[英]Split output of a layer in keras
Say, I have a layer with output dims (4, x, y).说,我有一个输出暗淡的层(4,x,y)。 I want to split this into 4 separate (1, x, y) tensors, which I can use as input for 4 other layers.我想将其拆分为 4 个单独的 (1, x, y) 张量,我可以将其用作其他 4 个层的输入。
What I'm essentially looking for is the opposite of the Merge layer.我本质上要寻找的是与 Merge 层相反的层。 I know that there's no split layer in keras, but is there a simple way to do this in keras?我知道在 keras 中没有分割层,但是在 keras 中是否有一种简单的方法可以做到这一点?
Are you looking for something like this? 你在找这样的东西吗?
import keras.backend as K
import numpy as np
val = np.random.random((4, 2, 3))
t = K.variable(value=val)
t1 = t[0, :, :]
t2 = t[1, :, :]
t3 = t[2, :, :]
t4 = t[3, :, :]
print('t1:\n', K.eval(t1))
print('t2:\n', K.eval(t2))
print('t3:\n', K.eval(t3))
print('t4:\n', K.eval(t4))
print('t:\n', K.eval(t))
It gives the following output: 它给出了以下输出:
t1:
[[ 0.18787734 0.1085723 0.01127671]
[ 0.06032621 0.14528386 0.21176969]]
t2:
[[ 0.34292713 0.56848335 0.83797884]
[ 0.11579451 0.21607392 0.80680907]]
t3:
[[ 0.1908586 0.48186591 0.23439431]
[ 0.93413448 0.535191 0.16410089]]
t4:
[[ 0.54303145 0.78971165 0.9961108 ]
[ 0.87826216 0.49061012 0.42450914]]
t:
[[[ 0.18787734 0.1085723 0.01127671]
[ 0.06032621 0.14528386 0.21176969]]
[[ 0.34292713 0.56848335 0.83797884]
[ 0.11579451 0.21607392 0.80680907]]
[[ 0.1908586 0.48186591 0.23439431]
[ 0.93413448 0.535191 0.16410089]]
[[ 0.54303145 0.78971165 0.9961108 ]
[ 0.87826216 0.49061012 0.42450914]]]
Note that, now t1, t2, t3, t4
is of shape(2,3)
. 注意,现在t1, t2, t3, t4
具有shape(2,3)
。
print(t1.shape.eval()) # prints [2 3]
So, if you want to keep the 3d shape, you need to do the following: 因此,如果要保持3d形状,则需要执行以下操作:
t1 = t[0, :, :].reshape((1, 2, 3))
t2 = t[1, :, :].reshape((1, 2, 3))
t3 = t[2, :, :].reshape((1, 2, 3))
t4 = t[3, :, :].reshape((1, 2, 3))
Now, you get the spitted tensors in correct dimension. 现在,您可以获得正确尺寸的吐出张量。
print(t1.shape.eval()) # prints [1 2 3]
Hope that it will help you to solve your problem. 希望它能帮助您解决问题。
You can define Lambda layers to do the slicing for you: 您可以定义Lambda图层来为您进行切片 :
from keras.layers import Lambda
from keras.backend import slice
.
.
x = Lambda( lambda x: slice(x, START, SIZE))(x)
For your specific example, try: 对于您的具体示例,请尝试:
x1 = Lambda( lambda x: slice(x, (0, 0, 0), (1, -1, -1)))(x)
x2 = Lambda( lambda x: slice(x, (1, 0, 0), (1, -1, -1)))(x)
x3 = Lambda( lambda x: slice(x, (2, 0, 0), (1, -1, -1)))(x)
x4 = Lambda( lambda x: slice(x, (3, 0, 0), (1, -1, -1)))(x)
您可以简单地使用tf.split 。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.