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.

Inline emphasis start-string without end-string.

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

Inline emphasis start-string without end-string.

• output (Tensor): tensor with shape: [1] by default.

Examples

import numpy as np

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 [1]
kldiv_criterion = nn.KLDivLoss(reduction='batchmean')
# shape=[1]

# 'mean' reduction, loss shape will be [1]
kldiv_criterion = nn.KLDivLoss(reduction='mean')
# shape=[1]

# 'sum' reduction, loss shape will be [1]
kldiv_criterion = nn.KLDivLoss(reduction='sum')
# shape=[1]

# 'none' reduction, loss shape is same with X shape
kldiv_criterion = nn.KLDivLoss(reduction='none')