tensorflow prelu的實(shí)現(xiàn)細(xì)節(jié)

output= tf.nn.leaky_relu(input, alpha=tf_gamma_data,name=name)

#tf.nn.leaky_relu 限制了tf_gamma_data在[0 1]的范圍內(nèi)

內(nèi)部實(shí)現(xiàn)方法是output = tf.maxmum(alpha * input, input)

alpha > 1 時(shí)，會(huì)出現(xiàn)，正值*alpha， 負(fù)值不變

import numpy as np
import tensorflow as tf

#bn = np.loadtxt('tfbn.txt')
bn = np.array([[-0.9, -0.9 ,-0.9],[1.1,1.1,1.1]])
print("srcdata ", bn)
gamma_data = np.array([1.205321])
print("gamma_data ", gamma_data)
tf_gamma_data = tf.Variable(gamma_data, dtype=np.float32)
input_data = tf.Variable(bn, dtype=np.float32)
tf_prelu_test = tf.nn.leaky_relu(input_data, alpha=tf_gamma_data,name=None)
#tf_prelu_test = tf.nn.relu(input_data) + tf.multiply(tf_gamma_data, -tf.nn.relu(-input_data))
#tf_prelu_test = tf.nn.relu(input_data,name=None)
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    tf_prelu_test = sess.run(tf_prelu_test)
    print("tf_prelu_test: 
", tf_prelu_test)

srcdata [[-0.9 -0.9 -0.9]
[ 1.1 1.1 1.1]]
gamma_data [1.205321]
tf_prelu_test:
[[-0.9 -0.9 -0.9 ]
[ 1.3258531 1.3258531 1.3258531]]
[Finished in 2.5s]

使用relu來(lái)代替
output = tf.nn.relu(data) + tf.multiply(alpha, -tf.nn.relu(-data))

import numpy as np
import tensorflow as tf

#bn = np.loadtxt('tfbn.txt')
bn = np.array([[-0.9, -0.9 ,-0.9],[1.1,1.1,1.1]])
print("srcdata ", bn)
gamma_data = np.array([1.205321])
print("gamma_data ", gamma_data)
tf_gamma_data = tf.Variable(gamma_data, dtype=np.float32)
input_data = tf.Variable(bn, dtype=np.float32)
#tf_prelu_test = tf.nn.leaky_relu(input_data, alpha=tf_gamma_data,name=None)
tf_prelu_test = tf.nn.relu(input_data) + tf.multiply(tf_gamma_data, -tf.nn.relu(-input_data))
#tf_prelu_test = tf.nn.relu(input_data,name=None)
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    tf_prelu_test = sess.run(tf_prelu_test)
    print("tf_prelu_test: 
", tf_prelu_test)

srcdata [[-0.9 -0.9 -0.9]
[ 1.1 1.1 1.1]]
gamma_data [1.205321]
tf_prelu_test:
[[-1.0847888 -1.0847888 -1.0847888]
[ 1.1 1.1 1.1 ]]
[Finished in 2.7s]

總結(jié)

以上是生活随笔為你收集整理的tensorflow prelu的实现细节的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。