1
0
Fork 0
mirror of synced 2024-09-21 20:11:38 +12:00
Commit graph

76 commits

Author SHA1 Message Date
nagadomi
13f702b968 Add support for resizing with gamma correction 2016-03-28 19:07:09 +09:00
nagadomi
29dc96eadf Remove unused attributes in json 2016-03-27 17:37:38 +09:00
nagadomi
664322fa97 Remove cleanup_model.lua; Change model format from binary to ascii 2016-03-12 05:20:19 +09:00
nagadomi
ff63a28540 Add tools/rebuild_model 2016-01-23 09:38:40 +09:00
nagadomi
56296c25b3 refactor 2015-11-27 13:15:37 +09:00
nagadomi
dde2cdf294 Fix denoising benchmark 2015-11-27 13:07:00 +09:00
nagadomi
3c9726da81 rmse 2015-11-27 12:50:09 +09:00
nagadomi
4551ddaaa6 Add support to reproduce the dynamic range bug in PSNR
I think some academic paper has this bug.
2015-11-25 14:42:38 +09:00
nagadomi
b829595c21 Make compatible with MATLAB based benchmarks 2015-11-23 00:41:22 +09:00
nagadomi
abedec9d9b Fix filter name for graphicsmagick
graphicsmagick package has bug in the definition of FilteTypes.
I will send PR to fix that bug.
This commit is related to it.
You should upgrade graphicsmagick package.

$ luarocks install graphicsmagick
2015-11-21 11:57:33 +09:00
nagadomi
e9187ecf1c load float images directly 2015-11-21 00:58:30 +09:00
nagadomi
c47df93505 show baseline 2015-11-21 00:29:57 +09:00
nagadomi
7ac7923345 Don't run model2 benchmark when model2_dir is not specified 2015-11-09 06:23:57 +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
5ab2c605c8 Fix header include order issues 2015-11-08 18:31:46 +09:00
nagadomi
df1c1b2c1e tools/bechmark.lua: Add -filter option. refactor 2015-11-07 23:44:37 +09:00
nagadomi
3b2aa67e55 Improve web interface 2015-11-07 22:54:29 +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
2b9753157a simplify 2015-11-06 08:04:43 +09:00
nagadomi
1a20ec501b Fix the evaluation metric in benchmark 2015-11-05 15:18:49 +09:00
nagadomi
425898a3aa Don't use cudnn.benchmark mode when predicting 2015-10-31 22:09:21 +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
3abc5a03e3 refactor 2015-10-28 16:01:07 +09:00