nagadomi
30fe5db735
Add upsampling_filter option
2016-04-02 22:03:27 +09:00
nagadomi
13f702b968
Add support for resizing with gamma correction
2016-03-28 19:07:09 +09:00
nagadomi
d4833160c7
Optionalize downsampling filters
2016-03-17 17:58:37 +09:00
nagadomi
4d115e4bdb
Add support for plotting loss chart
2016-03-14 05:06:14 +09:00
nagadomi
459c7c5e18
Use similar distribution on train/validation
2016-03-12 08:50:55 +09:00
nagadomi
1900ac7500
Use PSNR for evaluation
2016-03-12 06:53:42 +09:00
nagadomi
664322fa97
Remove cleanup_model.lua; Change model format from binary to ascii
2016-03-12 05:20:19 +09:00
nagadomi
290a5f960b
Use Huber loss instead of MSE
2016-03-11 11:13:45 +09:00
nagadomi
9b238bd693
Use clearState()
2016-03-11 11:12:02 +09:00
nagadomi
9f935835dd
Add -save_history option
2015-12-04 18:49:34 +09:00
nagadomi
aaac6ed6e5
Refactor training loop
...
more shuffle
2015-11-30 17:18:52 +09:00
nagadomi
c72ec3112b
Add -random_unsharp_mask_rate option for photo
2015-11-27 18:36:36 +09:00
nagadomi
d8ba661d6b
Add -jpeg_chroma_subsampling_rate option for JPEG denoise training
2015-11-26 17:10:57 +09:00
nagadomi
42bd89151e
Add -gpu option in train.lua
2015-11-13 19:26:58 +09:00
nagadomi
5ab2c605c8
Fix header include order issues
2015-11-08 18:31:46 +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
3ea16b3b86
tunable parameters
2015-11-07 07:18:22 +09:00
nagadomi
c773e18e59
Add trade-off parameter for noise reduction
2015-11-07 06:37:53 +09:00
nagadomi
903d945652
cleanup
2015-11-06 10:08:54 +09:00
nagadomi
b35a9ae7d7
tuning
2015-11-03 06:10:44 +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
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
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
nagadomi
54580ba8c0
add data augmentation method that uses overlay
2015-08-02 22:02:14 +09:00
nagadomi
e3d3a8355c
change training script
...
- add AlexNet's color noise (default: false)
- add `photo` category for noise level setting
2015-07-11 21:57:04 +09:00
nagadomi
fd9dadd7a4
use settings.validation_crop
2015-06-26 20:12:51 +09:00
nagadomi
5b4d692f03
add support for RGB color space reconstruction
...
- add new RGB model (models/anime_style_art_rgb).
- RGB model can reduce color noise.
- waifu2x uses this RGB model by default.
You can use Y model with:
$ th waifu2x.lua -model_dir models/anime_style_art -i input.png -o output.png
$ th train.lua -color y ...
2015-06-23 02:55:30 +09:00
nagadomi
a706892b59
merge develop repo
...
- remove support for cuDNN
- add new pre-trained model and json files
- some changes in training script
If you have cuDNN model, Please run following commands to convert.
$ cp models/your_own_model.t7 models/your_own_model.t7.backup
$ th cudnn2cunn.lua -model models/your_own_model.t7
2015-06-13 15:20:40 +09:00
nagadomi
1c1f2292d1
fix ugly chroma scaling
2015-05-22 20:06:25 +09:00
nagadomi
ffd52fdb2b
super typo fix
2015-05-19 16:47:52 +09:00
nagadomi
2231423056
update training script
2015-05-17 14:43:07 +09:00
nagadomi
1273b3609e
first commit
2015-05-16 14:48:05 +09:00
