Question

定义NN架构的问题

我正在尝试使用Keras为CIFAR-10图像数据集（https://keras.io/datasets/）创建一个CNN，但即使它出现在Keras库中，我也无法使Flatten函数工作：{{ 3}}

以下是错误消息：

NameError                                 Traceback (most recent call last)
<ipython-input-9-aabd6bce9082> in <module>()
     12 nn.add(Conv2D(64, 3, 3, activation='relu'))
     13 nn.add(MaxPooling2D(pool_size=(2, 2)))
---> 14 nn.add(Flatten())
     15 nn.add(Dense(128, activation='relu'))
     16 nn.add(Dense(10, activation='softmax'))

NameError: name 'Flatten' is not defined

我正在使用运行Python 2.7和Keras 1.1.1的Jupyter。以下是NN的代码：

from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.models import Sequential
from keras.layers import Dense, Activation

nn = Sequential()
nn.add(Conv2D(32, 3, 3, activation='relu', input_shape=(32, 32, 3)))

# Max-pool reduces the size of inputs, by taking the largest pixel-value from a grid
nn.add(MaxPooling2D(pool_size=(2, 2)))
nn.add(Conv2D(64, 3, 3, activation='relu'))
nn.add(MaxPooling2D(pool_size=(2, 2)))
nn.add(Flatten())
nn.add(Dense(128, activation='relu'))
nn.add(Dense(10, activation='softmax'))

提前致谢，

-Johan B。

Answer 1

首先尝试导入图层：

from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.models import Sequential
from keras.layers import Dense, Activation, Flatten

nn = Sequential()
nn.add(Conv2D(32, 3, 3, activation='relu', input_shape=(32, 32, 3)))

# Max-pool reduces the size of inputs, by taking the largest pixel-value from a grid
nn.add(MaxPooling2D(pool_size=(2, 2)))
nn.add(Conv2D(64, 3, 3, activation='relu'))
nn.add(MaxPooling2D(pool_size=(2, 2)))
nn.add(Flatten())
nn.add(Dense(128, activation='relu'))
nn.add(Dense(10, activation='softmax'))

在Keras中展平功能

1 个答案: