ML Community Day is November 9! Join us for updates from TensorFlow, JAX, and more Learn more


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

Inherits From: Loss

Used in the notebooks

Used in the guide Used in the tutorials

loss = square(y_true - y_pred)

Standalone usage:

y_true = [[0., 1.], [0., 0.]]
y_pred = [[1., 1.], [1., 0.]]
# Using 'auto'/'sum_over_batch_size' reduction type.
mse = tf.keras.losses.MeanSquaredError()
mse(y_true, y_pred).numpy()
# Calling with 'sample_weight'.
mse(y_true, y_pred, sample_weight=[0.7, 0.3]).numpy()
# Using 'sum' reduction type.
mse = tf.keras.losses.MeanSquaredError(
mse(y_true, y_pred).numpy()
# Using 'none' reduction type.
mse = tf.keras.losses.MeanSquaredError(
mse(y_true, y_pred).numpy()
array([0.5, 0.5], dtype=float32)

Usage with the compile() API:

model.compile(optimizer='sgd', loss=tf.keras.losses.MeanSquaredError())

reduction Type of tf.keras.losses.Reduction to apply to loss. Default value is AUTO. AUTO indicates that the reduction option will be determined by the usage context. For almost all cases this defaults to SUM_OVER_BATCH_SIZE. When used with