nagadomi
6c758ec5c0
Correct messages
2016-06-08 07:52:38 +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
3b09bff8cf
randomly swap fg/bg color in dots/gen
2016-06-08 06:38:26 +09:00
nagadomi
d0630d3a20
individual filters and box-only support
2016-06-06 14:04:13 +09:00
nagadomi
5e222a3981
Add -tta and -resize_blur option to benchmark
2016-06-02 10:15:54 +09:00
nagadomi
abae4cb855
Fix processing time
2016-06-02 10:13:07 +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
634046d5f0
Fix training mode
2016-05-29 05:50:53 +09:00
nagadomi
b96bc5d453
Use correct criterion
2016-05-28 10:56:15 +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
8fec6f1b5a
Change the learning rate decay rate
2016-05-21 09:56:26 +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
db68eb208e
Add caffe.prototxt example
2016-05-15 16:50:47 +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
nagadomi
b8088ca209
Remove the limit of learning_rate_decay
2016-04-30 13:48:24 +09:00
nagadomi
8da52d5fb9
Merge from master
2016-04-23 12:48:24 +09:00
nagadomi
1464b0db3e
Improve output file format
...
supported format variable:
%s: basename of the source filename
%d: sequence number
example:
output/2x/%s.png
output/%d.png
output/%06d_%s.png
output/%s_%d.png
2016-04-23 12:44:40 +09:00
nagadomi
7af5c9443d
Add model option and 12 layers net
2016-04-23 09:19:03 +09:00
nagadomi
da03209d3e
Remove PNG compression option
2016-04-20 18:53:31 +09:00
nagadomi
212b659ec5
Fix web page layout
2016-04-18 09:47:05 +09:00
nagadomi
1760c518be
Update fr
2016-04-18 09:23:49 +09:00
Adel Duprat-Kissami
d19f086f14
Update fr.yml
...
- Added translation for 'nr_highest'. "Maximale" sounds like a better fit than "Très haute" (Very High) or "La plus haute" (translated literally).
- Updated description.
- [URL is feminine in French.](https://fr.wikipedia.org/wiki/Uniform_Resource_Locator )
- [artefacts -> artéfacts.](https://en.wiktionary.org/wiki/Appendix:French_spelling_reforms_of_1990 )
- [MB -> Mo.](fr.wikipedia.org/wiki/Octet)
- [Unlike English, French has a space before colons.](http://www.oxforddictionaries.com/words/french-usage-notes-for-english-speakers-translating-into-french-33-spelling-and-punctuation )
- Various improvements.
2016-04-17 19:37:37 +01:00
nagadomi
68a6d4cef5
Use MSE instead of PSNR
...
PSNR depends on the minibatch size and those group.
2016-04-17 02:08:38 +09:00
nagadomi
d8083dde89
Merge pull request #103 from nagadomi/add_simplefied_chainese
...
Add Simplified Chinese Locale
2016-04-17 00:00:37 +09:00
nagadomi
b9a50f9422
Add Simplified Chinese Translation
2016-04-16 23:56:22 +09:00
nagadomi
439bf19b63
Revert sc.yml to zh-CN.yml
2016-04-16 23:48:29 +09:00
nagadomi
2c531955ae
Fix unreasonable file selection in webgen/gen.rb
2016-04-16 23:43:07 +09:00
tenyuhuang
08649a0e21
Update sc.yml
2016-04-16 23:31:52 +09:00
tenyuhuang
2fa6a89500
Update sc.yml
2016-04-16 23:31:33 +09:00
tenyuhuang
732581472f
Rename zh-cn.yml to sc.yml
2016-04-16 23:31:06 +09:00
tenyuhuang
38745c3f20
Add Simplified Chinese Translation
2016-04-16 23:31:00 +09:00
nagadomi
fa9355be7c
Fix validation metric
2016-04-16 03:52:05 +09:00
nagadomi
a92b2cb386
Fix progressbar
2016-04-16 03:45:21 +09:00
nagadomi
ea780f1871
Fix validation metric
2016-04-16 03:23:37 +09:00
nagadomi
ac9b6f1149
Merge branch 'dev' of private repo into dev
2016-04-15 13:32:02 +09:00
nagadomi
3a27e122ac
Add support for grayscale output
2016-04-15 13:29:50 +09:00
nagadomi
ba2fe8d9c1
Improve alpha channel detection
...
latest `graphicsmagick` is required.
2016-04-15 13:14:10 +09:00
