logic1988

I am also interested in it! Is there easy way to convert the ready-made chainer model to caffemodel? Anybody succeeded?

I found the reason for point 2: code in https://github.com/google/hdrnet/blob/master/hdrnet/bin/train.py#L105 was wrong.

Which one was more faster? include training and generating?

@Heartsie The result was so good. I have trained this style before, but the output was terrible, I used the default params and the image size was 512. What params...

From the paper we can see the effect is greatly improved. Anybody have the implement in python, I can test it.

There are a great Torch Implementation released by jcjohnson a few days ago. https://github.com/jcjohnson/fast-neural-style In addition to the original method, the new method inspired by the the paper [Instance Normalization:...

@6o6o The second result was great! Thanks for your work! I trained some models but the result was terrible. Can you help me for some details? 1. Training by the...

@6o6o Thank you very much! Please fork the project then I can learn from it. Looking forward to more communication.