Question

我想构建一个自定义Keras层，保留k个顶部激活值。我目前正在这样做（并且工作正常）：

def max_topk_pool(x,k):
    import tensorflow as tf
    k_max =  tf.nn.top_k(x,k=k,sorted=True,name=None)
    return  k_max

def KMax(k):
    return Lambda(max_topk_pool,
                  arguments={'k':k},
                  output_shape=lambda x: (None, k))

您是否知道是否可以按照Keras在https://keras.io/layers/writing-your-own-keras-layers/中展示的方式来构建自定义Layer类“ KMax”

from keras import backend as K
from keras.layers import Layer

class MyLayer(Layer):

def __init__(self, output_dim, **kwargs):
    self.output_dim = output_dim
    super(MyLayer, self).__init__(**kwargs)

def build(self, input_shape):
    # Create a trainable weight variable for this layer.
    self.kernel = self.add_weight(name='kernel', 
                                  shape=(input_shape[1], self.output_dim),
                                  initializer='uniform',
                                  trainable=True)
    super(MyLayer, self).build(input_shape)  # Be sure to call this at the end

def call(self, x):
    return K.dot(x, self.kernel)

def compute_output_shape(self, input_shape):
    return (input_shape[0], self.output_dim)

我想要这样的东西：

from keras import backend as K
from keras.layers import Layer

class KMax(Layer):

def __init__(self, output_dim, **kwargs):
    self.K = K
    super(MyLayer, self).__init__(**kwargs)

def build(self, input_shape):
    <... Lambda here ?>

def compute_output_shape(self, input_shape):
    return (input_shape[0], self.K)

非常感谢您！

Answer 1

这里是您所需要的（基于https://github.com/keras-team/keras/issues/373）：

g2: 8    pointer size
g2: 280  10 * 7 * int size

使用Lambda创建自定义Keras Layer对象

1 个答案: