问题描述
我的理解是 keras 需要损失函数才能有签名:
def custom_loss(y_true, y_pred):我正在尝试使用 sklearn.metrics.cohen_kappa_score，它需要(y1, y2, 标签=None, weights=None, sample_weight=None)`
如果我按原样使用它:
model.compile(loss=metrics.cohen_kappa_score,优化器='亚当'，指标=['准确度'])那么 weights 将不会被设置.我想将其设置为 quadtratic.有什么可以通过的吗?
在 Keras 中实现参数化自定义损失函数 (cohen_kappa_score) 有两个步骤.由于有满足您需求的实现功能，因此您无需自己实现.但是，根据 TensorFlow 文档，sklearn.metrics.cohen_kappa_score 不支持加权矩阵.因此，我建议使用 TensorFlow 的 cohen_kappa 实现.然而，在 Keras 中使用 TensorFlow 并不是那么容易......根据这个问题，他们使用了control_dependencies 在 Keras 中使用 TensorFlow 指标.举个例子:
将 keras.backend 导入为 Kdef _cohen_kappa(y_true, y_pred, num_classes, weights=None, metrics_collections=None, updates_collections=None, name=None):kappa, update_op = tf.contrib.metrics.cohen_kappa(y_true, y_pred, num_classes, weights, metrics_collections, updates_collections, name)K.get_session().run(tf.local_variables_initializer())使用 tf.control_dependencies([update_op]):kappa = tf.identity(kappa)返回河童由于 Keras 损失函数以 (y_true, y_pred) 作为参数，您需要一个返回另一个函数的包装函数.这是一些代码:
def cohen_kappa_loss(num_classes, weights=None, metrics_collections=None, updates_collections=None, name=None):def cohen_kappa(y_true, y_pred):返回-_cohen_kappa(y_true, y_pred, num_classes, weights, metrics_collections, updates_collections, name)返回 cohen_kappa最后，你可以在 Keras 中使用它:
#获取损失函数并设置参数model_cohen_kappa = cohen_kappa_loss(num_classes=3,weights=weights)#编译模型模型编译(损失=model_cohen_kappa，优化器='亚当'，指标=['准确度'])关于使用 Cohen-Kappa 度量作为损失函数.一般来说，可以使用加权 kappa 作为损失函数.这是一篇论文，使用加权 kappa 作为多类分类的损失函数.>
My understanding is that keras requires loss functions to have the signature:
def custom_loss(y_true, y_pred):
I am trying to use sklearn.metrics.cohen_kappa_score, which takes
(y1, y2, labels=None, weights=None, sample_weight=None)`
If I use it as is:
model.compile(loss=metrics.cohen_kappa_score,
optimizer='adam', metrics=['accuracy'])
Then the weights won't be set. I want to set that to quadtratic. Is there some what to pass this through?
There are two steps in implementing a parameterized custom loss function (cohen_kappa_score) in Keras. Since there are implemented function for your needs, there is no need for you to implement it yourself. However, according to TensorFlow Documentation, sklearn.metrics.cohen_kappa_score does not support weighted matrix.
Therefore, I suggest TensorFlow's implementation of cohen_kappa. However, using TensorFlow in Keras is not that easy...
According to this Question, they used control_dependencies to use a TensorFlow metric in Keras. Here is a example:
import keras.backend as K
def _cohen_kappa(y_true, y_pred, num_classes, weights=None, metrics_collections=None, updates_collections=None, name=None):
kappa, update_op = tf.contrib.metrics.cohen_kappa(y_true, y_pred, num_classes, weights, metrics_collections, updates_collections, name)
K.get_session().run(tf.local_variables_initializer())
with tf.control_dependencies([update_op]):
kappa = tf.identity(kappa)
return kappa
Since Keras loss functions take (y_true, y_pred) as parameters, you need a wrapper function that returns another function. Here is some code:
def cohen_kappa_loss(num_classes, weights=None, metrics_collections=None, updates_collections=None, name=None):
def cohen_kappa(y_true, y_pred):
return -_cohen_kappa(y_true, y_pred, num_classes, weights, metrics_collections, updates_collections, name)
return cohen_kappa
Finally, you can use it as follows in Keras:
# get the loss function and set parameters
model_cohen_kappa = cohen_kappa_loss(num_classes=3,weights=weights)
# compile model
model.compile(loss=model_cohen_kappa,
optimizer='adam', metrics=['accuracy'])
Regarding using the Cohen-Kappa metric as a loss function. In general it is possible to use weighted kappa as a loss function. Here is a paper using weighted kappa as a loss function for multi-class classification.
这篇关于如何在 Keras 中将损失函数指定为二次加权 kappa?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，WP2