我想使用矩阵指定激活节点之间的连接,而不是完全连接的层。例如:
我有一个20节点层连接到10节点层。使用典型的完全连接图层,我的W
矩阵为20 x 10,其中b
向量的大小为10.
我的激活看起来像relu(Wx + b)
如果我有一个与W
大小相同的1和0矩阵,我们称之为F
,我可以在W
和{{1}之间进行成对乘法运算删除我的第一层(20个节点)和第二层(10个节点)之间的连接
这是我目前的代码:
F
my_fun给我的地方:F.shape
# (20, 10)
import tflearn
import tensorflow as tf
input = tflearn.input_data(shape=[None, num_input])
first = tflearn.fully_connected(input, 20, activation='relu')
# Here is where I want to use a custom function, that uses my F matrix
# I dont want the second layer to be fully connected to the first,
# I want only connections that are ones (and not zeros) in F
# Currently:
second = tflearn.fully_connected(first, 10, activation='relu')
# What I want:
second = tflearn.custom_layer(first, my_fun)
和relu( (FW)X + b)
是成对乘法
如何创建此功能?我似乎无法找到关于如何完成的详细示例,但我也知道tflearn也允许基本张量流函数
答案 0 :(得分:1)
很难用tflearn严格执行此操作,但如果您愿意包含基本张量流操作,那么它很简单:
F.shape
# (20, 10)
import tflearn
import tensorflow as tf
input = tflearn.input_data(shape=[None, num_input])
tf_F = tf.constant(F, shape=[20, 10])
first = tflearn.fully_connected(input, 20, activation='relu')
# Here is where I want to use a custom function, that uses my F matrix
# I want only connections that are ones (and not zeros) in F
# Old:
# second = tflearn.fully_connected(first, 10, activation='relu')
# Solution:
W = tf.Variable(tf.random_uniform([20, 10]), name='Weights')
b = tf.Variable(tf.zeros([10]), name='biases')
W_filtered = tf.mul(tf_F, W)
second = tf.matmul( W_filtered, first) + b
答案 1 :(得分:0)
我也有这个问题。我的目的是通过删除层之间的大量连接来减少模型中的参数数量。但是@kamula明显的做法并没有减少模型的大小。