TypeError: ('关键字参数不理解：', 'mode')

问题描述

暹罗网络

def create_base_network_signet(input_shape):
'''Base Siamese Network'''

seq = Sequential()
seq.add(Conv2D(96,kernel_size=(11,11),activation='relu',name='conv1_1',strides=4,input_shape= input_shape,kernel_initializer='glorot_uniform'))
seq.add(Batchnormalization(epsilon=1e-06,mode=0,axis=1,momentum=0.9))
seq.add(MaxPooling2D((3,3),strides=(2,2)))    
seq.add(ZeroPadding2D((2,2),dim_ordering='tf'))

seq.add(Conv2D(256,kernel_size=(5,5),name='conv2_1',strides=1,2)))
seq.add(Dropout(0.3))# added extra
seq.add(ZeroPadding2D((1,1)))

seq.add(Conv2D(384,kernel_size=(3,name='conv3_1',kernel_initializer='glorot_uniform'))
seq.add(ZeroPadding2D((1,1)))

seq.add(Conv2D(256,name='conv3_2',kernel_initializer='glorot_uniform'))    
seq.add(MaxPooling2D((3,2)))
seq.add(Dropout(0.3))# added extra
seq.add(Flatten(name='flatten'))
seq.add(Dense(1024,W_regularizer=l2(0.0005),kernel_initializer='glorot_uniform'))
seq.add(Dropout(0.5))

seq.add(Dense(128,kernel_initializer='glorot_uniform')) # softmax changed to relu

return seq

错误

    TypeError                                 Traceback (most recent call last)
<ipython-input-68-ffbba8b5172f> in <module>()
      1 # network deFinition
----> 2 base_network = create_base_network_signet(input_shape)
      3 
      4 input_a = Input(shape=(input_shape))
      5 input_b = Input(shape=(input_shape))

4 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/generic_utils.py in validate_kwargs(kwargs,allowed_kwargs,error_message)
    806   for kwarg in kwargs:
    807     if kwarg not in allowed_kwargs:
--> 808       raise TypeError(error_message,kwarg)
    809 
    810 

TypeError: ('Keyword argument not understood:','mode')

我无法解决此错误我应该做哪些更改才能运行代码？它是用于签名验证的siamese网络代码。我正在使用更新的 keras 和 tensorflow

解决方法

暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！

如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@）

keras keras siamese-network