waifu2x upscaling, done in 35 lines of Python: https://mrcn.st/t/waifu2x.py https://mrcn.st/t/scale2.0x_model.json … PyOpenCL version next?pic.twitter.com/p89rzskasL
-
@marcan42 What's in JSON?
@cachemem The scale2.0x_model.t7 neural model from the original waifu2x, converted from Torch serialization format to a simple JSON format.
-
-
@marcan42 Ok, now I get it. One more question. How do you train this model? Get a lot of images and downscale them 1/2? -
@cachemem I believe that's how it works. I didn't do the training, the original author did. I'm using the existing model. - Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.