Tensorflow 创建卷积神经网络时出现奇怪错误

我想在keras中创建卷积神经网络模型，首先我已经导入了所有必要的库，就像这样

from tensorflow.keras.layers import Flatten
from tensorflow.keras.layers import Conv2D
from tensorflow.keras.layers import MaxPooling2D

比我尝试过的模式要好

model =Sequential()
model.add(Conv2D(filters=32,kernel_size=(5,5),padding='valid',input_shape=(1,28,28),activation='relu',data_format='channels_first'))
model.add(MaxPooling2D(2,2, dim_ordering='tf'))
moodel.add(Dropout(0.2))
model.add(Flattenn())
model.add(Dense(128,activation='relu'))
model.add(Dense(num_classes,activation='softmax'))
model.compile(loss='categorical_crossentropy' , optimizer='adam' , metrics=['accuracy' ])

但我有以下错误：

TypeError: The added layer must be an instance of class Layer. Found: <tensorflow.python.keras.layers.convolutional.Conv2D object at 0x7faaefc57438>

TypeError:添加的层必须是类层的实例。发现：

你能帮我纠正这个错误吗

moodel.add(Dropout(0.2))

打字错误-

moodel

->

model

model.add(Flattenn())

打字错误-

Flatten

->

Flatten

您应该使用

Convolution2D

而不是

Conv2D

导入

from tensorflow.keras.layers import Convolution2D

model = Sequential()
model.add(Convolution2D(filters=32,...

打字错误-

moodel

->

model

model.add(Flattenn())

打字错误-

Flatten

->

Flatten

您应该使用

Convolution2D

而不是

Conv2D

导入

from tensorflow.keras.layers import Convolution2D

model = Sequential()
model.add(Convolution2D(filters=32,...

---

我做过这样的导入：从tensorflow.keras.layers导入激活，退出，密集，Conv2D，展平，退出，MaxPoolig2D，从tensorflow.keras导入批量标准化。keras导入顺序我修复了错误谢谢，这意味着卷积2D是最新的一个正确的我做过这样的导入：从tensorflow.keras.layers导入激活，Dropout，Dense，Conv2D，Flatte，Dropout，MaxPoolig2D，来自tensorflow.keras的BatchNormalization导入Sequentiali修复了错误，谢谢，这意味着卷积2D是最新的，对吗