Xiang Liang

I find in https://github.com/jcjohnson/fast-neural-style/blob/master/fast_neural_style/models.lua#L96, it has already support nearest neighbor upsampling to fix this problem.

The results looks awesome! Thanks! I will try to do more works on post-processing.

@jcjohnson I have tried to train with 200K images from coco, MIT space, and imageNet. Seems does not get better results. I will try this again later.

@jcjohnson what is your parameter for the_wave style. I seems can not reproduce your results with parameter in print_options.lua. Following is my result:  Your results  prisma 

I also test failed on GTX 1080 Running GPU tests terminate called after throwing an instance of 'std::runtime_error' what(): Error: compute_ctc_loss in small_test, stat = execution failed Aborted

Good job!