
kldiv_criterion = nn.KLDivLoss(reduction='sum')
pred_loss = kldiv_criterion(paddle.to_tensor(x),
paddle.to_tensor(target))
# shape=

# 'none' reduction, loss shape is same with X shape
kldiv_criterion = nn.KLDivLoss(reduction='none')
pred_loss = kldiv_criterion(paddle.to_tensor(x),
paddle.to_tensor(target))
# shape=[5, 20]
```
`forward` ( input, label )

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters
• *inputs (tuple) – unpacked tuple arguments

• **kwargs (dict) – unpacked dict arguments