1

我有一个使用一些张量流函数的函数。我在 Theano 中需要这个功能，因为在平台上我想使用这个代码，只有安装了 Theano 而不是 tensorflow。我主要使用 Keras，所以 tensorflow 对我来说非常神秘。该函数如下所示：

class WeightedBinaryCrossEntropy(object):

    def __init__(self, pos_ratio):
        neg_ratio = 1. - pos_ratio
        self.pos_ratio = tf.constant(pos_ratio, tf.float32)
        self.weights = tf.constant(neg_ratio / pos_ratio, tf.float32)
        self.__name__ = "weighted_binary_crossentropy({0})".format(pos_ratio)

    def __call__(self, y_true, y_pred):
        return self.weighted_binary_crossentropy(y_true, y_pred)

    def weighted_binary_crossentropy(self, y_true, y_pred):
        # Transform to logits
        epsilon = tf.convert_to_tensor(K.common._EPSILON, y_pred.dtype.base_dtype)
        y_pred = tf.clip_by_value(y_pred, epsilon, 1 - epsilon)
        y_pred = tf.log(y_pred / (1 - y_pred))

        cost = tf.nn.weighted_cross_entropy_with_logits(y_true, y_pred, self.weights)
        return K.mean(cost * self.pos_ratio, axis=-1)

model.compile(loss=WeightedBinaryCrossEntropy(0.05), optimizer=optimizer, metrics=['accuracy'])

无法在平台上安装 TensorFlow。我从这里得到了代码https://github.com/fchollet/keras/issues/2115

那么 Theano 中是否有与 Tensorflow 中的函数类似的函数？

4

1 回答 1

3

也许你应该只使用 keras 并拥有一个可移植的模型：
（Keras 功能：https ://keras.io/backend/ ）

class WeightedBinaryCrossEntropy(object):

    def __init__(self, pos_ratio):
        neg_ratio = 1. - pos_ratio
        self.pos_ratio = K.constant([pos_ratio])
        self.weights = K.constant([neg_ratio / pos_ratio])
        self.__name__ = "weighted_binary_crossentropy({0})".format(pos_ratio)

    def __call__(self, y_true, y_pred):
        return self.weighted_binary_crossentropy(y_true, y_pred)

    def weighted_binary_crossentropy(self, y_true, y_pred):
        # Transform to logits
        epsilon = K.epsilon()
        y_pred = K.clip(y_pred, epsilon, 1 - epsilon)
        y_pred = K.log(y_pred / (1 - y_pred))

        #for the crossentropy, you can maybe (make sure, please) 
        #use K.binary_crossentropy and multiply the weights later
        cost = self.approach1(y_true,y_pred)

        #or you could simulate the same formula as in tensorflow: 
        #https://www.tensorflow.org/api_docs/python/tf/nn/weighted_cross_entropy_with_logits
        cost = self.approach2(y_true,y_pred)

        return K.mean(cost * self.pos_ratio, axis=-1)

    #I use a similar thing in my codes, but I'm not sure my weights are calculated the same way you do
    def approach1(self,y_true,y_pred):

        weights = (y_true * self.weights) + 1 #weights applied only to positive values
        return K.binary_crossentropy(y_true, y_pred,from_logits=True)*weights

    #seems more trustable, since it's exactly the tensorflow formula
    def approach2(self,y_true,y_pred):

        posPart = y_true * (-K.log(K.sigmoid(y_pred))) * self.weights
        negPart = (1-y_true)*(-K.log(1 - K.sigmoid(y_pred)))

        return posPart + negPart            


model.compile(loss=WeightedBinaryCrossEntropy(0.05), optimizer=optimizer, metrics=['accuracy'])
于 2017-10-19T12:32:16.610 回答