Python 如何最大限度地激活TensorFlow DeepDream中的层？

基本上我是在学习教程，但是 我正在尝试从下载的pb文件加载inception v5：

model_fn = 'tensorflow_inception_graph.pb'

graph = tf.Graph()
sess = tf.compat.v1.InteractiveSession(graph=graph)
with tf.compat.v1.gfile.FastGFile(model_fn, 'rb') as f:
    graph_def = tf.compat.v1.GraphDef()
    graph_def.ParseFromString(f.read())

t_input = tf.compat.v1.placeholder(np.float32, name='input')
imagenet_mean = 117.0 
t_preprocessed = tf.expand_dims(t_input-imagenet_mean, 0)

op = sess.graph.get_operations()

tf.import_graph_def(graph_def, {'input': t_preprocessed})

# Maximize the activations of these layers
names = ['mixed4c', 'mixed5']
layers = [tf.keras.Model.get_layer(name).output for name in names]

上面的代码给了我一个错误：

Traceback (most recent call last):
File "main.py", line 52, in <module>
layers = [tf.keras.Model.get_layer(name).output for name in names]
File "main.py", line 52, in <listcomp>
layers = [tf.keras.Model.get_layer(name).output for name in names]
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site- 
packages/tensorflow/python/keras/engine/training.py", line 2399, in get_layer
raise ValueError('Provide either a layer name or layer index.')
ValueError: Provide either a layer name or layer index. 

回溯（最近一次呼叫最后一次）：
文件“main.py”，第52行，在
layers=[tf.keras.Model.get_layer（name）.name中name的输出]
文件“main.py”，第52行，在
layers=[tf.keras.Model.get_layer（name）.name中name的输出]
文件“/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-
packages/tensorflow/python/keras/engine/training.py”，第2399行，在get_层
raise VALUERROR（'提供图层名称或图层索引'）
ValueError：提供图层名称或图层索引。