1

I have a list of variable size image and wish to standardise them into 256x256 size. I used the following code 

import tensorflow as tf import matplotlib.pyplot as plt file_contents = tf.read_file('image.jpg') im = tf.image.decode_jpeg(file_contents) im = tf.image.resize_images(im, 256, 256) sess = tf.Session() sess.run(tf.initialize_all_variables()) img = sess.run(im) plt.imshow(img) plt.show()

However, tf.resize_images() tend to mess up the image. However, using tf.reshape() seems to allow resize_image() function correctly

Tensorflow version : 0.8.0

Original Image: enter image description here

Resized Image: enter image description here

I know skimage package can handle what I need, however I wish to enjoy the function from tf.train.shuffle_batch(). I try to avoid maintaining 2 identical dataset ( with 1 fixed image size ) since Caffe seems to have no problem handling them.

Improve this question
3
  • Could you try resizing using method=ResizeMethod.BILINEAR or method=ResizeMethod.BICUBIC. If it still fails, could you file an issue with an image that causes this, so it can be fixed on TensorFlow side? Commented May 4, 2016 at 17:25
  • only ResizeMethod.NEAREST_NEIGHBOR work, rest of the method produce similar result as above, I will raise an issue in github. Commented May 5, 2016 at 1:22
  • github.com/tensorflow/tensorflow/issues/31539 Commented Aug 13, 2019 at 3:26

1 Answer 1

Reset to default
5

This happens because image_resize() is performing an interpolation between adjacent pixels, and returning floats instead of integers in the range 0-255. That's why NEAREST_NEIGHBOR does work: it takes the value of one of the near pixels without doing further math. Suppose you have some adjacent pixels with values 240, 241. NEAREST_NEIGHBOR will return either 240 or 241. With any other method, the value could be something like 240.5, and is returned without rounding it, I assume intentionally so you can decide what is better for you (floor, round up, etc). The plt.imshow() on the other side, when facing float values, interprets only the decimal part, as if they were pixel values in a full scale between 0.0 and 1.0. To make the above code work, one of the possible solutions would be:

import numpy as np plt.imshow(img.astype(np.uint8))
Improve this answer
Sign up to request clarification or add additional context in comments.

Comments

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.