tf.keras.losses.MeanSquaredError

View source on GitHub

Computes the mean of squares of errors between labels and predictions.

Inherits From: Loss

tf.keras.losses.MeanSquaredError(
    reduction='sum_over_batch_size',
    name='mean_squared_error'
)

Used in the notebooks

Used in the tutorials
Time series forecasting Intro to Autoencoders Load CSV data Hello, many worlds Recommending movies: ranking

Formula:

loss = mean(square(y_true - y_pred))

Args
reduction	Type of reduction to apply to the loss. In almost all cases this should be "sum_over_batch_size". Supported options are "sum", "sum_over_batch_size" or None.
name	Optional name for the loss instance.

Methods

call

View source

call(
    y_true, y_pred
)

from_config

View source

@classmethod
from_config(
    config
)

get_config

View source

get_config()

__call__

View source

__call__(
    y_true, y_pred, sample_weight=None
)

Call self as a function.