Keras自定義損失錯誤：未知損失函數

Question

我試圖在Keras中自定義損失函數。

我嘗試了兩種方法：

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

我的模型結構是：

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()

但是我使用兩種自定義丟失方法都收到此錯誤消息：

未知的損失函數：mae_in_minute

我該如何解決這個問題？

我在這里找到了一種解決方案。

但這是使用自定義損失的唯一方法嗎？ 要預先保存我的模型並加載它？

提前致謝。

Answer 1

只需刪除自定義損失的形式，它就可以完美運行。

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

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()

后

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()