试图在keras中向CNN模型添加输入层

时间:2020-05-03 15:53:02

标签: python tensorflow keras ipython cnn

我试图将输入添加到并行路径cnn中,以形成残留的体系结构,但是我遇到了尺寸不匹配的情况。


from keras import layers, Model
input_shape = (128,128,3) # Change this accordingly
my_input = layers.Input(shape=input_shape) # one input
def parallel_layers(my_input, parallel_id=1):
  x = layers.SeparableConv2D(32, (9, 9), activation='relu', name='conv_1_'+str(parallel_id))(my_input)
  x = layers.MaxPooling2D(2, 2)(x)
  x = layers.SeparableConv2D(64, (9, 9), activation='relu', name='conv_2_'+str(parallel_id))(x)
  x = layers.MaxPooling2D(2, 2)(x)
  x = layers.SeparableConv2D(128, (9, 9), activation='relu', name='conv_3_'+str(parallel_id))(x)
  x = layers.MaxPooling2D(2, 2)(x)
  x = layers.Flatten()(x)
  x = layers.Dropout(0.5)(x)
  x = layers.Dense(512, activation='relu')(x)

  return x

parallel1 = parallel_layers(my_input, 1)
parallel2 = parallel_layers(my_input, 2)

concat = layers.Concatenate()([parallel1, parallel2])
concat=layers.Add()(concat,my_input)
x = layers.Dense(128, activation='relu')(concat)
x = Dense(7, activation='softmax')(x)

final_model = Model(inputs=my_input, outputs=x)

final_model.fit_generator(train_generator, steps_per_epoch = 
    nb_train_samples // batch_size, epochs = epochs, validation_data = validation_generator,
    validation_steps = nb_validation_samples // batch_size) 

我遇到了错误

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-48-163442df0d4c> in <module>()
      1 concat = layers.Concatenate()([parallel1, parallel2])
----> 2 concat=layers.Add()(concat,my_input)
      3 x = layers.Dense(128, activation='relu')(parallel2)
      4 x = Dense(7, activation='softmax')(x)
      5 

TypeError: __call__() takes 2 positional arguments but 3 were given

我正在使用keras 2.1.6版本。请帮助解决此问题 final_model.summary()

2 个答案:

答案 0 :(得分:0)

以这种方式定义您的添加层

concat=layers.Add()([concat,my_input])

答案 1 :(得分:0)

您必须删除以下行:

concat=layers.Add()(concat,my_input)

这没有任何意义。您有一个接受输入的方法,分为两个并行模型。它们(parallel1parallel2)的输出都是长度为512的向量。然后,您可以Concatenate的长度为1024,也可以Add的长度再次为512concat然后经过另外的Dense层。

因此,简而言之,删除以下行:

concat=layers.Add()(concat,my_input)

如果要连接并具有长度为1024的向量,请保留其余代码,否则,如果要添加它们并具有长度为512的向量,请替换以下行:

concat = layers.Concatenate()([parallel1, parallel2])

与此:

concat = layers.Add()([parallel1, parallel2])