Question

我是Python和深度学习的新手，并且在我的curdrent Udacity项目中遇到了这种语法错误。有133个分类，所以我把它作为输出。无论如何，请参考下面的代码，让我知道为什么我可能会收到此错误：

File "<ipython-input-1-2979a000d526>", line 18
    model.add(Dense(133))
        ^
SyntaxError: invalid syntax

以下是代码：

from keras.layers import Conv2D, MaxPooling2D, GlobalAveragePooling2D
from keras.layers import Dropout, Flatten, Dense
from keras.models import Sequential

model = Sequential()
model.add(Conv2D(filters=16, kernel_size=2, strides=(2,2), padding='valid', activation='relu', 
                        input_shape=(224, 224, 3)))# putput of (224,224,16)
model.add(MaxPooling2D(pool_size=2))#output of (112,112,16)
model.add(Conv2D(filters=32, kernel_size=2, strides=(2,2), padding='valid', activation='relu'))
#output is (112,112,32)
model.add(MaxPooling2D(pool_size=2))#output is (56,56,32)
model.add(Conv2D(filters=64, kernel_size=2, strides=(2,2), padding='same', activation='relu'))
#output is (56,56,64)
model.add(MaxPooling2D(pool_size=2))#output is (28,28,64)
#add global average pooling 2D layer 
model.add(GlobalAveragePooling2D(data_format = channels_last)
# don't need to flatten after GAP model.add(Flatten())
model.add(Dense(133)) #error is here
model.add(Activation('softmax'))

### TODO: Define your architecture.

model.summary()

Answer 1

你的行

model.add(GlobalAveragePooling2D(data_format = channels_last)

最后缺少一个括号。

model.add的Keras语法错误（密集，（133））

1 个答案: