Keras自定义损失功能:访问当前输入模式 [英] Keras custom loss function: Accessing current input pattern

问题描述

在Keras(具有Tensorflow后端)中，当前输入模式可用于我的自定义损失函数吗?

In Keras (with Tensorflow backend), is the current input pattern available to my custom loss function?

当前输入模式定义为用于产生预测的输入向量.例如，考虑以下内容:X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42, shuffle=False).然后，当前输入模式是与y_train相关联的当前X_train向量(在损失函数中称为y_true).

The current input pattern is defined as the input vector used to produce the prediction. For example, consider the following: X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42, shuffle=False). Then the current input pattern is the current X_train vector associated with the y_train (which is termed y_true in the loss function).

在设计自定义损失函数时，我打算优化/最小化一个需要访问当前输入模式而不只是当前预测的值.

When designing a custom loss function, I intend to optimize/minimize a value that requires access to the current input pattern, not just the current prediction.

我已经浏览过 https://github.com /fchollet/keras/blob/master/keras/losses.py

我还查看了"不仅是y_pred，y_true的成本函数?"

我还熟悉前面的示例，以生成自定义的损失函数:

I am also familiar with previous examples to produce a customized loss function:

import keras.backend as K

def customLoss(y_true,y_pred):
    return K.sum(K.log(y_true) - K.log(y_pred))

大概(y_true,y_pred)在其他地方定义.我查看了源代码，但没有成功，我想知道我是否需要自己定义当前的输入模式，或者我的损失函数是否已经可以访问此输入模式.

Presumably (y_true,y_pred) are defined elsewhere. I've taken a look through the source code without success and I'm wondering whether I need to define the current input pattern myself or whether this is already accessible to my loss function.

推荐答案

您可以将loss函数包装为内部函数，并将输入张量传递给它(如将其他参数传递给loss函数时通常这样做).

You can wrap the loss function as a inner function and pass your input tensor to it (as commonly done when passing additional arguments to the loss function).

def custom_loss_wrapper(input_tensor):
    def custom_loss(y_true, y_pred):
        return K.binary_crossentropy(y_true, y_pred) + K.mean(input_tensor)
    return custom_loss

input_tensor = Input(shape=(10,))
hidden = Dense(100, activation='relu')(input_tensor)
out = Dense(1, activation='sigmoid')(hidden)
model = Model(input_tensor, out)
model.compile(loss=custom_loss_wrapper(input_tensor), optimizer='adam')

您可以验证input_tensor和损失值(主要是K.mean(input_tensor)部分)是否会随着将不同的X传递给模型而改变.

You can verify that input_tensor and the loss value (mostly, the K.mean(input_tensor) part) will change as different X is passed to the model.

X = np.random.rand(1000, 10)
y = np.random.randint(2, size=1000)
model.test_on_batch(X, y)  # => 1.1974642

X *= 1000
model.test_on_batch(X, y)  # => 511.15466

这篇关于Keras自定义损失功能:访问当前输入模式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！