导入错误：无法从'keras.layers.normalization'导入名称'BatchNormalization'

Question

我在执行代码时遇到一个导入问题:

from keras.models import Sequential
from keras.layers.normalization import BatchNormalization

2021-10-06 22:27:14.064885: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2021-10-06 22:27:14.064974: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
Traceback (most recent call last):
File "C:Databreast-cancer-classificationtrain_model.py", line 10, in <module>
from cancernet.cancernet import CancerNet
File "C:Databreast-cancer-classificationcancernetcancernet.py", line 2, in <module>
from keras.layers.normalization import BatchNormalization
ImportError: cannot import name 'BatchNormalization' from 'keras.layers.normalization' (C:UsersCatalinAppDataLocalProgramsPythonPython39libsite-packageskeraslayersnormalization__init__.py)

• Keras版本:2.6.0
• Tensorflow: 2.6.0
Python版本:3.9.7

与

一起安装的库

pip install numpy opencv-python pillow tensorflow keras imutils scikit-learn matplotlib

你有什么想法吗?

库路径

Answer 1

您应该导入BatchNormalization

from tensorflow.keras.layers import BatchNormalization

Answer 2

您对tf.keras使用了过时的导入。现在可以直接从tensorflow.keras.layers导入图层:

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import (
BatchNormalization, SeparableConv2D, MaxPooling2D, Activation, Flatten, Dropout, Dense
)
from tensorflow.keras import backend as K

class CancerNet:
@staticmethod
def build(width, height, depth, classes):
model = Sequential()
shape = (height, width, depth)
channelDim = -1
if K.image_data_format() == "channels_first":
shape = (depth, height, width)
channelDim = 1
model.add(SeparableConv2D(32, (3, 3), padding="same", input_shape=shape))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=channelDim))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(SeparableConv2D(64, (3, 3), padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=channelDim))
model.add(SeparableConv2D(64, (3, 3), padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=channelDim))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(SeparableConv2D(128, (3, 3), padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=channelDim))
model.add(SeparableConv2D(128, (3, 3), padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=channelDim))
model.add(SeparableConv2D(128, (3, 3), padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=channelDim))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(256))
model.add(Activation("relu"))
model.add(BatchNormalization())
model.add(Dropout(0.5))
model.add(Dense(classes))
model.add(Activation("softmax"))
return model
model = CancerNet()

Answer 3

这对我有用:

from tensorflow.python.layers.normalization import BatchNormalization