Question

我目前正在尝试使用MobileNetV2的前50层。因此，我想提取这些图层并创建一个新模型。

我以为我可以调用每个层，但是“ block_2_add”层会导致错误，我不明白为什么。

import tensorflow as tf
from keras.models import Model

mobile_net=tf.keras.applications.mobilenet_v2.MobileNetV2(input_shape=(224,224,3), alpha=0.5, include_top=False, weights='imagenet')


inputs = Input(shape=(224, 224, 3))
x=mobile_net.layers[1](inputs)
for layer in mobile_net.layers[2:50]:
  x=layer(x)




{'name': 'block_2_add', 'trainable': True, 'dtype': 'float32'}
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-77-5873b9344fa3> in <module>()
      3 for layer in mobile_net.layers[2:50]:
      4   print(layer.get_config())
----> 5   x=layer(x)
      6 
      7 for layer in mobile_net.layers[:50]:

1 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/layers/merge.py in call(self, inputs)
    119   def call(self, inputs):
    120     if not isinstance(inputs, list):
--> 121       raise ValueError('A merge layer should be called on a list of inputs.')
    122     if self._reshape_required:
    123       reshaped_inputs = []

ValueError: A merge layer should be called on a list of inputs.

Answer 1

我的猜测是MobileNetV2不是顺序模型，即层图不是线性的。如果您只需要模型的输出而不是任何中间层的输出，我认为下面的代码就可以完成这项工作（即使您似乎想在输出前计算最后一层，结果仍然应该是您想要的）：

import tensorflow as tf
from keras.models import Model

mobile_net=tf.keras.applications.mobilenet_v2.MobileNetV2(input_shape=(224,224,3), alpha=0.5, include_top=False, weights='imagenet')


inputs = Input(shape=(224, 224, 3))
output = mobile_net(inputs)

Answer 2

我可能会迟到，但我想下面的代码会为你做的

pre_trained_model = MobileNetV2(input_shape = (256, 256, 3), 
                            include_top = False, 
                            weights = "imagenet" )
last_layer = pre_trained_model.get_layer('block_15_project_BN')
layer.output
input_l = pre_trained_model.input
base_model1 = tf.keras.Model(input_l, last_output
                         )

ValueError：应在输入列表上调用合并层。 Tensorflow Keras

2 个答案: