使用tensorflow自定义loss函数定义python函数wrapper类

107 阅读 0 评论 71 点赞

我是靠谱客的博主落寞芝麻，这篇文章主要介绍使用tensorflow自定义loss函数定义python函数wrapper类，现在分享给大家，希望可以做个参考。

文章目录

定义python函数
wrapper
类

定义python函数

复制代码

1
2
3
4
5
6
7
8
9

def my_huber_loss(y_true, y_pred):
error = y_true - y_pred
is_small_error = tf.abs(error) <= threshold
small_error_loss = tf.square(error) / 2
big_error_loss = threshold * (tf.abs(error) - (0.5 * threshold))
return tf.where(is_small_error, small_error_loss, big_error_loss)
model.compile(loss=my_huber_loss, optimizer=...)

需要注意的是：如果我们想要传入超参数，我们不能直接在函数内添加参数，而应该使用wrapper,因为作为loss函数只能够拥有 $y_true,y_pred$ 两个参数

wrapper

复制代码

1
2
3
4
5
6
7
8
9
10
11
12
# wrapper function that accepts the hyperparameter
def my_huber_loss_with_threshold(threshold):
# function that accepts the ground truth and predictions
def my_huber_loss(y_true, y_pred):
error = y_true - y_pred
is_small_error = tf.abs(error) <= threshold
small_error_loss = tf.square(error) / 2
big_error_loss = threshold * (tf.abs(error) - (0.5 * threshold))
return tf.where(is_small_error, small_error_loss, big_error_loss)
# return the inner function tuned by the hyperparameter
return my_huber_loss

类

同时，我们也可以定义一个loss类，可以支持更多操作。

复制代码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
from tensorflow.keras.losses import Loss
class MyHuberLoss(Loss):
# initialize instance attributes
def __init__(self, threshold=1):
super().__init__()
self.threshold = threshold
# compute loss
def call(self, y_true, y_pred):
error = y_true - y_pred
is_small_error = tf.abs(error) <= self.threshold
small_error_loss = tf.square(error) / 2
big_error_loss = self.threshold * (tf.abs(error) - (0.5 * self.threshold))
return tf.where(is_small_error, small_error_loss, big_error_loss)