(Keras)——Keras中自定义目标函数(损失函数)

在做kaggle项目时，看到一个人设计了一个unet，使用自定义的iou作为损失函数，才想起来原来可以自己设计损失函数…
为了实现自己的目标函数，自然想到先看下Keras中的目标函数是定义的，查下源码发现在/usr/local/lib/python3.5/dist-packages/keras中(我的系统是ubuntu16.04，使用系统自带的python3.5)，Keras已经定义了一系列的目标函数。
当然是要先查看下Keras源码了…

"""Built-in loss functions.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import six
from . import backend as K
from .utils.generic_utils import deserialize_keras_object
from .utils.generic_utils import serialize_keras_object


def mean_squared_error(y_true, y_pred):
    return K.mean(K.square(y_pred - y_true), axis=-1)


def mean_absolute_error(y_true, y_pred):
    return K.mean(K.abs(y_pred - y_true), axis=-1)


def mean_absolute_percentage_error(y_true, y_pred):
    diff = K.abs((y_true - y_pred) / K.clip(K.abs(y_true),
                                            K.epsilon(),
                                            None))
    return 100. * K.mean(diff, axis=-1)


def mean_squared_logarithmic_error(y_true, y_pred):
    first_log = K.log(K.clip(y_pred, K.epsilon(), None) + 1.)
    second_log = K.log(K.clip(y_true, K.epsilon(), None) + 1.)
    return K.mean(K.square(first_log - second_log), axis=-1)


def squared_hinge(y_true, y_pred):
    return K.mean(K.square(K.maximum(1. - y_true * y_pred, 0.)), axis=-1)


def hinge(y_true, y_pred):
    return K.mean(K.maximum(1. - y_true * y_pred, 0.), axis=-1)


def categorical_hinge(y_true, y_pred):
    pos = K.sum(y_true * y_pred, axis=-1)
    neg = K.max((1. - y_true) * y_pred, axis=-1)
    return K.maximum(0., neg - pos + 1.)


def logcosh(y_true, y_pred):
    """Logarithm of the hyperbolic cosine of the prediction error.

    `log(cosh(x))` is approximately equal to `(x ** 2) / 2` for small `x` and
    to `abs(x) - log(2)` for large `x`. This means that 'logcosh' works mostly
    like the mean squared error, but will not be so strongly affected by the
    occasional wildly incorrect prediction.

    # Arguments
        y_true: tensor of true targets.
        y_pred: tensor of predicted targets.

    # Returns
        Tensor with one scalar loss entry per sample.
    """
    def _logcosh(x):
        return x + K.softplus(-2. * x) - K.log(2.)
    return K.mean(_logcosh(y_pred - y_true), axis=-1)


def categorical_crossentropy(y_true, y_pred):
    return K.categorical_crossentropy(y_true, y_pred)


def sparse_categorical_crossentropy(y_true, y_pred):
    return K.sparse_categorical_crossentropy(y_true, y_pred)


def binary_crossentropy(y_true, y_pred):
    return K.mean(K.binary_crossentropy(y_true, y_pred), axis=-1)


def kullback_leibler_divergence(y_true, y_pred):
    y_true = K.clip(y_true, K.epsilon(), 1)
    y_pred = K.clip(y_pred, K.epsilon(), 1)
    return K.sum(y_true * K.log(y_true / y_pred), axis=-1)


def poisson(y_true, y_pred):
    return K.mean(y_pred - y_true * K.log(y_pred + K.epsilon()), axis=-1)


def cosine_proximity(y_true, y_pred):
    y_true = K.l2_normalize(y_true, axis=-1)
    y_pred = K.l2_normalize(y_pred, axis=-1)
    return -K.sum(y_true * y_pred, axis=-1)


# Aliases.

mse = MSE = mean_squared_error
mae = MAE = mean_absolute_error
mape = MAPE = mean_absolute_percentage_error
msle = MSLE = mean_squared_logarithmic_error
kld = KLD = kullback_leibler_divergence
cosine = cosine_proximity


def serialize(loss):
    return serialize_keras_object(loss)


def deserialize(name, custom_objects=None):
    return deserialize_keras_object(name,
                                    module_objects=globals(),
                                    custom_objects=custom_objects,
                                    printable_module_name='loss function')


def get(identifier):
    """Get the `identifier` loss function.

    # Arguments
        identifier: None or str, name of the function.

    # Returns
        The loss function or None if `identifier` is None.

    # Raises
        ValueError if unknown identifier.
    """
    if identifier is None:
        return None
    if isinstance(identifier, six.string_types):
        identifier = str(identifier)
        return deserialize(identifier)
    if isinstance(identifier, dict):
        return deserialize(identifier)
    elif callable(identifier):
        return identifier
    else:
        raise ValueError('Could not interpret '
                         'loss function identifier:', identifier)

看到源码后，事情就简单多了

首先定义损失函数IoU

## intersection over union
def IoU(y_true, y_pred, eps=1e-6):
    if np.max(y_true) == 0.0:
        return IoU(1-y_true, 1-y_pred) ## empty image; calc IoU of zeros
    intersection = K.sum(y_true * y_pred, axis=[1,2,3])
    union = K.sum(y_true, axis=[1,2,3]) + K.sum(y_pred, axis=[1,2,3]) - intersection
    return -K.mean( (intersection + eps) / (union + eps), axis=0)

然后执行编译

seg_model.compile(optimizer=Adam(1e-3, decay=1e-6), loss=IoU, metrics=['binary_accuracy'])

就是这么简单…

(Keras)——Keras中自定义目标函数(损失函数)

猜你喜欢