加载具有自定义损失 + keras 的模型 [英] Loading model with custom loss + keras

问题描述

在 Keras 中，如果您需要使用附加参数自定义损失，我们可以像 https://datascience.stackexchange.com/questions/25029/custom-loss-function-with-additional-parameter-in-keras

In Keras, if you need to have a custom loss with additional parameters, we can use it like mentioned on https://datascience.stackexchange.com/questions/25029/custom-loss-function-with-additional-parameter-in-keras

def penalized_loss(noise):
    def loss(y_true, y_pred):
        return K.mean(K.square(y_pred - y_true) - K.square(y_true - noise), axis=-1)
    return loss

上述方法在我训练模型时有效.但是，一旦模型经过训练，我就很难加载模型.当我尝试在 load_model 中使用 custom_objects 参数时，如下所示

The above method works when I am training the model. However, once the model is trained I am having difficulty in loading the model. When I try to use the custom_objects parameter in load_model like below

model = load_model(modelFile, custom_objects={'penalized_loss': penalized_loss} )

它抱怨 ValueError: Unknown loss function:loss

有什么方法可以将损失函数作为 custom_objects 中的自定义损失之一传入?据我所知，内部函数在 load_model 调用期间不在命名空间中.有没有更简单的方法来加载模型或使用带有附加参数的自定义损失

Is there any way to pass in the loss function as one of the custom losses in custom_objects ? From what I can gather, the inner function is not in the namespace during load_model call. Is there any easier way to load the model or use a custom loss with additional parameters

推荐答案

是的，有！custom_objects 期望您用作损失函数的确切函数(在您的情况下是内部函数):

Yes, there is! custom_objects expects the exact function that you used as loss function (the inner one in your case):

model = load_model(modelFile, custom_objects={ 'loss': penalized_loss(noise) })

不幸的是，keras 不会将噪声值存储在模型中，因此您需要手动将其提供给 load_model 函数.

Unfortunately keras won't store in the model the value of noise, so you need to feed it to the load_model function manually.

这篇关于加载具有自定义损失 + keras 的模型的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！