nagadomi
2b9753157a
simplify
2015-11-06 08:04:43 +09:00
nagadomi
1f91548c6e
Fix model loading error when using ukbench model; Add error handling
2015-11-05 16:17:55 +09:00
nagadomi
1a20ec501b
Fix the evaluation metric in benchmark
2015-11-05 15:18:49 +09:00
nagadomi
44208f18ab
Fix handling for gamma embed PNG
2015-11-05 14:59:51 +09:00
nagadomi
bbd0ff39ad
Fix handling for CMYK JPEG
2015-11-03 23:20:21 +09:00
nagadomi
ee19e2608e
update README for dev
2015-11-03 06:19:36 +09:00
nagadomi
b35a9ae7d7
tuning
2015-11-03 06:10:44 +09:00
nagadomi
425898a3aa
Don't use cudnn.benchmark mode when predicting
2015-10-31 22:09:21 +09:00
nagadomi
490eb33a6b
Minimize the weighted huber loss instead of the weighted mean square error
...
Huber loss is less sensitive to outliers(i.e. noise) in data than the squared error loss.
2015-10-31 22:05:59 +09:00
nagadomi
243d8821be
Add -backend option to use cuDNN
2015-10-31 04:38:28 +09:00
nagadomi
9ddee6088d
Add WeightedHuberCriterion
2015-10-31 04:36:20 +09:00
nagadomi
9d63ed2947
Fix gradient scale in WeightedMSECriterion
2015-10-31 04:35:33 +09:00
nagadomi
4c691b4640
refactor
2015-10-29 22:44:15 +09:00
nagadomi
21ea5dd858
add cudnn converter
2015-10-29 18:05:33 +09:00
nagadomi
da786e15ba
remove noise_scale training
2015-10-28 16:27:31 +09:00
nagadomi
3abc5a03e3
refactor
2015-10-28 16:01:07 +09:00
nagadomi
cb81d21064
Add notice for v1.0 branch
2015-10-26 10:05:58 +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
36a53fa0c5
Update the torch7 install instruction in README
2015-10-12 02:08:00 +09:00
nagadomi
f399b34799
Added support for ru in nginx.conf
2015-09-07 15:16:44 +09:00
nagadomi
b35798016e
Added support for index.ru.html in web.lua
2015-09-07 14:51:56 +09:00
vitaliylag
7aab0b4e12
typo
2015-09-07 06:59:10 +03:00
vitaliylag
dcba842b51
Update index.ru.html
2015-09-07 06:40:05 +03:00
vitaliylag
9475d2e885
Update index.html
2015-09-07 06:38:07 +03:00
vitaliylag
fc021b5fe8
Create index.ru.html
2015-09-07 02:54:21 +03:00
vitaliylag
749d7b2f67
Update index.ja.html
2015-09-07 02:53:49 +03:00
vitaliylag
4628671201
Update index.html
2015-09-07 02:52:55 +03:00
nagadomi
42d11a9be0
Merge pull request #48 from mrkn/patch-1
...
Fix typo
2015-08-30 18:57:59 +09:00
Kenta Murata
306ee3c76d
Fix typo
2015-08-30 10:47:20 +09:00
nagadomi
6cab1329dd
Merge pull request #46 from KevinFrans3/master
...
Added descriptions on how to install cuda
2015-08-26 14:05:42 +09:00
Kevin Frans
ef9e1c42ce
Added descriptions on how to install cud
2015-08-25 20:27:55 -07:00
nagadomi
8c7bda11fb
add new AMI
2015-08-12 23:06:27 +09:00
nagadomi
291a139ed8
improve nginx config
2015-08-12 23:01:45 +09:00
nagadomi
0b9a8b514c
Merge pull request #44 from nagadomi/remove_cunn_rescue
...
explicitly loading torch/cutorch
2015-08-05 16:22:31 +09:00
nagadomi
ee826715b7
explicitly loading torch/cutorch
2015-08-05 16:20:45 +09:00
nagadomi
e62c424109
Merge pull request #43 from nagadomi/remove_cunn_rescue
...
remove exception handling for cunn
2015-08-05 16:06:39 +09:00
nagadomi
2ffa93213e
remove exception handling for cunn
2015-08-05 16:03:51 +09:00
nagadomi
716b8abb8b
Merge pull request #42 from nagadomi/fix_nn_issue
...
fix missing nn in latest torch7
2015-08-05 11:51:39 +09:00
nagadomi
dcd43b89fd
fix missing nn in latest torch7
2015-08-05 11:49:38 +09:00
nagadomi
54580ba8c0
add data augmentation method that uses overlay
2015-08-02 22:02:14 +09:00
nagadomi
3438692f49
Merge pull request #39 from nagadomi/set_compression_level
...
fix slow compression
2015-07-25 02:41:27 +09:00
nagadomi
6c65463564
fix slow compression
2015-07-25 02:39:36 +09:00
nagadomi
4221c19839
Merge pull request #38 from nagadomi/set_compression_level
...
set compression level of the output file
2015-07-24 17:19:19 +09:00
nagadomi
e5a2ef97c7
set compression level of the output file
2015-07-24 17:16:27 +09:00
nagadomi
33389d5d22
update anime_style_art_rgb/noise1 and anime_style_art_rgb/noise2
2015-07-18 11:37:06 +09:00
nagadomi
8e1625d001
change the noisy:cleaned ratio of training data
2015-07-18 11:17:34 +09:00
nagadomi
2c00335f96
update anime_style_art_rgb/scale2.0x_model
2015-07-12 00:03:24 +09:00
nagadomi
e3d3a8355c
change training script
...
- add AlexNet's color noise (default: false)
- add `photo` category for noise level setting
2015-07-11 21:57:04 +09:00
nagadomi
99db05a753
fix image size validation in convert.lua
2015-07-11 21:53:45 +09:00
