Open ArkaJU opened 5 years ago
2K might not be enough. Researchers often trained the colorization models using millions of RGB images. See the colorization-pytorch repo for more details.
Thanks. If I just increase the number of RGB images with number of black and white images constant, is it fine?
You can also train the model with a paired dataset. See the colorization-pytorch and this paper for more details.
Actually paired data is not available for this problem.
You can create paired data by converting RGB to grayscale images. Please look at the paper for more details.
I am working on an image colorization problem. I made the dataset by downloading black and white/colored movies from youtube and extracting frames from them. But I am not getting the desired very good results. Dataset size is 2k images each and was trained for about 40 epochs. Some results are shown below:
Can you give some pointers on how to get better results, or whether it is indeed possible for CycleGAN to colorize a grayscale image. Thank you.