nagadomi
|
715b6f0d28
|
Fix LBPCriterion #316
|
2019-11-27 13:58:35 +09:00 |
|
|
nagadomi
|
128222332b
|
Add license of RandomBinaryConvolution.lua
|
2018-12-15 14:38:56 +09:00 |
|
|
nagadomi
|
9a89ddd20e
|
remove unused model
|
2018-11-14 17:40:48 +09:00 |
|
|
nagadomi
|
d5c2277e0e
|
misc
|
2018-11-14 17:21:34 +09:00 |
|
|
nagadomi
|
dd8cb71601
|
clean
|
2018-11-14 07:51:14 +09:00 |
|
|
nagadomi
|
9589259812
|
Revert "defualt oracle_rate=0"
This reverts commit 98a091a7cb.
|
2018-11-05 09:29:33 +09:00 |
|
|
nagadomi
|
86d8fe96da
|
performance tuning
|
2018-11-05 00:19:09 +09:00 |
|
|
nagadomi
|
98a091a7cb
|
defualt oracle_rate=0
|
2018-11-04 10:49:10 +09:00 |
|
|
nagadomi
|
9c759ac58f
|
Fix aea254eab5
|
2018-11-03 23:17:16 +00:00 |
|
|
nagadomi
|
62770a901a
|
Update cunet arch optimized by benchmark
|
2018-11-04 08:03:37 +09:00 |
|
|
nagadomi
|
aea254eab5
|
Rename RandomBinaryCriterion to LBPCriterion
|
2018-11-04 00:24:51 +09:00 |
|
|
nagadomi
|
daadbaccae
|
performance tuning
|
2018-11-04 00:21:56 +09:00 |
|
|
nagadomi
|
6655d03971
|
Fix a bug that batch_size option is not used
|
2018-11-02 18:15:17 +09:00 |
|
|
nagadomi
|
3654ee41cf
|
Fix shortcut connection order in unet_branch
|
2018-11-01 20:00:11 +09:00 |
|
|
nagadomi
|
2e59d97b17
|
Temporary added experimental models
|
2018-11-01 19:59:07 +09:00 |
|
|
nagadomi
|
b3fb286258
|
lbp loss: multilayer support
|
2018-11-01 00:27:11 +09:00 |
|
|
nagadomi
|
804896276e
|
Remove SEBlock from the first layer
|
2018-10-31 07:04:30 +00:00 |
|
|
nagadomi
|
9d924acbe5
|
Add cunet_s
|
2018-10-31 01:02:28 +09:00 |
|
|
nagadomi
|
3e4058821e
|
SEBlock test tmp
|
2018-10-30 14:44:28 +00:00 |
|
|
nagadomi
|
bdafab9e10
|
Add -resume_epoch option
|
2018-10-29 17:25:34 +00:00 |
|
|
nagadomi
|
6efd7f890e
|
Add cunet for 1x; Remove unused code
|
2018-10-29 04:07:05 +09:00 |
|
|
nagadomi
|
b28b6172ca
|
clean; Add upcunet_v3
|
2018-10-28 16:03:52 +09:00 |
|
|
nagadomi
|
17b8de2d36
|
Make the performance benchmark practical
|
2018-10-27 20:38:04 +09:00 |
|
|
nagadomi
|
4c14b2faf0
|
Fix clearState in ScaleTable
|
2018-10-27 20:35:06 +09:00 |
|
|
nagadomi
|
4c8a47e149
|
clearState
|
2018-10-27 09:41:52 +00:00 |
|
|
nagadomi
|
2d85f70415
|
Add support for w2nn_valid_input_size
|
2018-10-27 08:00:23 +00:00 |
|
|
nagadomi
|
8051535fdc
|
nobias
|
2018-10-27 06:05:10 +00:00 |
|
|
nagadomi
|
0b82668359
|
Add upcunet_v2, fixed the Global AVE problem
|
2018-10-27 14:59:51 +09:00 |
|
|
nagadomi
|
1f18d1919a
|
clean
|
2018-10-25 11:44:55 +00:00 |
|
|
nagadomi
|
06246e0d78
|
refactor
|
2018-10-21 00:56:39 +00:00 |
|
|
nagadomi
|
ef5aa1ccbb
|
SEBlock
|
2018-10-18 19:49:10 +00:00 |
|
|
nagadomi
|
eea286059f
|
Add ScaleTable for Squeeze and Excitation Networks
|
2018-10-18 19:35:16 +00:00 |
|
|
nagadomi
|
4b9196deaa
|
cunet_v5
|
2018-10-16 13:02:42 +00:00 |
|
|
nagadomi
|
89c8f5db8e
|
Add aux_lbp; Fix oracle
|
2018-10-16 13:02:09 +00:00 |
|
|
nagadomi
|
8065ec9bb2
|
fix
|
2018-10-13 20:06:12 +00:00 |
|
|
nagadomi
|
e6da46d08f
|
experimental model
|
2018-10-14 01:21:23 +09:00 |
|
|
nagadomi
|
f317545732
|
aux_huber and lbp loss
|
2018-10-14 01:20:03 +09:00 |
|
|
nagadomi
|
5365890fa8
|
Add some modules
|
2018-10-14 01:18:32 +09:00 |
|
|
nagadomi
|
aef969d64b
|
Add support for criterion arguments in AuxiliaryLossCriterion
|
2018-10-14 01:15:51 +09:00 |
|
|
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 |
|