如何从Keras中的自定义损失函数获得结果? [英] How to get results from custom loss function in Keras?

问题描述

我想在Python中实现自定义损失函数，它应该像下面的伪代码一样工作:

I want to implement a custom loss function in Python and It should work like this pseudocode:

aux = | Real - Prediction | / Prediction
errors = []
if aux <= 0.1:
 errors.append(0)
elif aux > 0.1 & <= 0.15:
 errors.append(5/3)
elif aux > 0.15 & <= 0.2:
 errors.append(5)
else:
 errors.append(2000)
return sum(errors)

我开始像这样定义指标:

I started to define the metric like this:

def custom_metric(y_true,y_pred):
    # y_true:
    res = K.abs((y_true-y_pred) / y_pred, axis = 1)
    ....

但是我不知道如何获取 if 和 else 的res值.我也想知道什么必须返回该函数.

But I do not know how to get the value of the res for the if and else. Also I want to know what have to return the function.

谢谢

推荐答案

我还想知道必须返回什么函数.

Also I want to know what have to return the function.

自定义指标可以在编译步骤中传递.

Custom metrics can be passed at the compilation step.

该函数需要以(y_true, y_pred)作为参数并返回单个tensor值.

The function would need to take (y_true, y_pred) as arguments and return a single tensor value.

但是我不知道如何获取if和else的res值.

But I do not know how to get the value of the res for the if and else.

您可以从result_metric函数返回result.

def custom_metric(y_true,y_pred):
     result = K.abs((y_true-y_pred) / y_pred, axis = 1)
     return result

第二步是使用keras回调函数来查找错误的总和.

The second step is to use a keras callback function in order to find the sum of the errors.

可以定义回调并将其传递给fit方法.

The callback can be defined and passed to the fit method.

history = CustomLossHistory()
model.fit(callbacks = [history])

最后一步是创建CustomLossHistory类，以查找预期的错误列表中的sum.

The last step is to create the the CustomLossHistory class in order to find out the sum of your expecting errors list.

CustomLossHistory将继承keras.callbacks.Callback的一些默认方法.

CustomLossHistory will inherit some default methods from keras.callbacks.Callback.

• on_epoch_begin :在每个纪元开始时调用.
• on_epoch_end :在每个纪元结束时调用.
• on_batch_begin :在每批开始时调用.
• on_batch_end :在每个批次结束时调用.
• on_train_begin :在模型训练开始时调用.
• on_train_end :在模型训练结束时调用.

• on_epoch_begin: called at the beginning of every epoch.
• on_epoch_end: called at the end of every epoch.
• on_batch_begin: called at the beginning of every batch.
• on_batch_end: called at the end of every batch.
• on_train_begin: called at the beginning of model training.
• on_train_end: called at the end of model training.

您可以在 Keras文档

但是在这个示例中，我们只需要on_train_begin和on_batch_end方法.

But for this example we only need on_train_begin and on_batch_end methods.

实施

class LossHistory(keras.callbacks.Callback):
    def on_train_begin(self, logs={}):
        self.errors= []

    def on_batch_end(self, batch, logs={}):
         loss = logs.get('loss')
         self.errors.append(self.loss_mapper(loss))

    def loss_mapper(self, loss):
         if loss <= 0.1:
             return 0
         elif loss > 0.1 & loss <= 0.15:
             return 5/3
         elif loss > 0.15 & loss <= 0.2:
             return 5
         else:
             return 2000

训练好模型后，您可以使用以下语句访问错误.

After your model is trained you can access your errors using following statement.

errors = history.errors

这篇关于如何从Keras中的自定义损失函数获得结果?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！