nagadomi
|
20abbbc68e
|
Support for binary model file
|
2018-10-03 18:42:05 +09:00 |
|
|
nagadomi
|
56536ac133
|
Add support for AuxiliaryLoss
|
2018-10-03 18:41:32 +09:00 |
|
|
nagadomi
|
cf638aea48
|
Add default option for ClippedMSECriterion
|
2018-10-03 18:40:04 +09:00 |
|
|
nagadomi
|
1dc32aaa89
|
Add w2nn.Print for debug
|
2018-10-03 18:30:54 +09:00 |
|
|
nagadomi
|
0fe21eef70
|
Update random erasing; Support x padding
|
2018-10-03 18:30:22 +09:00 |
|
|
nagadomi
|
93cd40a53c
|
merge random erasing
|
2018-10-03 18:29:05 +09:00 |
|
|
nagadomi
|
fa6ee00624
|
merge
|
2018-01-26 08:09:40 +09:00 |
|
|
nagadomi
|
4ec0b4530d
|
merge
|
2018-01-26 08:08:52 +09:00 |
|
|
nagadomi
|
cba96e36fb
|
Add -invert_x option for user_method
|
2017-05-17 08:51:07 +09:00 |
|
|
nagadomi
|
05bc54fa12
|
Add support for identity initializer for dilated convolution, and refactor
|
2017-04-21 08:54:39 +09:00 |
|
|
nagadomi
|
fe885a3466
|
Fix -pairwise_y_binary
|
2017-04-16 04:38:53 +09:00 |
|
|
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 |
|