How use bigger size images? 512, 1024... and more
Aziz87 opened this issue · comments
Aziz commented
When i use img_size = 512 i have error
ValueError: Cannot feed value of shape (1, 512, 512, 3) for Tensor 'X:0', which has shape '(?, 256, 256, 3)'
on the line:
Xs_ = sess.run(Xs, feed_dict={X: X_img, Y: Y_img})
may be need other model.meta?
Cortland Walker commented
The model is implemented to accept 256x256 images. I could be wrong, but you would have to make changes to layers in the generator and discriminator to allow for larger images.