 nagadomi
|
bd63f99b59
clip
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
df1c1b2c1e
tools/bechmark.lua: Add -filter option. refactor
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
57115bdcac
Add -depth option
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
3b2aa67e55
Improve web interface
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
15f3f2d901
typo
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
84c38baab7
Fix double loading of image
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
3ea16b3b86
tunable parameters
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
cf862782a5
depth 8
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
c773e18e59
Add trade-off parameter for noise reduction
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
43832a9f92
Add support for depth of PNG
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
539941c234
Add support for url cache in web.lua
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
5db37f3392
Fix README syntax
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
7856ba90c7
Update trained models
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
268b9f6671
refactor tools/export_model.lua
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
6924920a2f
Fix tools/cudnn2cunn.lua no effect
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
903d945652
cleanup
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
2b9753157a
simplify
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
1f91548c6e
Fix model loading error when using ukbench model; Add error handling
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
1a20ec501b
Fix the evaluation metric in benchmark
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
44208f18ab
Fix handling for gamma embed PNG
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
bbd0ff39ad
Fix handling for CMYK JPEG
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
ee19e2608e
update README for dev
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
b35a9ae7d7
tuning
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
425898a3aa
Don't use cudnn.benchmark mode when predicting
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
490eb33a6b
Minimize the weighted huber loss instead of the weighted mean square error
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
243d8821be
Add -backend option to use cuDNN
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
9ddee6088d
Add WeightedHuberCriterion
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
9d63ed2947
Fix gradient scale in WeightedMSECriterion
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
4c691b4640
refactor
|
%!s(int64=9) %!d(string=hai) anos |
|
nagadomi
|
21ea5dd858
add cudnn converter
|
%!s(int64=9) %!d(string=hai) anos |
