Keras custom loss error : Unknown loss function

Question

我尝试在 Keras 中自定义一个损失函数。

我试过两种方法：

import keras.backend as K
from keras.losses import mean_absolute_error

def mae_in_minute(y_true, y_pred):
    temp = K.mean(K.abs(y_pred - y_true), axis=-1)/60
    return temp

和

import keras.backend as K
from keras.losses import mean_absolute_error

def mae_in_minute(y_true, y_pred):
    return mean_absolute_error(y_true, y_pred)/60

我的模型结构是：

input_layer = Input(shape=training.shape[1:len(training.shape)])
added = Conv2D(128, (3, training.shape[2]),activation="relu")(input_layer)
added = Flatten()(added)
added = Dense(600, activation='relu')(added)
added = Dense(400, activation='relu')(added)
added = Dense(256, activation='relu')(added)
added = Dense(256, activation='relu')(added)
added = Dense(256, activation='relu')(added)
added = Dense(200, activation='relu')(added)
added = Dense(100, activation='relu')(added)
added = Dense(50, activation='relu')(added)
output_temp = Dense(2,activation='softmax', name="temp_output")(added)
output_time = Dense(1,activation='relu', name="time_output")(added)
model = Model(input=input_layer, output=[output_temp,output_time])
losses = {
    "temp_output": "categorical_crossentropy",
    "time_output": "mae_in_minute",
}
lossWeights = {"temp_output": 1.0, "time_output": 1.0}
model.compile(optimizer='adam',loss=losses, loss_weights=lossWeights)
model.summary()

但是我在两种自定义损失方法中都收到此错误消息：

Unknown loss function:mae_in_minute

如何解决这个问题？

我找到了一种解决方案 here。

但这是使用自定义损失的唯一方法吗？要提前保存我的模型并加载它？

提前致谢。

Answer 1

去掉custom loss的引号，应该运行完美。 #My_loss

import keras.backend as K
from keras.losses import mean_absolute_error

def mae_in_minute(y_true, y_pred):
    return mean_absolute_error(y_true, y_pred)/60

##之前损失 = { "temp_output": "categorical_crossentropy", "time_output": "mae_in_minute", } lossWeights = {"temp_output": 1.0, "time_output": 1.0} model.compile(优化器='adam',loss=losses, loss_weights=lossWeights) model.summary()

##之后损失 = { "temp_output": "categorical_crossentropy", "time_output": mae_in_minute, } lossWeights = {"temp_output": 1.0, "time_output": 1.0} model.compile(优化器='adam',loss=losses, loss_weights=lossWeights) model.summary()

Keras custom loss error : Unknown loss function

Keras custom loss error : Unknown loss function

python

keras

tensorflow

loss-function