如何使用张量流加载我自己的图像数据？

Question

I have an image set which has 300,000 images in it. There are 10000 categories and 30 images per category . Each image file name is like 01_flower.png, 02_flower.png, 01_cat.png ... .

The question is:

1. How to load these images with tensorflow.

2. How to encode testing image tag to one hot vector.

Really appreciate your help.

Answer 1

It is hard to tell where exactly your Problems start.

To get you started, there are multiple ways to load data into a TensorFlow program:

• Feeding: Python code provides the data when running each step.
• Reading from files: an input pipeline reads the data from files at the beginning of a TensorFlow graph.
• Preloaded data: a constant or variable in the TensorFlow graph holds all the data (for small data sets).

A small Code example could look like that:

with tf.Session():
  input = tf.placeholder(tf.float32)
  classifier = ...
  print(classifier.eval(feed_dict={input: your_data}))