欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  IT编程

tensorflow 打印内存中的变量方法

程序员文章站 2022-06-11 11:05:08
法一: 循环打印 模板 for (x, y) in zip(tf.global_variables(), sess.run(tf.global_variabl...

法一:

循环打印

模板

for (x, y) in zip(tf.global_variables(), sess.run(tf.global_variables())):
 print '\n', x, y

实例

# coding=utf-8

import tensorflow as tf


def func(in_put, layer_name, is_training=True):
 with tf.variable_scope(layer_name, reuse=tf.AUTO_REUSE):
  bn = tf.contrib.layers.batch_norm(inputs=in_put,
           decay=0.9,
           is_training=is_training,
           updates_collections=None)
 return bn

def main():

 with tf.Graph().as_default():
  # input_x
  input_x = tf.placeholder(dtype=tf.float32, shape=[1, 4, 4, 1])
  import numpy as np
  i_p = np.random.uniform(low=0, high=255, size=[1, 4, 4, 1])
  # outputs
  output = func(input_x, 'my', is_training=True)
  with tf.Session() as sess:
   sess.run(tf.global_variables_initializer())
   t = sess.run(output, feed_dict={input_x:i_p})

   # 法一: 循环打印
   for (x, y) in zip(tf.global_variables(), sess.run(tf.global_variables())):
    print '\n', x, y

if __name__ == "__main__":
 main()
2017-09-29 10:10:22.714213: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1052] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0, compute capability: 6.1)

<tf.Variable 'my/BatchNorm/beta:0' shape=(1,) dtype=float32_ref> [ 0.]

<tf.Variable 'my/BatchNorm/moving_mean:0' shape=(1,) dtype=float32_ref> [ 13.46412563]

<tf.Variable 'my/BatchNorm/moving_variance:0' shape=(1,) dtype=float32_ref> [ 452.62246704]

Process finished with exit code 0

法二:

指定变量名打印

模板

print 'my/BatchNorm/beta:0', (sess.run('my/BatchNorm/beta:0'))

实例

# coding=utf-8

import tensorflow as tf


def func(in_put, layer_name, is_training=True):
 with tf.variable_scope(layer_name, reuse=tf.AUTO_REUSE):
  bn = tf.contrib.layers.batch_norm(inputs=in_put,
           decay=0.9,
           is_training=is_training,
           updates_collections=None)
 return bn

def main():

 with tf.Graph().as_default():
  # input_x
  input_x = tf.placeholder(dtype=tf.float32, shape=[1, 4, 4, 1])
  import numpy as np
  i_p = np.random.uniform(low=0, high=255, size=[1, 4, 4, 1])
  # outputs
  output = func(input_x, 'my', is_training=True)
  with tf.Session() as sess:
   sess.run(tf.global_variables_initializer())
   t = sess.run(output, feed_dict={input_x:i_p})

   # 法二: 指定变量名打印
   print 'my/BatchNorm/beta:0', (sess.run('my/BatchNorm/beta:0'))
   print 'my/BatchNorm/moving_mean:0', (sess.run('my/BatchNorm/moving_mean:0'))
   print 'my/BatchNorm/moving_variance:0', (sess.run('my/BatchNorm/moving_variance:0'))

if __name__ == "__main__":
 main()
2017-09-29 10:12:41.374055: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1052] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0, compute capability: 6.1)

my/BatchNorm/beta:0 [ 0.]
my/BatchNorm/moving_mean:0 [ 8.08649635]
my/BatchNorm/moving_variance:0 [ 368.03442383]

Process finished with exit code 0

以上这篇tensorflow 打印内存中的变量方法就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。