如何在Keras中为张量创建布尔蒙版? [英] How do you create a boolean mask for a tensor in Keras?

问题描述

我正在建立一个自定义指标，以在训练过程中测量多类数据集中一个类的准确性.我在选择课程时遇到了麻烦.

目标是一个热点(例如，类0的标签为[1 0 0 0 0]):

from keras import backend as K

def single_class_accuracy(y_true, y_pred):
    idx = bool(y_true[:, 0])              # boolean mask for class 0 
    class_preds = y_pred[idx]
    class_true = y_true[idx]
    class_acc = K.mean(K.equal(K.argmax(class_true, axis=-1), K.argmax(class_preds, axis=-1)))  # multi-class accuracy  
    return class_acc

麻烦的是，我们必须使用Keras函数索引张量.如何为张量创建布尔蒙版?

解决方案

请注意，当谈到一个类别的准确性时，一个可能指以下(不等同)以下两种金额之一: /p>

• 召回，对于 C 类，是标有 C 类且预计具有类的示例的比率> C .
• 精度，对于 C 类，是预测为 C 类的示例的比例，这些示例实际上被标记为类 C .

除了执行复杂的索引编制之外，您还可以仅依靠掩码进行计算.假设我们在这里谈论精度(更改召回率是微不足道的).

from keras import backend as K

INTERESTING_CLASS_ID = 0  # Choose the class of interest

def single_class_accuracy(y_true, y_pred):
    class_id_true = K.argmax(y_true, axis=-1)
    class_id_preds = K.argmax(y_pred, axis=-1)
    # Replace class_id_preds with class_id_true for recall here
    accuracy_mask = K.cast(K.equal(class_id_preds, INTERESTING_CLASS_ID), 'int32')
    class_acc_tensor = K.cast(K.equal(class_id_true, class_id_preds), 'int32') * accuracy_mask
    class_acc = K.sum(class_acc_tensor) / K.maximum(K.sum(accuracy_mask), 1)
    return class_acc

如果您想更加灵活，还可以将感兴趣的类别参数化:

from keras import backend as K

def single_class_accuracy(interesting_class_id):
    def fn(y_true, y_pred):
        class_id_true = K.argmax(y_true, axis=-1)
        class_id_preds = K.argmax(y_pred, axis=-1)
        # Replace class_id_preds with class_id_true for recall here
        accuracy_mask = K.cast(K.equal(class_id_preds, interesting_class_id), 'int32')
        class_acc_tensor = K.cast(K.equal(class_id_true, class_id_preds), 'int32') * accuracy_mask
        class_acc = K.sum(class_acc_tensor) / K.maximum(K.sum(accuracy_mask), 1)
        return class_acc
    return fn

并将其用作:

model.compile(..., metrics=[single_class_accuracy(INTERESTING_CLASS_ID)])

I am building a custom metric to measure the accuracy of one class in my multi-class dataset during training. I am having trouble selecting the class.

The targets are one hot (e.g: the class 0 label is [1 0 0 0 0]):

from keras import backend as K

def single_class_accuracy(y_true, y_pred):
    idx = bool(y_true[:, 0])              # boolean mask for class 0 
    class_preds = y_pred[idx]
    class_true = y_true[idx]
    class_acc = K.mean(K.equal(K.argmax(class_true, axis=-1), K.argmax(class_preds, axis=-1)))  # multi-class accuracy  
    return class_acc

The trouble is, we have to use Keras functions to index tensors. How do you create a boolean mask for a tensor?

解决方案

Note that when talking about the accuracy of one class one may refer to either of the following (not equivalent) two amounts:

• The recall, which, for class C, is the ratio of examples labelled with class C that are predicted to have class C.
• The precision, which, for class C, is the ratio of examples predicted to be of class C that are in fact labelled with class C.

Instead of doing complex indexing, you can just rely on masking for you computation. Assuming we are talking about precision here (changing to recall would be trivial).

from keras import backend as K

INTERESTING_CLASS_ID = 0  # Choose the class of interest

def single_class_accuracy(y_true, y_pred):
    class_id_true = K.argmax(y_true, axis=-1)
    class_id_preds = K.argmax(y_pred, axis=-1)
    # Replace class_id_preds with class_id_true for recall here
    accuracy_mask = K.cast(K.equal(class_id_preds, INTERESTING_CLASS_ID), 'int32')
    class_acc_tensor = K.cast(K.equal(class_id_true, class_id_preds), 'int32') * accuracy_mask
    class_acc = K.sum(class_acc_tensor) / K.maximum(K.sum(accuracy_mask), 1)
    return class_acc

If you want to be more flexible, you can also have the class of interest parametrised:

from keras import backend as K

def single_class_accuracy(interesting_class_id):
    def fn(y_true, y_pred):
        class_id_true = K.argmax(y_true, axis=-1)
        class_id_preds = K.argmax(y_pred, axis=-1)
        # Replace class_id_preds with class_id_true for recall here
        accuracy_mask = K.cast(K.equal(class_id_preds, interesting_class_id), 'int32')
        class_acc_tensor = K.cast(K.equal(class_id_true, class_id_preds), 'int32') * accuracy_mask
        class_acc = K.sum(class_acc_tensor) / K.maximum(K.sum(accuracy_mask), 1)
        return class_acc
    return fn

And the use it as:

model.compile(..., metrics=[single_class_accuracy(INTERESTING_CLASS_ID)])

这篇关于如何在Keras中为张量创建布尔蒙版?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！