是否可以在 Keras/TensorFlow 中提取部分多输入模型？

Question

我有这个多输入网络：

def build_model():
  inputRGB = tf.keras.Input(shape=(128,128,3), name='train_ds')
  inputFixed = tf.keras.Input(shape=(128,128,3), name='fixed_ds')
  inputDinamic = tf.keras.Input(shape=(128,128,3), name='dinamic_ds')

    # rete per Immagini RGB
  rgb = models.Sequential()  
  rgb = layers.Conv2D(32, (5, 5), padding='SAME')(inputRGB)
  rgb = layers.PReLU()(rgb)
  rgb = layers.MaxPooling2D((2, 2))(rgb)
  rgb = layers.BatchNormalization()(rgb)
  rgb = layers.Conv2D(64, (3, 3))(rgb)
  rgb = layers.PReLU()(rgb)
  rgb = layers.Conv2D(64, (3, 3))(rgb)
  rgb = layers.PReLU()(rgb)
  rgb = layers.Conv2D(64, (3, 3))(rgb)
  rgb = layers.PReLU()(rgb)
  rgb = layers.Dropout(0.5)(rgb)
  rgb = layers.GlobalAvgPool2D()(rgb)
  rgb = Model(inputs = inputRGB, outputs=rgb)

    # rete per Density Map con "Pallini"
  fixed = models.Sequential()
  fixed = layers.Conv2D(32, (5, 5), padding='SAME')(inputFixed)
  fixed = layers.PReLU()(fixed)
  fixed = layers.MaxPooling2D((2, 2))(fixed)
  fixed = layers.BatchNormalization()(fixed)
  fixed = layers.Conv2D(64, (3, 3))(fixed)
  fixed = layers.PReLU()(fixed)
  fixed = layers.Conv2D(64, (3, 3))(fixed)
  fixed = layers.PReLU()(fixed)
  fixed = layers.Conv2D(64, (3, 3))(fixed)
  fixed = layers.PReLU()(fixed)
  fixed = layers.Dropout(0.5)(fixed)
  fixed = layers.GlobalAvgPool2D()(fixed)
  fixed = Model(inputs = inputFixed, outputs=fixed)

    # rete per Density map per "assembramenti"
  dinamic = models.Sequential()  
  dinamic = layers.Conv2D(32, (5, 5), padding='SAME')(inputDinamic)
  dinamic = layers.PReLU()(dinamic)
  dinamic = layers.MaxPooling2D((2, 2))(dinamic)
  dinamic = layers.BatchNormalization()(dinamic)
  dinamic = layers.Conv2D(64, (3, 3))(dinamic)
  dinamic = layers.PReLU()(dinamic)
  dinamic = layers.Conv2D(64, (3, 3))(dinamic)
  dinamic = layers.PReLU()(dinamic)
  dinamic = layers.Conv2D(64, (3, 3))(dinamic)
  dinamic = layers.PReLU()(dinamic)
  dinamic = layers.Dropout(0.5)(dinamic)
  dinamic = layers.GlobalAvgPool2D()(dinamic)
  dinamic = Model(inputs = inputDinamic, outputs=dinamic)

  concat = layers.concatenate([rgb.output, fixed.output, dinamic.output])  # merge the outputs of the two models
  k = layers.Dense(1)(concat)

  modelFinal = Model(inputs={'train_ds':inputRGB, 'fixed_ds':inputFixed, 'dinamic_ds':inputDinamic}, outputs=[k])

  opt = tf.keras.optimizers.Adam(learning_rate=0.001, amsgrad=False)


  modelFinal.compile(optimizer=opt , loss='mae', metrics=['mae'])
  return modelFinal

我想从我保存并重新加载的最佳模型中提取以下代码行：

best_model = tf.keras.models.load_model(checkpoint_path + 'regression_count_128.30-1.11.hdf5')

只是前面展示的多输入神经网络的第一部分。具体来说，我想提取将 RGB 图像作为输入的部分，以便仅在 RGB 测试图像上测试模型（使用 3 种不同类型的图像训练）。

Answer 1

使用输入层的名称（即'train_ds'）和RGB部分的输出层名称（你没有命名，但你可以使用best_model.summary()找到它;它从 'global_average_pooling2d') 开始构建一个新模型，如下所示：

rgb_model = Model(
      best_model.get_layer('train_ds').output,
      best_model.get_layer(name_of_rgb_output_layer).output
)

旁注： ... = model.Sequential() 行是多余的，可以删除，因为您正在使用 keras 的功能 API 来定义模型。

是否可以在 Keras/TensorFlow 中提取部分多输入模型？

Is it possible to extract part of a multi-input model in Keras/TensorFlow?

python

neural-network

keras

tensorflow

tf.keras