Keras之自定义损失(loss)函数用法说明

时间:2021-05-22

在Keras中可以自定义损失函数,在自定义损失函数的过程中需要注意的一点是,损失函数的参数形式,这一点在Keras中是固定的,须如下形式:

def my_loss(y_true, y_pred):# y_true: True labels. TensorFlow/Theano tensor# y_pred: Predictions. TensorFlow/Theano tensor of the same shape as y_true . . . return scalar #返回一个标量值

然后在model.compile中指定即可,如:

model.compile(loss=my_loss, optimizer='sgd')

具体参考Keras官方metrics的定义keras/metrics.py:

"""Built-in metrics."""from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_function import sixfrom . import backend as Kfrom .losses import mean_squared_errorfrom .losses import mean_absolute_errorfrom .losses import mean_absolute_percentage_errorfrom .losses import mean_squared_logarithmic_errorfrom .losses import hingefrom .losses import logcoshfrom .losses import squared_hingefrom .losses import categorical_crossentropyfrom .losses import sparse_categorical_crossentropyfrom .losses import binary_crossentropyfrom .losses import kullback_leibler_divergencefrom .losses import poissonfrom .losses import cosine_proximityfrom .utils.generic_utils import deserialize_keras_objectfrom .utils.generic_utils import serialize_keras_object def binary_accuracy(y_true, y_pred): return K.mean(K.equal(y_true, K.round(y_pred)), axis=-1) def categorical_accuracy(y_true, y_pred): return K.cast(K.equal(K.argmax(y_true, axis=-1), K.argmax(y_pred, axis=-1)), K.floatx()) def sparse_categorical_accuracy(y_true, y_pred): # reshape in case it's in shape (num_samples, 1) instead of (num_samples,) if K.ndim(y_true) == K.ndim(y_pred): y_true = K.squeeze(y_true, -1) # convert dense predictions to labels y_pred_labels = K.argmax(y_pred, axis=-1) y_pred_labels = K.cast(y_pred_labels, K.floatx()) return K.cast(K.equal(y_true, y_pred_labels), K.floatx()) def top_k_categorical_accuracy(y_true, y_pred, k=5): return K.mean(K.in_top_k(y_pred, K.argmax(y_true, axis=-1), k), axis=-1) def sparse_top_k_categorical_accuracy(y_true, y_pred, k=5): # If the shape of y_true is (num_samples, 1), flatten to (num_samples,) return K.mean(K.in_top_k(y_pred, K.cast(K.flatten(y_true), 'int32'), k), axis=-1) # Aliases mse = MSE = mean_squared_errormae = MAE = mean_absolute_errormape = MAPE = mean_absolute_percentage_errormsle = MSLE = mean_squared_logarithmic_errorcosine = cosine_proximity def serialize(metric): return serialize_keras_object(metric) def deserialize(config, custom_objects=None): return deserialize_keras_object(config, module_objects=globals(), custom_objects=custom_objects, printable_module_name='metric function') def get(identifier): if isinstance(identifier, dict): config = {'class_name': str(identifier), 'config': {}} return deserialize(config) elif isinstance(identifier, six.string_types): return deserialize(str(identifier)) elif callable(identifier): return identifier else: raise ValueError('Could not interpret ' 'metric function identifier:', identifier)

以上这篇Keras之自定义损失(loss)函数用法说明就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。

声明:本页内容来源网络,仅供用户参考;我单位不保证亦不表示资料全面及准确无误,也不保证亦不表示这些资料为最新信息,如因任何原因,本网内容或者用户因倚赖本网内容造成任何损失或损害,我单位将不会负任何法律责任。如涉及版权问题,请提交至online#300.cn邮箱联系删除。

相关文章