[英]How to load my own Image data with tensorflow?
I have an image set which has 300,000 images in it. 我有一个包含300,000张图像的图像集。 There are 10000 categories and 30 images per category .
有10,000个类别 , 每个类别30张图像 。 Each image file name is like
01_flower.png, 02_flower.png, 01_cat.png ...
. 每个图像文件名都类似于
01_flower.png, 02_flower.png, 01_cat.png ...
The question is: 问题是:
How to load these images with tensorflow. 如何使用张量流加载这些图像。
How to encode testing image tag to one hot vector. 如何将测试图像标签编码为一个热矢量。
Really appreciate your help. 非常感谢您的帮助。
It is hard to tell where exactly your Problems start. 很难说出您的问题从何开始。
To get you started, there are multiple ways to load data into a TensorFlow program:
首先,有多种方法可以将数据加载到TensorFlow程序中:
A small Code example could look like that: 一个小的代码示例如下所示:
with tf.Session():
input = tf.placeholder(tf.float32)
classifier = ...
print(classifier.eval(feed_dict={input: your_data}))
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.