 nagadomi
|
61f2abd632
remove unused code
|
8 years ago |
|
nagadomi
|
f088af9606
add srresnet_12l
|
8 years ago |
|
nagadomi
|
c8271af3ab
add srresnet_12l
|
8 years ago |
|
nagadomi
|
c63bb3b01f
Merge branch 'dev' of github.com:nagadomi/waifu2x into dev
|
8 years ago |
|
nagadomi
|
9a13392f91
Change the default -random_blur_sigma_max 0.75->1.0
|
8 years ago |
|
nagadomi
|
bdff13a35f
Use rgb2y instead of rgb2yuv
|
8 years ago |
|
nagadomi
|
4be1141292
Fix srresnet_2x
|
8 years ago |
|
nagadomi
|
bdaca16c67
perfomance tuning
|
8 years ago |
|
nagadomi
|
6220afc31a
Fix a bug in random negate
|
8 years ago |
|
nagadomi
|
74ed227f48
Update fcn_v1
|
8 years ago |
|
nagadomi
|
f16950438c
Fix tta-mode
|
8 years ago |
|
nagadomi
|
61aeb46303
Use bilinear instead of bicubic beacuse of overshoot
|
8 years ago |
|
nagadomi
|
b066761cdc
Add data augmentation for user method
|
8 years ago |
|
nagadomi
|
a72af8cfef
Use 'image' module because the deadlock problem has fixed
|
8 years ago |
|
nagadomi
|
4998078d2a
use threads.safe to avoid deadlock problem
|
8 years ago |
|
nagadomi
|
1e80e45a03
add experimental models
|
8 years ago |
|
nagadomi
|
ea64fe83bd
Update benchmark.md
|
8 years ago |
|
nagadomi
|
fa055c59b2
Update benchmark.md
|
8 years ago |
|
nagadomi
|
558527e268
merge
|
8 years ago |
|
nagadomi
|
50fd999c38
Add -gpu option
|
8 years ago |
|
nagadomi
|
16731fb634
Add support for scale4 in benchmark
|
8 years ago |
|
nagadomi
|
ef8bb4b0b9
update Benchmark.md
|
8 years ago |
|
nagadomi
|
83fc4684d8
update Benchmark.md
|
8 years ago |
|
nagadomi
|
6f437e4014
Update benchmark
|
8 years ago |
|
nagadomi
|
8d16fbaa9a
Update benchmark
|
8 years ago |
|
nagadomi
|
64952bad1f
Add upconv_7l models. only 2x.
|
8 years ago |
|
nagadomi
|
66bff68ef1
split first
|
8 years ago |
|
nagadomi
|
a604aa3b7a
Add some experimental model
|
8 years ago |
|
nagadomi
|
e71ff1fc6a
Fix a bug in random blur
|
8 years ago |
|
nagadomi
|
72862f182e
benchmark: add border option; use %.3f;
|
8 years ago |
