带有 keras 的卷积神经网络给出错误，UnboundLocalError：赋值前引用的局部变量 'a'

Question

我在下面写代码，但在下面给出错误"UnboundLocalError:在赋值之前引用了局部变量"a"每次我使用keras.layers.BatchNormalization()时，程序都会给我这个错误。我该怎么办？怎么了？

def make_CNN_model():
model = Sequential()
# input layer transformation (BatchNormalization + Dropout)
model.add(layers.BatchNormalization(name='inputlayer',input_shape=(28,28,1)))
model.add(layers.Dropout(name='Droupout_inputlayer',rates=0.3))
# convolutional layer (Conv2D + MaxPooling2D + Flatten + Dropout)
model.add(layers.Conv2D(filiters=32,activation='relu', name="Convoluationlayer_1",kernal_size=(3,3),border_mode='same'))
model.add(layers.MaxPooling2D(name='MaxPooling_1'))
model.add(layers.Flatten(name="Flaten_1"))
model.add(layers.Dropout(rate=0.3))
# fully connected layer (Dense + BatchNormalization + Activation + Dropout)
model.add(layers.Dense(name="FullyConnectedLayer_1",units=50))
model.add(layers.BatchNormalization())
model.add(layers.Activation('relu'))
model.add(layers.Dropout(rate=0.3))
# output layer (Dense + BatchNormalization + Activation)
model.add(layers.Dense(name = "Outputlayer", units=10))
model.add(layers.BatchNormalization())
model.add(layers.Activation('sigmod'))
return model
model = make_CNN_model()
model.compile(
optimizer='Adam',
loss='categorical_crossentropy',
metrics=['accuracy']
)
summary = model.fit(
X_train, y_train_onehot,
batch_size=5000,
epochs=5,
validation_split=0.2,
verbose=1,
callbacks=[time_summary]
)

Answer 1

我可以看到一些非常明显的拼写错误，比如model.add(layers.Dropout(name='Droupout_inputlayer',rates=0.3))中的"rate"而不是"rate"。

然后，在model.add(layers.Conv2D(filiters=32,activation='relu', name="Convoluationlayer_1",kernal_size=(3,3),border_mode='same'))中使用"filiters"代替"filters"，使用"kernal_size"代替"kernel_size"。

最后，在model.add(layers.Activation('sigmod'))中使用"sigmod"而不是"sigmoid"。

我在你的代码中没有看到任何变量a，所以如果我是你，我会确保首先修复你的拼写错误，因为它们可能会以某种方式导致这个问题。

Answer 2

def make_CNN_model()：

model = Sequential()
# input layer transformation (BatchNormalization + Dropout)
model.add(layers.BatchNormalization(name='inputlayer',input_shape=(28,28,1)))
model.add(layers.Dropout(name='Droupout_inputlayer',rate=0.3))
# convolutional layer (Conv2D + MaxPooling2D + Flatten + Dropout)
model.add(layers.Conv2D(filters=32,activation='relu', name="Convoluationlayer_1",kernel_size=(3,3),border_mode='same'))
model.add(layers.MaxPooling2D(name='MaxPooling_1'))
model.add(layers.Flatten(name="Flaten_1"))
model.add(layers.Dropout(rate=0.3))
# fully connected layer (Dense + BatchNormalization + Activation + Dropout)
model.add(layers.Dense(name="FullyConnectedLayer_1",units=50))
model.add(layers.BatchNormalization())
model.add(layers.Activation('relu'))
model.add(layers.Dropout(rate=0.3))
# output layer (Dense + BatchNormalization + Activation)
model.add(layers.Dense(name = "Outputlayer", units=10))
model.add(layers.BatchNormalization())
model.add(layers.Activation('sigmoid'))
return model

Answer 3

我在终端上写了下面的代码，并再次安装了python 3，问题就解决了。

$conda install-c conda forge tensorflow