6 commits

Author	SHA1	Message	Date
nagadomi	2c00335f96	update anime_style_art_rgb/scale2.0x_model	2015-07-12 00:03:24 +09:00
nagadomi	95e9d276a3	add new model for photo ... - add ukbench model (models/ukbench) - ukbench model was trained by Recognition Benchmark Images (http://www.vis.uky.edu/~stewe/ukbench/) usage: $ th waifu2x.lua -m scale -model_dir models/ukbench -i input.jpg -o output.png	2015-06-23 18:03:23 +09:00
nagadomi	5b4d692f03	add support for RGB color space reconstruction ... - add new RGB model (models/anime_style_art_rgb). - RGB model can reduce color noise. - waifu2x uses this RGB model by default. You can use Y model with: $ th waifu2x.lua -model_dir models/anime_style_art -i input.png -o output.png $ th train.lua -color y ...	2015-06-23 02:55:30 +09:00
nagadomi	a706892b59	merge develop repo ... - remove support for cuDNN - add new pre-trained model and json files - some changes in training script If you have cuDNN model, Please run following commands to convert. $ cp models/your_own_model.t7 models/your_own_model.t7.backup $ th cudnn2cunn.lua -model models/your_own_model.t7	2015-06-13 15:20:40 +09:00
nagadomi	83548d7494	update noise1_model	2015-05-17 02:44:08 +09:00
nagadomi	1273b3609e	first commit	2015-05-16 14:48:05 +09:00