 nagadomi
|
be67a4e001
Fix a bug that the alpha channel is upscaled by noise_scale model
|
9 years ago |
|
nagadomi
|
edac608f18
Add support for user specified pairwise data for universal filter
|
9 years ago |
|
nagadomi
|
416f9f2b40
Add -q (quiet) option to waifu2x.lua
|
9 years ago |
|
nagadomi
|
af74a67bd1
Add -force_cudnn option; support for cuDNN in waifu2x.lua/web.lua
|
9 years ago |
|
nagadomi
|
599da6a665
refactor
|
9 years ago |
|
nagadomi
|
01b2e6d441
Remove -upsampling_filter option
|
9 years ago |
|
nagadomi
|
afac4b52ab
Add -batch_size option to waifu2x.lua/web.lua
|
9 years ago |
|
nagadomi
|
0b949c05a7
Add support for TTA level
|
9 years ago |
|
nagadomi
|
37bc7a5eea
Add support for new noise_scale method
|
9 years ago |
|
nagadomi
|
abae4cb855
Fix processing time
|
9 years ago |
|
nagadomi
|
a210090033
Convert model files; Add new pretrained model
|
9 years ago |
|
nagadomi
|
1464b0db3e
Improve output file format
|
9 years ago |
|
nagadomi
|
3a27e122ac
Add support for grayscale output
|
9 years ago |
|
nagadomi
|
fbad30c031
Fix embed gamma handling
|
9 years ago |
|
nagadomi
|
30fe5db735
Add upsampling_filter option
|
9 years ago |
|
nagadomi
|
86ad50f7cd
Merge branch 'master' of github.com:nagadomi/waifu2x into dev
|
9 years ago |
|
nagadomi
|
57e0f52b41
Reduce memory usage
|
9 years ago |
|
nagadomi
|
8a799e2d56
Add support for noise level 3
|
9 years ago |
|
nagadomi
|
c4df6f11f4
Fix error in video conversion
|
10 years ago |
|
nagadomi
|
d2c081bbcf
Improve alpha channel handling #29
|
10 years ago |
|
nagadomi
|
4a4885c856
Add -white_noise option
|
10 years ago |
|
nagadomi
|
c21516f04d
Fix unused crop_size option
|
10 years ago |
|
nagadomi
|
b335f3a9ad
Add -tta option
|
10 years ago |
|
nagadomi
|
5ab2c605c8
Fix header include order issues
|
10 years ago |
|
nagadomi
|
57115bdcac
Add -depth option
|
10 years ago |
|
nagadomi
|
903d945652
cleanup
|
10 years ago |
|
nagadomi
|
1f91548c6e
Fix model loading error when using ukbench model; Add error handling
|
10 years ago |
|
nagadomi
|
425898a3aa
Don't use cudnn.benchmark mode when predicting
|
10 years ago |
|
nagadomi
|
3abc5a03e3
refactor
|
10 years ago |
|
nagadomi
|
8dea362bed
sync from internal repo
|
10 years ago |
