mse_loss¶

paddle.fluid.layers.loss. mse_loss ( input, label ) [source]

This op accepts input predications and target label and returns the mean square error.

The loss can be described as:

\[Out = MEAN((input - label)^2)\]

Parameters

• input (Tensor) – Input tensor, the data type should be float32.

• label (Tensor) – Label tensor, the data type should be float32.

Returns

The tensor storing the mean square error difference of input and label.

Return type

Tensor

Return type: Tensor.

Examples

import paddle
input = paddle.to_tensor([1.1, 1.9])
label = paddle.to_tensor([1.0, 2.0])
output = paddle.fluid.layers.mse_loss(input, label)
print(output.numpy())
# [0.01]