Tensorflow:输出tensor具体值

51 阅读 0 评论 34 点赞

我是靠谱客的博主细腻楼房，最近开发中收集的这篇文章主要介绍Tensorflow:输出tensor具体值，觉得挺不错的，现在分享给大家，希望可以做个参考。

概述

在一些任务中,经常需要看tensor的具体值是多少,举个例子,你得查看一部分的feature map,或者是一些数据是否符合训练的预期,那么怎么查看对应tensor的具体值(⊙o⊙)?

有些小伙伴可能会特别不屑,print一下不就好了?哈哈,要是直接print有效, LZ还花这闲工夫干啥!

举个例子,不难.
我们先生成一些随机数

import numpy as np
np.random.seed(100)
triangles = np.random.rand(1, 5, 3, 3).astype('float32')

使用print打印一下:

print triangles

显示如下:

[[[[0.54340494 0.2783694  0.4245176 ]
   [0.84477615 0.00471886 0.12156912]
   [0.67074907 0.82585275 0.13670659]]
  [[0.5750933  0.89132196 0.20920213]
   [0.18532822 0.10837689 0.21969749]
   [0.9786238  0.8116832  0.17194101]]
  [[0.81622475 0.27407375 0.4317042 ]
   [0.9400298  0.81764936 0.33611196]
   [0.17541045 0.37283206 0.00568851]]
  [[0.25242636 0.7956625  0.01525497]
   [0.5988434  0.6038045  0.10514768]
   [0.38194343 0.03647606 0.89041156]]
  [[0.98092085 0.05994199 0.89054596]
   [0.5769015  0.7424797  0.63018394]
   [0.5818422  0.02043913 0.21002658]]]]

OK,然后我们将数据转化成tensor类型,在使用print进行打印,看下会发生什么?

inp = tf.constant(traingles)
print inp

显示如下:并没有输出具体数值,同样也就没有办法对所获得的tensor进行分析

Tensor("Const:0", shape=(1, 5, 3, 3), dtype=float32)

解决方法有两种:

第一种:利用session.run()进行处理

sess = tf.Session()
print(sess.run(inp))

最后的显示结果如此啊所示:

[[[[0.54340494 0.2783694  0.4245176 ]
   [0.84477615 0.00471886 0.12156912]
   [0.67074907 0.82585275 0.13670659]]
  [[0.5750933  0.89132196 0.20920213]
   [0.18532822 0.10837689 0.21969749]
   [0.9786238  0.8116832  0.17194101]]
  [[0.81622475 0.27407375 0.4317042 ]
   [0.9400298  0.81764936 0.33611196]
   [0.17541045 0.37283206 0.00568851]]
  [[0.25242636 0.7956625  0.01525497]
   [0.5988434  0.6038045  0.10514768]
   [0.38194343 0.03647606 0.89041156]]
  [[0.98092085 0.05994199 0.89054596]
   [0.5769015  0.7424797  0.63018394]
   [0.5818422  0.02043913 0.21002658]]]]

第二种方法:

with tf.Session():
    print(inp.eval())

最后打印结果也是一致的

[[[[0.54340494 0.2783694  0.4245176 ]
   [0.84477615 0.00471886 0.12156912]
   [0.67074907 0.82585275 0.13670659]]
  [[0.5750933  0.89132196 0.20920213]
   [0.18532822 0.10837689 0.21969749]
   [0.9786238  0.8116832  0.17194101]]
  [[0.81622475 0.27407375 0.4317042 ]
   [0.9400298  0.81764936 0.33611196]
   [0.17541045 0.37283206 0.00568851]]
  [[0.25242636 0.7956625  0.01525497]
   [0.5988434  0.6038045  0.10514768]
   [0.38194343 0.03647606 0.89041156]]
  [[0.98092085 0.05994199 0.89054596]
   [0.5769015  0.7424797  0.63018394]
   [0.5818422  0.02043913 0.21002658]]]]

如果不先注册session,直接运行

print(inp.eval())

那么就会报错,如下所示:

Traceback (most recent call last):
  File "<input>", line 1, in <module>
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 606, in eval
    return _eval_using_default_session(self, feed_dict, self.graph, session)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 3914, in _eval_using_default_session
    raise ValueError("Cannot evaluate tensor using `eval()`: No default "
ValueError: Cannot evaluate tensor using `eval()`: No default session is registered. Use `with sess.as_default()` or pass an explicit session to `eval(session=sess)`

Y(^o)Y,好啦,这个就是tensorflow输出tensor具体值的一个小技巧,O(∩_∩)O哈哈~,Felaim要继续加油呢!