您的位置:首页 > 其它

Tensorflow常见的图像操作

2016-07-14 10:32 267 查看
这些操作代码是自己在学习tensorflow时教程里给出的,现在整理一下方便自己日后使用,也方便大家一起学习tensorflow。

1、图像转置(逆时针旋转90度)——transpose()



import matplotlib.image as mpimg
import matplotlib.pyplot as plt
import tensorflow as tf

#加载图像
filename = "MarshOrchid.jpg"
image = mpimg.imread(filename)

#创建tensorflow变量
x = tf.Variable(image,name='x')

model = tf.initialize_all_variables()

with tf.Session() as session:
x = tf.transpose(x, perm=[1,0,2])     ##转置函数,通过该函数实现转置
session.run(model)
result = session.run(x)

plt.imshow(result)
plt.show()<strong>
</strong>


2、图像翻转(左右翻转)——reverse_sequence()

<span style="font-size:12px;color:#000000;">import matplotlib.image as mpimg
import matplotlib.pyplot as plt
import tensorflow as tf

#加载图像
filename = "MarshOrchid.jpg"
image = mpimg.imread(filename)

height,width,depth = image.shape

print(height,width,depth)

#创建一个tensorflow变量
x = tf.Variable(image,name='x')

model = tf.initialize_all_variables()

with tf.Session() as session:
x = tf.reverse_sequence(x, [width]*height, 1, batch_dim=0)  ####翻转函数
session.run(model)
result = session.run(x)

print(result.shape)
plt.imshow(result)
plt.show()</span>












内容来自用户分享和网络整理,不保证内容的准确性,如有侵权内容,可联系管理员处理 点击这里给我发消息
标签: