nagadomi
bb0fc3a1d3
Add -validation_filename_split option
2017-04-15 16:29:38 +09:00
nagadomi
88e3322296
Add ShakeShakeTable
2017-04-13 17:35:32 +09:00
nagadomi
f54dd37848
Merge branch 'dev'
2017-04-10 20:22:37 +09:00
nagadomi
b7e116de54
Add support for multi GPU training (data parallel)
...
train.lua -gpu 1,3,4
When use multi GPU mode, nccl.torch is required.
2017-04-10 20:20:17 +09:00
nagadomi
f0fc2c89d1
Add support for grayscale data
2017-04-09 20:53:53 +09:00
nagadomi
71a34393b8
Add support for padding in convert_data.lua
2017-04-08 22:01:13 +09:00
nagadomi
eb3926b61c
Fix to work on Lua52
...
web.lua does not work on Lua52 because turbo does not support Lua52 FFI.
2017-03-02 14:47:49 +09:00
nagadomi
780e22cf51
Fix io.read option
2017-03-01 15:17:09 +09:00
nagadomi
ed12b43477
Change downsampling filters in pairwise_scale()
2017-02-26 09:01:26 +09:00
nagadomi
cdafbf00ae
Add BCE(binary cross entropy) loss for segmentation
...
Sigmoid() output is required.
2017-02-23 08:48:00 +09:00
nagadomi
385020e0e1
Fix a bug of 763f5ddcab
2017-02-19 01:42:40 +09:00
nagadomi
8b5ccbed08
Merge branch 'dev' of into dev
2017-02-12 17:48:44 +09:00
nagadomi
c6e3a68974
Optimize flip in user method when -patchs is small
2017-02-12 17:48:21 +09:00
nagadomi
763f5ddcab
Fix crop bug in rare case
2017-02-12 17:46:07 +09:00
nagadomi
1db2eeb788
Merge branch 'master' of github.com:nagadomi/waifu2x into dev
2017-02-12 17:27:33 +09:00
nagadomi
d6f5e48dab
Add support for icc profile
2017-02-12 17:19:03 +09:00
nagadomi
29260ede24
fix batchwise psnr
2017-02-12 02:04:23 +09:00
nagadomi
b111901cbb
add -update_criterion option for back compatible
2017-02-12 01:56:03 +09:00
nagadomi
3447c6c44c
rename srresnet_12l to resnet_14l because it's not the same as SRResNet
2017-01-21 16:53:10 +09:00
nagadomi
0eccbc6555
Add support for MSE loss
2017-01-09 13:00:04 +09:00
nagadomi
6051dad793
Fix a bug in ClippedMSECriterion:backward
2017-01-09 12:55:50 +09:00
nagadomi
742c9fdd95
disable gcn
2017-01-09 12:51:45 +09:00
nagadomi
43a9b58fcb
Add GCN option for user method
2016-12-25 20:17:47 +09:00
nagadomi
d2cfb8f104
Add L1 criterion. Change the criterion of updating model
2016-12-05 10:32:26 +09:00
nagadomi
61f2abd632
remove unused code
2016-11-09 03:10:54 +09:00
nagadomi
f088af9606
add srresnet_12l
2016-11-09 03:06:57 +09:00
nagadomi
c8271af3ab
add srresnet_12l
2016-11-09 03:06:26 +09:00
nagadomi
9a13392f91
Change the default -random_blur_sigma_max 0.75->1.0
2016-11-06 18:14:27 +09:00
nagadomi
bdff13a35f
Use rgb2y instead of rgb2yuv
2016-11-06 05:32:36 +09:00
nagadomi
4be1141292
Fix srresnet_2x
2016-11-06 01:19:20 +09:00
nagadomi
bdaca16c67
perfomance tuning
2016-11-02 23:42:14 +09:00
nagadomi
6220afc31a
Fix a bug in random negate
2016-10-24 17:23:09 +09:00
nagadomi
74ed227f48
Update fcn_v1
2016-10-24 09:10:17 +09:00
nagadomi
f16950438c
Fix tta-mode
2016-10-24 09:06:27 +09:00
nagadomi
61aeb46303
Use bilinear instead of bicubic beacuse of overshoot
2016-10-22 15:11:05 +09:00
nagadomi
b066761cdc
Add data augmentation for user method
2016-10-21 18:34:48 +09:00
nagadomi
a72af8cfef
Use 'image' module because the deadlock problem has fixed
2016-10-21 01:21:42 +09:00
nagadomi
1e80e45a03
add experimental models
2016-10-20 23:41:39 +09:00
nagadomi
50fd999c38
Add -gpu option
2016-10-18 19:54:00 +09:00
nagadomi
a604aa3b7a
Add some experimental model
2016-10-08 17:21:01 +09:00
nagadomi
e71ff1fc6a
Fix a bug in random blur
2016-10-05 18:48:32 +09:00
nagadomi
3e77378983
Add SSIMCriterion (supports only forward())
2016-10-02 22:22:50 +09:00
nagadomi
d7ab10581c
Use clamp
2016-09-24 08:17:37 +09:00
nagadomi
f1a45b19c5
test
2016-09-24 07:46:50 +09:00
nagadomi
0517605d0d
Remove flip() from preprocess() because the data will flip() at flip_augmentation()
2016-09-24 06:22:30 +09:00
nagadomi
f65132dadb
Use conv2d instead of nn.SpatialConvolutionMM
2016-09-24 05:54:18 +09:00
nagadomi
5a3d012f4e
Add random blur method for data augmentation
2016-09-24 05:32:33 +09:00
nagadomi
cabeeed2a7
Add Clip(0,1) to last layer
2016-09-14 21:23:29 +09:00
nagadomi
f11108cba1
Add comment about RNG seed
2016-09-14 21:19:59 +09:00
nagadomi
451ee1407f
Stop calculate the instance loss when oracle_rate=0
2016-09-11 20:59:32 +09:00
nagadomi
c2e4bb4380
Support for multi-thread in training
...
And remove `sys`,`image` and `graphicsmagicks.conveter` from the training code because those causes the deadlock on thread package.
2016-09-11 06:31:44 +09:00
nagadomi
f7e83e4465
performance tuning
2016-09-08 22:35:27 +09:00
nagadomi
382d493514
no confidence change for #128
2016-07-27 22:55:56 +09:00
nagadomi
b3c968ef11
Fix a bug in user method when scale=2
2016-07-20 14:06:17 +09:00
nagadomi
9563d84302
No bias at FullConvolution
2016-07-12 11:15:12 +09:00
nagadomi
81df729a8a
Remove -loss option
2016-07-09 15:05:11 +09:00
nagadomi
a0d8826779
Merge branch 'master' into upconv
2016-07-09 09:58:48 +09:00
nagadomi
8e90a44d30
noise0
2016-07-09 09:08:04 +09:00
nagadomi
06e073089b
Fix for edac608f
2016-07-06 08:04:24 +09:00
nagadomi
14330e919c
tuning a little
2016-07-06 08:03:24 +09:00
nagadomi
deae802267
Fix a bug in noise reduction when using Y model
2016-07-06 00:47:58 +09:00
nagadomi
edac608f18
Add support for user specified pairwise data for universal filter
2016-07-05 02:42:40 +09:00
nagadomi
9ec1f5159b
Fix a bug in ClippedMSECriterion
2016-07-04 11:16:04 +09:00
nagadomi
eeb90dc39b
Fix a bug in preprocessing when filters=box only
2016-06-22 00:37:29 +09:00
nagadomi
d8fcde46f3
Change default -validation_crops to 200.
2016-06-20 15:56:26 +09:00
nagadomi
fb3636c3b7
Change noise rate in jpeg training
2016-06-20 15:55:43 +09:00
nagadomi
f61d59d28a
Change default params. enabling jpeg_chroma_subsampling by default
2016-06-18 20:27:34 +09:00
nagadomi
9d3e1a241e
refactor
2016-06-18 20:25:15 +09:00
nagadomi
2e26122a9e
performance tuning
2016-06-17 20:40:03 +09:00
nagadomi
e50c7d1478
Remove unused modules
2016-06-13 12:48:11 +09:00
nagadomi
3b1b2d03fe
Change default -nr_rate to 0.65
2016-06-13 12:44:32 +09:00
nagadomi
25e293202a
Add support for tta_level=1; Add support for TTA to web.lua
2016-06-12 16:55:05 +09:00
nagadomi
af74a67bd1
Add -force_cudnn option; support for cuDNN in waifu2x.lua/web.lua
2016-06-12 16:33:50 +09:00
nagadomi
6be1479710
Fix a block_size issue when using upconv_7 model
2016-06-12 05:15:24 +09:00
nagadomi
9103d393fe
Fix a performance issue
2016-06-12 05:13:40 +09:00
nagadomi
b8ff8c6787
Remove -gamma_correction option
2016-06-10 07:37:39 +09:00
nagadomi
01b2e6d441
Remove -upsampling_filter option
2016-06-10 07:34:11 +09:00
nagadomi
afac4b52ab
Add -batch_size option to waifu2x.lua/web.lua
2016-06-09 14:03:18 +09:00
nagadomi
0b949c05a7
Add support for TTA level
2016-06-09 13:09:28 +09:00
nagadomi
9514027f65
Fix a bug that -nr_rate is not used
2016-06-09 02:44:22 +09:00
nagadomi
e5cfd3dfce
Add -resume option
2016-06-09 02:39:52 +09:00
nagadomi
51914b894a
change weight initialization and upconv_7
2016-06-08 06:58:46 +09:00
nagadomi
307ae40883
Add noise_scale training
2016-06-08 06:39:36 +09:00
nagadomi
d0630d3a20
individual filters and box-only support
2016-06-06 14:04:13 +09:00
nagadomi
0349fc774c
refactor
2016-06-02 10:12:04 +09:00
nagadomi
c89fd7249a
Add learning_rate_decay
2016-06-02 10:11:15 +09:00
nagadomi
70eb2b508f
Fix a performance problem in resampling
2016-05-30 19:15:54 +09:00
nagadomi
70a2849e39
Fix missing file
2016-05-30 06:48:26 +09:00
nagadomi
99e6dd1a57
Fix border removing
2016-05-28 10:25:08 +09:00
nagadomi
8a65db7bab
Change the evaluation metric
2016-05-27 16:57:14 +09:00
nagadomi
8088460a20
Add oracle_rate option
2016-05-27 16:54:29 +09:00
nagadomi
7814691cbf
Add resize_blur parameter
...
latest graphicsmagick is required
2016-05-21 09:54:12 +09:00
nagadomi
145b47dbf5
Add use_transparent_png option
2016-05-19 23:02:02 +09:00
nagadomi
f6a37b66c3
Add support for Transparent PNG in convert_data.lua
2016-05-15 12:34:03 +09:00
nagadomi
8d3950b90a
Change the default parameter (epoch, downsampling_filters)
2016-05-15 11:33:34 +09:00
nagadomi
c028ce6e4f
Fix a bug in reconstrct.scale() when inner_scale > 1 && y only model
2016-05-15 11:31:14 +09:00
nagadomi
a210090033
Convert model files; Add new pretrained model
...
- Add new pretrained model to ./models/upconv_7
- Move old models to ./models/vgg_7
- Use nn.LeakyReLU instead of w2nn.LeakyReLU
- Add useful attribute to .json
New JSON attribute:
The first layer has `model_config` attribute.
It contains:
model_arch: architecture name of model. see `lib/srcnn.lua`
scale_factor: if scale_factor > 1, model:forward() changes image resolution with scale_factor.
channels: input/output channels. if channels == 3, model is RGB model.
offset: pixel size that is to be removed from output.
for example:
(scale_factor=1, offset=7, input=100x100) => output=(100-7)x(100-7)
(scale_factor=2, offset=12, input=100x100) => output=(100*2-12)x(100*2-12)
And each layer has `class_name` attribute.
2016-05-15 03:04:08 +09:00
nagadomi
48411a4dde
refactor
2016-05-14 16:51:36 +09:00
nagadomi
51ae485cd1
Add new models
...
upconv_7 is 2.3x faster than previous model
2016-05-13 09:49:53 +09:00
nagadomi
e62305377f
Add compression.size()
2016-05-13 09:35:53 +09:00
