Problem in training and colorizing few grayscale images

[Angad Singh]

As an experiment, I trained model on frames/resized images and used same images for testing/colorizing and there was no problem in running scripts. However, when grayscale images are a part of either train/test images I am getting errors OutOfRangeError (As mentioned in #2 ). Further I took a random image and tried to colorize it. Below is the grayscale image and its colorization result.

I strongly believe that result will be accurate by selecting proper training images. As I have trained model on pokemon gameplay video and my concern is not regarding the accuracy of model.

I was able to recover images you used in demo version by going through old commits, but using them as a test image gave errors (I have shared error images in issue #2 ). I think the reason because of which I was getting error in training stage of #2 is that I was also having resized grayscale images in image directory and have also mentioned in same that removing them fixed problem I was facing.