nagadomi
|
3b728643ec
|
Update upconv_7 models; bias term in last layer is removed
|
2016-07-21 20:41:48 +09:00 |
|
nagadomi
|
5786099bc8
|
Fix a issue of time comparison in benchmark when using cuDNN
|
2016-07-21 18:04:01 +09:00 |
|
nagadomi
|
b3c968ef11
|
Fix a bug in user method when scale=2
|
2016-07-20 14:06:17 +09:00 |
|
nagadomi
|
0b40d7db3f
|
Merge branch 'master' into upconv
|
2016-07-14 23:38:15 +09:00 |
|
nagadomi
|
be67a4e001
|
Fix a bug that the alpha channel is upscaled by noise_scale model
|
2016-07-14 23:38:04 +09:00 |
|
nagadomi
|
651e8f8ecb
|
Fix #129
|
2016-07-14 23:13:41 +09:00 |
|
nagadomi
|
58f7e53401
|
Update README.md #128
|
2016-07-14 22:21:04 +09:00 |
|
nagadomi
|
9563d84302
|
No bias at FullConvolution
|
2016-07-12 11:15:12 +09:00 |
|
nagadomi
|
6e089c699e
|
Update for #127
|
2016-07-11 10:49:20 +09:00 |
|
nagadomi
|
dd9aa370b3
|
Merge pull request #127 from adeldk/patch-2
Update fr.yml
|
2016-07-11 10:48:27 +09:00 |
|
Adel Duprat-Kissami
|
49f8e103f2
|
Update fr.yml
Added translation for `nr_low`.
|
2016-07-10 17:28:42 +01:00 |
|
nagadomi
|
93ea0e64df
|
Update README.md
|
2016-07-09 16:34:03 +09:00 |
|
nagadomi
|
e04650f94d
|
Change model links
|
2016-07-09 16:24:50 +09:00 |
|
nagadomi
|
6761b852b9
|
Update images
|
2016-07-09 15:42:50 +09:00 |
|
nagadomi
|
81df729a8a
|
Remove -loss option
|
2016-07-09 15:05:11 +09:00 |
|
nagadomi
|
83e5d885f5
|
Update scripts
|
2016-07-09 13:41:51 +09:00 |
|
nagadomi
|
0300c714eb
|
raise load error
|
2016-07-09 13:20:30 +09:00 |
|
nagadomi
|
7f6d113ff5
|
Update index.fr.html #123
|
2016-07-09 10:20:55 +09:00 |
|
nagadomi
|
7aef1435c5
|
Update fr.yml #123
|
2016-07-09 10:04:29 +09:00 |
|
nagadomi
|
a0d8826779
|
Merge branch 'master' into upconv
|
2016-07-09 09:58:48 +09:00 |
|
nagadomi
|
5ee954d8fe
|
Change web limits; hide TTA option
file limits: 3MB->5MB
image limits: 2560x2560->3000x3000, 1280x1280->1500x1500
|
2016-07-09 09:48:33 +09:00 |
|
nagadomi
|
9150618426
|
Add support for noise0 on web
|
2016-07-09 09:27:05 +09:00 |
|
nagadomi
|
8e90a44d30
|
noise0
|
2016-07-09 09:08:04 +09:00 |
|
nagadomi
|
cbe1874be3
|
Add noise0 model to photo/art
|
2016-07-09 09:06:51 +09:00 |
|
nagadomi
|
54b31e837d
|
Fix a bug in convert_data.lua
|
2016-07-07 11:22:12 +09:00 |
|
nagadomi
|
06e073089b
|
Fix for edac608f
|
2016-07-06 08:04:24 +09:00 |
|
nagadomi
|
14330e919c
|
tuning a little
|
2016-07-06 08:03:24 +09:00 |
|
nagadomi
|
deae802267
|
Fix a bug in noise reduction when using Y model
|
2016-07-06 00:47:58 +09:00 |
|
nagadomi
|
edac608f18
|
Add support for user specified pairwise data for universal filter
|
2016-07-05 02:42:40 +09:00 |
|
nagadomi
|
9ec1f5159b
|
Fix a bug in ClippedMSECriterion
|
2016-07-04 11:16:04 +09:00 |
|
nagadomi
|
d4dc8204a6
|
Fix .gitattributes
|
2016-07-04 05:08:38 +09:00 |
|
nagadomi
|
038f78604c
|
Add support for photo model in web.lua
|
2016-07-04 05:07:18 +09:00 |
|
nagadomi
|
ca6786b9dc
|
Add upconv_7/photo models. Update vgg_7/photo/noise* models
|
2016-07-04 04:51:22 +09:00 |
|
nagadomi
|
eeb90dc39b
|
Fix a bug in preprocessing when filters=box only
|
2016-06-22 00:37:29 +09:00 |
|
Adel Duprat-Kissami
|
2cdb8f9d65
|
Update fr.yml
- Updated `description`, `show_demonstration`, `go_to_github`, `upscaling`, `file_limits`.
- *Agrandissement* (enlargement) -> *Mise à l'échelle* (upscaling).
- Added translation for TTA-related strings.
|
2016-06-20 18:06:26 +00:00 |
|
nagadomi
|
708447a246
|
Update pretrained models. support for yuv420 jpeg
|
2016-06-20 15:58:11 +09:00 |
|
nagadomi
|
de669d24a4
|
Change default -validation_crops to 200.
|
2016-06-20 15:56:39 +09:00 |
|
nagadomi
|
d8fcde46f3
|
Change default -validation_crops to 200.
|
2016-06-20 15:56:26 +09:00 |
|
nagadomi
|
fb3636c3b7
|
Change noise rate in jpeg training
|
2016-06-20 15:55:43 +09:00 |
|
nagadomi
|
4379d4d0fd
|
Fix a inf in benchmark.lua
|
2016-06-19 22:28:42 +09:00 |
|
nagadomi
|
f61d59d28a
|
Change default params. enabling jpeg_chroma_subsampling by default
|
2016-06-18 20:27:34 +09:00 |
|
nagadomi
|
b89833daa3
|
Add -yuv420 option to tools/benchmark.lua
|
2016-06-18 20:25:47 +09:00 |
|
nagadomi
|
9d3e1a241e
|
refactor
|
2016-06-18 20:25:15 +09:00 |
|
nagadomi
|
2e26122a9e
|
performance tuning
|
2016-06-17 20:40:03 +09:00 |
|
nagadomi
|
416f9f2b40
|
Add -q (quiet) option to waifu2x.lua
|
2016-06-17 16:09:17 +09:00 |
|
nagadomi
|
96098d74d1
|
Merge pull request #120 from izzygomez/patch-1
(minor) Update README
|
2016-06-15 15:05:57 +09:00 |
|
Izzy Gomez
|
5138fc765d
|
(minor) Update README
It defaults to installing libgraphicsmagick1-dev anyways, so might as well make that clear.
|
2016-06-14 16:00:43 -07:00 |
|
nagadomi
|
53c3184765
|
Update prototxt
|
2016-06-13 17:36:52 +09:00 |
|
nagadomi
|
6e995bbc8b
|
Add benchmark results
|
2016-06-13 17:34:55 +09:00 |
|
nagadomi
|
a545bcffbd
|
Update models/upconv_7/art
|
2016-06-13 14:54:26 +09:00 |
|