pavelgonchar / color-independent-style-transfer Goto Github PK
View Code? Open in Web Editor NEWTransfer Style But Not Color http://blog.deepart.io/2016/06/04/color-independent-style-transfer/
Transfer Style But Not Color http://blog.deepart.io/2016/06/04/color-independent-style-transfer/
Hi,
File "run.py", line 85, in
original_image = original_image.reshape((1, 338, 600, 3))
ValueError: cannot reshape array of size 360000 into shape (1,338,600,3)
Please suggest
there are some APIS changed in tensorflow 1.0. For instance, "tf.initialize_all_variables" should be changed to tf.global_variables_initializer..
The revised code is below:
import skimage.io
import tensorflow as tf
from tensorflow.python.framework import ops, dtypes
import numpy as np
from matplotlib import pyplot as plt
flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_string('original', 'minsk.jpg', 'Original Image')
flags.DEFINE_string('styled', 'tmp_950_color.jpg', 'Styled Image')
original = tf.placeholder("float", [1, 338, 600, 3])
styled = tf.placeholder("float", [1, 338, 600, 3])
def concat_images(imga, imgb):
"""
Combines two color image ndarrays side-by-side.
"""
ha, wa = imga.shape[:2]
hb, wb = imgb.shape[:2]
max_height = np.max([ha, hb])
total_width = wa + wb
new_img = np.zeros(shape=(max_height, total_width, 3), dtype=np.float32)
new_img[:ha, :wa] = imga
new_img[:hb, wa:wa + wb] = imgb
return new_img
def rgb2yuv(rgb):
"""
Convert RGB image into YUV https://en.wikipedia.org/wiki/YUV
"""
rgb2yuv_filter = tf.constant(
[[[[0.299, -0.169, 0.499],
[0.587, -0.331, -0.418],
[0.114, 0.499, -0.0813]]]])
rgb2yuv_bias = tf.constant([0., 0.5, 0.5])
temp = tf.nn.conv2d(rgb, rgb2yuv_filter, [1, 1, 1, 1], 'SAME')
temp = tf.nn.bias_add(temp, rgb2yuv_bias)
return temp
def yuv2rgb(yuv):
"""
Convert YUV image into RGB https://en.wikipedia.org/wiki/YUV
"""
yuv = tf.multiply(yuv, 255)
yuv2rgb_filter = tf.constant(
[[[[1., 1., 1.],
[0., -0.34413999, 1.77199996],
[1.40199995, -0.71414, 0.]]]])
yuv2rgb_bias = tf.constant([-179.45599365, 135.45983887, -226.81599426])
temp = tf.nn.conv2d(yuv, yuv2rgb_filter, [1, 1, 1, 1], 'SAME')
temp = tf.nn.bias_add(temp, yuv2rgb_bias)
temp = tf.maximum(temp, tf.zeros(temp.get_shape(), dtype=tf.float32))
temp = tf.minimum(temp, tf.multiply(
tf.ones(temp.get_shape(), dtype=tf.float32), 255))
temp = tf.div(temp, 255)
return temp
styled_grayscale = tf.image.rgb_to_grayscale(styled)
styled_grayscale_rgb = tf.image.grayscale_to_rgb(styled_grayscale)
styled_grayscale_yuv = rgb2yuv(styled_grayscale_rgb)
original_yuv = rgb2yuv(original)
#combined_yuv = tf.concat(3, [tf.split(3, 3, styled_grayscale_yuv)[0], tf.split(3, 3, original_yuv)[1], tf.split(3, 3, original_yuv)[2]])
combined_yuv = tf.concat([tf.split(styled_grayscale_yuv, 3, 3)[0], tf.split(original_yuv, 3, 3)[1], tf.split(original_yuv, 3, 3)[2]],3)
combined_rbg = yuv2rgb(combined_yuv)
#init = tf.initialize_all_variables()
init=tf.global_variables_initializer()
with tf.Session() as sess:
#sess.run(tf.initialize_all_variables())
sess.run(tf.global_variables_initializer())
original_image = skimage.io.imread(FLAGS.original) / 255.0
original_image = original_image.reshape((1, 338, 600, 3))
styled_image = skimage.io.imread(FLAGS.styled) / 255.0
styled_image = styled_image.reshape((1, 338, 600, 3))
combined_rbg_ = sess.run(combined_rbg, feed_dict={original: original_image, styled: styled_image})
summary_image = concat_images(original_image.reshape((338, 600, 3)), styled_image.reshape((338, 600, 3)))
summary_image = concat_images(summary_image, combined_rbg_[0])
plt.imsave("results.jpg", summary_image)
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.