“Flatten"的作用是什么?在凯拉斯? [英] What is the role of "Flatten" in Keras?

问题描述

我试图了解 Flatten 函数在 Keras 中的作用.下面是我的代码，这是一个简单的两层网络.接收形状​​为(3, 2)的二维数据，输出形状为(1, 4)的一维数据:

model = Sequential()model.add(密集(16, input_shape=(3, 2)))模型.添加(激活('relu'))模型.添加(展平())模型.添加(密集(4))model.compile(loss='mean_squared_error', 优化器='SGD')x = np.array([[[1, 2], [3, 4], [5, 6]]])y = 模型.预测(x)打印 y.shape

这会打印出 y 的形状为 (1, 4).但是，如果我删除 Flatten 行，它会打印出 y 的形状为 (1, 3, 4).

我不明白这个.根据我对神经网络的理解，model.add(Dense(16, input_shape=(3, 2))) 函数正在创建一个隐藏的全连接层，有 16 个节点.这些节点中的每一个都连接到 3x2 输入元素中的每一个.因此，第一层输出的 16 个节点已经平坦"了.所以，第一层的输出形状应该是 (1, 16).然后，第二层以此为输入，输出形状为(1, 4)的数据.

那么如果第一层的输出已经是平坦的"并且形状为 (1, 16)，为什么我还需要进一步平坦化它?

解决方案

如果您阅读 Keras 文档条目

I am trying to understand the role of the Flatten function in Keras. Below is my code, which is a simple two-layer network. It takes in 2-dimensional data of shape (3, 2), and outputs 1-dimensional data of shape (1, 4):

model = Sequential()
model.add(Dense(16, input_shape=(3, 2)))
model.add(Activation('relu'))
model.add(Flatten())
model.add(Dense(4))
model.compile(loss='mean_squared_error', optimizer='SGD')

x = np.array([[[1, 2], [3, 4], [5, 6]]])

y = model.predict(x)

print y.shape

This prints out that y has shape (1, 4). However, if I remove the Flatten line, then it prints out that y has shape (1, 3, 4).

I don't understand this. From my understanding of neural networks, the model.add(Dense(16, input_shape=(3, 2))) function is creating a hidden fully-connected layer, with 16 nodes. Each of these nodes is connected to each of the 3x2 input elements. Therefore, the 16 nodes at the output of this first layer are already "flat". So, the output shape of the first layer should be (1, 16). Then, the second layer takes this as an input, and outputs data of shape (1, 4).

So if the output of the first layer is already "flat" and of shape (1, 16), why do I need to further flatten it?

解决方案

If you read the Keras documentation entry for Dense, you will see that this call:

Dense(16, input_shape=(5,3))

would result in a Dense network with 3 inputs and 16 outputs which would be applied independently for each of 5 steps. So, if D(x) transforms 3 dimensional vector to 16-d vector, what you'll get as output from your layer would be a sequence of vectors: [D(x[0,:]), D(x[1,:]),..., D(x[4,:])] with shape (5, 16). In order to have the behavior you specify you may first Flatten your input to a 15-d vector and then apply Dense:

model = Sequential()
model.add(Flatten(input_shape=(3, 2)))
model.add(Dense(16))
model.add(Activation('relu'))
model.add(Dense(4))
model.compile(loss='mean_squared_error', optimizer='SGD')

EDIT: As some people struggled to understand - here you have an explaining image:

这篇关于“Flatten"的作用是什么?在凯拉斯?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！