tf.keras.losses.MeanSquaredLogarithmicError 损失函数 的用法

均方对数误差

$error=\frac{1}{n}{\sum }_{i=1}^n(log(p_i+1)-log(a_i+1){)}^2$

log 减小了损失值

import tensorflow as tf

y_true = [[0., 1.], [0., 0.]]
y_pred = [[1., 1.], [1., 0.]]
# Using 'auto'/'sum_over_batch_size' reduction type.
msle = tf.keras.losses.MeanSquaredLogarithmicError()
msle(y_true, y_pred).numpy()

0.24022643

不使用 log 时

y_true = [[0., 1.], [0., 0.]]
y_pred = [[1., 1.], [1., 0.]]
# Using 'auto'/'sum_over_batch_size' reduction type.
msle = tf.keras.losses.MeanSquaredError()
msle(y_true, y_pred).numpy()

0.5