ValueError: Could not interpret optimizer identifier: ＜keras.optimizers.optimizer

本文链接：https://blog.csdn.net/qq_36783848/article/details/132794477

Tensorflow由2.3.0换成2.10.0，之前可运行的代码报错如下：

Tensorflow 2.10.0 ValueError: Could not interpret optimizer identifier: <keras.optimizers.optimizer_v2.nadam.Nadam object at 0x000002822FE46B50>

于是将：

from tensorflow.python.keras import backend as K
from tensorflow.python.keras.layers import Input
from tensorflow.python.keras.layers import Conv2D, Reshape
from tensorflow.python.keras.layers import Concatenate
from tensorflow.python.keras.layers import Multiply, GlobalAveragePooling2D, MaxPooling2D
from tensorflow.python.keras.models import Model
from tensorflow.python.keras import regularizers

改为以下，即可运行

from tensorflow.keras import backend as K
from tensorflow.keras.layers import Input
from tensorflow.keras.layers import Conv2D, Reshape
from tensorflow.keras.layers import Concatenate
from tensorflow.keras.layers import Multiply, GlobalAveragePooling2D, MaxPooling2D
from tensorflow.keras.models import Model
from tensorflow.keras import regularizers