如何在keras中使用并行卷积层？

2 回答

• 11

  我的方法是创建定义所有并行卷积和拉动操作的其他模型，并将所有并行结果张量连接到单输出张量 . 现在，您可以像顺序层一样在顺序模型中添加此并行模型图 . 这是我的解决方案，希望它能解决您的问题 .

  #variable initialization 
  nb_filters =100
  kernel_size= {}
  kernel_size[0]= [3,3]
  kernel_size[1]= [4,4]
  kernel_size[2]= [5,5]
  input_shape=(32, 32, 3)
  pool_size = (2,2)
  nb_classes =2
  no_parallel_filters = 3
  
  # create seperate model graph for parallel processing with different filter sizes
  # apply 'same' padding so that ll produce o/p tensor of same size for concatination
  # cancat all paralle output
  
  inp = Input(shape=input_shape)
  convs = []
  for k_no in range(len(kernel_size)):
      conv = Convolution2D(nb_filters, kernel_size[k_no][0], kernel_size[k_no][1],
                      border_mode='same',
                           activation='relu',
                      input_shape=input_shape)(inp)
      pool = MaxPooling2D(pool_size=pool_size)(conv)
      convs.append(pool)
  
  if len(kernel_size) > 1:
      out = Merge(mode='concat')(convs)
  else:
      out = convs[0]
  
  conv_model = Model(input=inp, output=out)
  
  # add created model grapg in sequential model
  
  model = Sequential()
  model.add(conv_model)        # add model just like layer
  model.add(Convolution2D(nb_filters, kernel_size[1][0], kernel_size[1][0]))
  model.add(Activation('relu'))
  model.add(MaxPooling2D(pool_size=pool_size))
  model.add(Dropout(0.25))
  model.add(Flatten(input_shape=input_shape))
  model.add(Dense(128))
  model.add(Activation('relu'))
  model.add(Dense(128))
  model.add(Activation('relu'))
  model.add(Dropout(0.5))
  model.add(Dense(nb_classes))
  model.add(Activation('tanh'))
  

  有关更多信息，请参阅类似的问题：Combining the outputs of multiple models into one model

  回复于 2024-04-27T07:06:48+08:00
• 13

  下面是在keras版本2中设计并行卷积和子采样层网络的示例 . 我希望这可以解决您的问题 .

  rows, cols = 100, 15
  def create_convnet(img_path='network_image.png'):
      input_shape = Input(shape=(rows, cols, 1))
  
      tower_1 = Conv2D(20, (100, 5), padding='same', activation='relu')(input_shape)
      tower_1 = MaxPooling2D((1, 11), strides=(1, 1), padding='same')(tower_1)
  
      tower_2 = Conv2D(20, (100, 7), padding='same', activation='relu')(input_shape)
      tower_2 = MaxPooling2D((1, 9), strides=(1, 1), padding='same')(tower_2)
  
      tower_3 = Conv2D(20, (100, 10), padding='same', activation='relu')(input_shape)
      tower_3 = MaxPooling2D((1, 6), strides=(1, 1), padding='same')(tower_3)
  
      merged = keras.layers.concatenate([tower_1, tower_2, tower_3], axis=1)
      merged = Flatten()(merged)
  
      out = Dense(200, activation='relu')(merged)
      out = Dense(num_classes, activation='softmax')(out)
  
      model = Model(input_shape, out)
      plot_model(model, to_file=img_path)
      return model
  

  此网络的图像看起来像
  

  回复于 2024-04-27T07:06:48+08:00