nagadomi
a210090033
Convert model files; Add new pretrained model
...
- Add new pretrained model to ./models/upconv_7
- Move old models to ./models/vgg_7
- Use nn.LeakyReLU instead of w2nn.LeakyReLU
- Add useful attribute to .json
New JSON attribute:
The first layer has `model_config` attribute.
It contains:
model_arch: architecture name of model. see `lib/srcnn.lua`
scale_factor: if scale_factor > 1, model:forward() changes image resolution with scale_factor.
channels: input/output channels. if channels == 3, model is RGB model.
offset: pixel size that is to be removed from output.
for example:
(scale_factor=1, offset=7, input=100x100) => output=(100-7)x(100-7)
(scale_factor=2, offset=12, input=100x100) => output=(100*2-12)x(100*2-12)
And each layer has `class_name` attribute.
2016-05-15 03:04:08 +09:00
nagadomi
8da52d5fb9
Merge from master
2016-04-23 12:48:24 +09:00
nagadomi
b9a50f9422
Add Simplified Chinese Translation
2016-04-16 23:56:22 +09:00
nagadomi
3a27e122ac
Add support for grayscale output
2016-04-15 13:29:50 +09:00
nagadomi
fbad30c031
Fix embed gamma handling
2016-04-15 09:13:37 +09:00
nagadomi
cafc579627
Merge branch 'master' into dev
2016-04-15 08:32:49 +09:00
nagadomi
4d4519515c
Add Turkish Language
2016-04-15 06:45:24 +09:00
nagadomi
77bdd16284
Add German Translation
2016-04-08 21:02:11 +09:00
nagadomi
30fe5db735
Add upsampling_filter option
2016-04-02 22:03:27 +09:00
nagadomi
ed9c8b7ea8
Add support for level 3 noise reduction on web
2016-03-27 17:35:34 +09:00
nagadomi
86ad50f7cd
Merge branch 'master' of github.com:nagadomi/waifu2x into dev
2016-03-21 03:59:17 +09:00
nagadomi
57e0f52b41
Reduce memory usage
2016-03-21 03:42:47 +09:00
nagadomi
0b130b797c
Merge branch 'master' of github.com:nagadomi/waifu2x into dev
2016-03-14 13:38:49 +09:00
nagadomi
1d463b7e5f
Change output filename in WebUI
2016-03-14 11:17:38 +09:00
nagadomi
9b238bd693
Use clearState()
2016-03-11 11:12:02 +09:00
nagadomi
138768a46d
Add support for french
2016-02-23 00:00:01 +09:00
nagadomi
c76c656e57
Fix merge
2016-02-14 11:51:30 +09:00
nagadomi
35d4fc7a5e
Fix download error on Android
2016-02-14 11:26:46 +09:00
nagadomi
b5903b3d56
Fix content-disposition for download
2016-02-14 11:13:53 +09:00
nagadomi
4e7527cc45
Add support for spanish
2016-02-12 09:57:01 +09:00
nagadomi
49fecb8523
web
2016-02-07 07:38:39 +09:00
nagadomi
0d31657874
Relax the file size limitation on the web UI
2016-02-07 06:02:05 +09:00
nagadomi
122ffd37fe
Web page
...
- Add `webgen/gen.rb` to generate web page from template
- Add support for mobile browser
- Change layouts
2016-02-07 05:58:27 +09:00
nagadomi
c1d15933a9
Add support for Accept-Language=pt
2016-01-23 11:12:58 +09:00
nagadomi
26d4179cfe
Add web ui for lang=pt
2016-01-23 09:48:40 +09:00
nagadomi
95a0b8ad09
Add support for photo model and cookie in web.lua
2015-12-04 22:07:52 +09:00
nagadomi
d2c081bbcf
Improve alpha channel handling #29
...
- make border
- scale the alpha channel by waifu2x
- composite
2015-12-01 17:26:45 +09:00
nagadomi
ac5b18e4da
Change the scaling filter for 1.6x
2015-11-22 20:22:46 +09:00
nagadomi
26f0d61bb1
Add download button for mobile
2015-11-21 16:01:49 +09:00
nagadomi
abedec9d9b
Fix filter name for graphicsmagick
...
graphicsmagick package has bug in the definition of FilteTypes.
I will send PR to fix that bug.
This commit is related to it.
You should upgrade graphicsmagick package.
$ luarocks install graphicsmagick
2015-11-21 11:57:33 +09:00
nagadomi
c4657b4720
disabling the photo model in web.lua
...
I will support the photo model in the next version
2015-11-15 09:25:48 +09:00
nagadomi
c345f35ed0
Use Image.toString instead of Image.toBlob
2015-11-13 16:11:12 +09:00
nagadomi
13dad2ec26
Add support for photo denosing model in web.lua
2015-11-13 16:07:30 +09:00
nagadomi
b63e08905b
Remove unused variable
2015-11-11 10:54:28 +09:00
nagadomi
4a4885c856
Add -white_noise option
...
post-processing for anime screencap.
2015-11-11 10:42:33 +09:00
nagadomi
6e41796328
Use gamma 2.2 space when resizing
2015-11-08 20:28:14 +09:00
nagadomi
5ab2c605c8
Fix header include order issues
2015-11-08 18:31:46 +09:00
nagadomi
3b2aa67e55
Improve web interface
2015-11-07 22:54:29 +09:00
nagadomi
539941c234
Add support for url cache in web.lua
2015-11-06 12:24:27 +09:00
nagadomi
425898a3aa
Don't use cudnn.benchmark mode when predicting
2015-10-31 22:09:21 +09:00
nagadomi
3abc5a03e3
refactor
2015-10-28 16:01:07 +09:00
nagadomi
956ae0d24c
merge from master
2015-10-26 09:39:41 +09:00
nagadomi
8dea362bed
sync from internal repo
...
- Memory compression by snappy (lua-csnappy)
- Use RGB-wise Weighted MSE(R*0.299, G*0.587, B*0.114) instead of MSE
- Aggressive cropping for edge region
and some change.
2015-10-26 09:23:52 +09:00
nagadomi
b35798016e
Added support for index.ru.html in web.lua
2015-09-07 14:51:56 +09:00
nagadomi
a7a5f5b1b2
fix disk full
2015-06-28 23:56:12 +00:00
nagadomi
6a91d7d3b4
Merge branch 'master' of https://github.com/nagadomi/waifu2x
2015-06-22 18:17:50 +00:00
nagadomi
0a683fcb34
multi GPU server
2015-06-22 18:17:41 +00:00
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
bbc3cac273
add support for transparent png (retain the alpha channel)
2015-06-16 20:41:48 +09:00
nagadomi
4548eddacd
fix SSL error in demo page
2015-06-14 00:26:00 +09:00