CNTK没有属性LeakyReLU

时间:2017-10-13 08:26:48

标签: python machine-learning deep-learning cntk

制作这样的CNN模型时:

# function to build model

def create_model(features):
    with C.layers.default_options(init=C.glorot_uniform(), activation=C.LeakyReLU):
            h = features
            h = C.layers.Convolution2D(filter_shape=(5,5), 
                                       num_filters=8, 
                                       strides=(2,2), 
                                       pad=True, name='first_conv')(h)
            h = C.layers.Convolution2D(filter_shape=(5,5), 
                                       num_filters=16, 
                                       strides=(2,2), 
                                       pad=True, name='second_conv')(h)
            r = C.layers.Dense(num_output_classes, activation=None, name='classify')(h)
            return r

# Create the model
z = create_model(x)

# Print the output shapes / parameters of different components
print("Output Shape of the first convolution layer:", z.first_conv.shape)
print("Bias value of the last dense layer:", z.classify.b.value)

我收到错误:

  

AttributeError Traceback(最近一次调用   最后)in()         1#创建模型   ----> 2 z = create_model(x)         3         4#打印不同组件的输出形状/参数         5打印(“第一卷积层的输出形状:”,z.first_conv.shape)

     create_model中的

(功能)         2         3 def create_model(功能):   ----> 4与C.layers.default_options(init = C.glorot_uniform(),activation = C.LeakyReLU):         5小时=特征         6 h = C.layers.Convolution2D(filter_shape =(5,5),

     

AttributeError:模块'cntk'没有属性'LeakyReLU'

我是深度学习的新手,所以我可能会遗漏一些简单的东西。任何帮助表示赞赏。谢谢!

2 个答案:

答案 0 :(得分:3)

尝试C.leaky_relu

>>> C.leaky_relu([[-1, -0.5, 0, 1, 2]]).eval()
array([[-0.01 , -0.005,  0.   ,  1.   ,  2.   ]], dtype=float32)

答案 1 :(得分:1)

将以下行更改为:

使用C.layers.default_options(init = C.glorot_uniform(),激活= C. leaky_relu ):