Revision history [back]

Thank you, guys. I found a problem. Error, actually was in the number of channels and decided to replace the lines:

x = tf.placeholder(tf.float32, shape=[None, img_height, img_width], name='x_input')
x_image = tf.reshape(x, [-1, img_height, img_width, num_channels])

with these:

x_image = tf.placeholder(tf.float32, shape=[None, img_height, img_width, num_channels], name='x_input')

@berak , @dkurt Thank you, guys. I found a problem. Error, actually was in the number of channels and decided to replace the lines:

x = tf.placeholder(tf.float32, shape=[None, img_height, img_width], name='x_input')
x_image = tf.reshape(x, [-1, img_height, img_width, num_channels])

with these:

x_image = tf.placeholder(tf.float32, shape=[None, img_height, img_width, num_channels], name='x_input')