nagadomi
4a4885c856
Add -white_noise option
...
post-processing for anime screencap.
2015-11-11 10:42:33 +09:00
nagadomi
0941d098e1
more round
2015-11-10 22:38:22 +09:00
nagadomi
2d5a090305
Change default -nr_rate
2015-11-10 22:07:45 +09:00
nagadomi
eaeaef10b7
more flip
2015-11-09 23:45:01 +09:00
nagadomi
7ac7923345
Don't run model2 benchmark when model2_dir is not specified
2015-11-09 06:23:57 +09:00
nagadomi
af1b9c604b
refactor
2015-11-09 04:35:11 +09:00
nagadomi
c21516f04d
Fix unused crop_size option
2015-11-09 04:10:51 +09:00
nagadomi
b335f3a9ad
Add -tta option
...
The TTA mode:
- 8x slower than normal mode
- improves PSNR +0.1
2015-11-09 04:01:28 +09:00
nagadomi
4322b63750
Set cuda():evaluate()
2015-11-09 03:45:03 +09:00
nagadomi
986ef34ffc
Add color and gamma attribute to json file
2015-11-08 22:12:48 +09:00
nagadomi
7d67afb982
Use iproc.crop instead of image.crop
2015-11-08 22:11:36 +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
180e7676e4
Drop full transparent background
2015-11-08 06:32:15 +09:00
nagadomi
797b45ae23
Use roundf-like clip for 8 bit-depth image
...
Maybe PSNR +0.03 improved by this commit
2015-11-08 05:44:14 +09:00
nagadomi
bd63f99b59
clip
2015-11-08 01:21:52 +09:00
nagadomi
df1c1b2c1e
tools/bechmark.lua: Add -filter option. refactor
2015-11-07 23:44:37 +09:00
nagadomi
57115bdcac
Add -depth option
2015-11-07 23:01:57 +09:00
nagadomi
3b2aa67e55
Improve web interface
2015-11-07 22:54:29 +09:00
nagadomi
15f3f2d901
typo
2015-11-07 07:38:45 +09:00
nagadomi
84c38baab7
Fix double loading of image
2015-11-07 07:33:41 +09:00
nagadomi
3ea16b3b86
tunable parameters
2015-11-07 07:18:22 +09:00
nagadomi
cf862782a5
depth 8
2015-11-07 06:39:47 +09:00
nagadomi
c773e18e59
Add trade-off parameter for noise reduction
2015-11-07 06:37:53 +09:00
nagadomi
43832a9f92
Add support for depth of PNG
2015-11-06 13:12:36 +09:00
nagadomi
539941c234
Add support for url cache in web.lua
2015-11-06 12:24:27 +09:00
nagadomi
5db37f3392
Fix README syntax
2015-11-06 10:49:08 +09:00
nagadomi
7856ba90c7
Update trained models
2015-11-06 10:43:05 +09:00
nagadomi
268b9f6671
refactor tools/export_model.lua
2015-11-06 10:42:37 +09:00
nagadomi
6924920a2f
Fix tools/cudnn2cunn.lua no effect
2015-11-06 10:32:13 +09:00
nagadomi
903d945652
cleanup
2015-11-06 10:08:54 +09:00
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
