Python 在Lambda层中使用VGG preprocess_输入以及Dense和KERAS.backend.clear_session（）时出现KERAS错误

我需要在一个循环中创建几个模型（因此我

需要使用keras.backend.clear_session（）

为每个迭代清理环境），但是，如果模型包含

Lambda

和

vgg16.preprocess_input

和稠密层，在我第二次创建模型之后，我得到

ValueError:Tensor（“预处理/Const:0”，shape=（3，），dtype=float32）必须来自与Tensor（“预处理/1/跨步切片：0”，shape=（？，3），dtype=float32）相同的图形。

复制错误的代码：

# making the model
from keras.layers import Dense, Reshape, Lambda
from keras import Sequential
f = keras.applications.vgg16.preprocess_input
d_l = Dense(3, activation='linear', input_shape=(3,), name='MYDENSE')

p_l = Lambda(f,name='PREPROCESS')

model_mod = Sequential()
model_mod.add(d_l)
model_mod.add(p_l)
model_mod.summary()
model_mod.build()
# clean the environment
keras.backend.clear_session()
# making again the same model
f = keras.applications.vgg16.preprocess_input
d_l = Dense(3, activation='linear', input_shape=(3,), name='MYDENSE')
p_l = Lambda(f,name='PREPROCESS')
model_mod = Sequential()
model_mod.add(d_l)
model_mod.add(p_l)

---

keras版本：“2.2.4”

以下代码适用于Tensorflow

# making the model
import tensorflow as tf
from keras.layers import Dense, Reshape, Lambda
from keras import Sequential
f = tf.keras.applications.vgg16.preprocess_input
d_l = Dense(3, activation='linear', input_shape=(3,), name='MYDENSE')

p_l = Lambda(f,name='PREPROCESS')

model_mod = Sequential()
model_mod.add(d_l)
model_mod.add(p_l)
model_mod.summary()
model_mod.build()
# clean the environment
tf.keras.backend.clear_session()
# making again the same model
f = tf.keras.applications.vgg16.preprocess_input
d_l = Dense(3, activation='linear', input_shape=(3,), name='MYDENSE')
p_l = Lambda(f,name='PREPROCESS')
model_mod = Sequential()
model_mod.add(d_l)
model_mod.add(p_l)

输出

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
MYDENSE (Dense)              (None, 3)                 12        
_________________________________________________________________
PREPROCESS (Lambda)          (None, 3)                 0         
=================================================================
Total params: 12
Trainable params: 12
Non-trainable params: 0