Xianyan
c58a6ab420
refactor smoothL1Criterion and fix tensor storage usage ( #986 )
...
* refactor smoothL1Criterion and fix tensor storage usage
2017-06-08 12:36:15 +08:00
zhangxiaoli73
970763f895
delete useless CriterionTable ( #981 )
2017-06-08 09:51:02 +08:00
Ian Wong
17349e48d9
some new layer and existing layer refactor ( #957 )
...
* nn refactor
* fix code style issue
* add python api
* change back the layers
2017-06-07 19:10:34 +08:00
Yang Wang
f6afb611b0
refactor InitializationMethod ( #960 )
...
* refactor init
* fix test
* address some comments
* fix tests
* add trait
* fix tests
2017-06-07 18:08:12 +08:00
Fu Zhouwang
1342865e4d
Add isTensor and isTable method in Activity with additional test cases ( #980 )
...
* Add isTensor and isTable method in Activity
* fix sytle in comment
2017-06-07 15:08:20 +08:00
Xianyan
8437b7b12c
change SelectTable from Container to AbstractModule ( #977 )
2017-06-07 09:44:31 +08:00
zhangxiaoli73
65afa653be
fix add bug ( #968 )
2017-06-06 15:34:20 +08:00
Yan Wan
7b9e5cbd15
share memory in CAddTable for LSTM, GRU, SimpleRNN ( #855 )
...
* share memory in CAddTable for LSTM, GRU, SimpleRNN; share memory for Reverse layer
* revise javadoc
* revert GRU
* set default inPlace value to be false in Reverse layer
2017-06-06 14:52:08 +08:00
qiuxin2012
776009b736
fix BCECriterion
2017-06-05 16:06:24 +08:00
jenniew
9c39513289
add tensor size info when requirement failed ( #942 )
...
* add tensor size info when requirement failed
* add layer info when requirement fail
2017-06-01 06:37:49 +08:00
Yao Zhang
fc15ce4521
fix bug in Concat layer and Add backward to ConcatTable ( #902 )
2017-05-25 10:48:32 +08:00
qiuxin2012
00d473811a
fix ConcatTable.clearState() don't clear gradInput when gradInput is a table
2017-05-25 10:42:35 +08:00
JerryYanWan
52cc3d2fbe
linear; initialize gradWeight when running backward
2017-05-24 12:57:55 +08:00
li,zhichao
e1d987f458
Refine model name ( #912 )
...
* refine model name
* add printName
* style
2017-05-19 14:23:19 +08:00
seaofocean
ba1f202d8b
fix the bug of SpatialDilatedConvolution
2017-05-19 12:39:35 +08:00
SujieZhu
446e774c01
fix the Squeeze layer for multi dimension
2017-05-18 16:58:11 +08:00
Xianyan
16eafb4e52
fix bug of CMul and CAdd when getParameters is called ( #872 )
2017-05-11 14:40:27 +08:00
jenniew
d7d1f3875a
Merge branch 'master' of https://github.com/intel-analytics/BigDL into set_weights
2017-05-09 12:32:07 -07:00
jenniew
6c7506541e
update style and set/get weights method name
...
remove not used import
2017-05-09 12:30:44 -07:00
Yao Zhang
6548dcd66e
Support layerwise, weight-bias separated and multiple sorts (L1, L2 and others) of regularization ( #714 )
...
* make linear layerwise regurization work
* add regularizer option to layers with weights
fix a bug
* new version
* include accRegularization in accGradparameters
* meet code review
* add layerwise regualrization performance tests
* fix to meet code review
* make Regularizer.isRegularized private and optimize L1 regularization implementation
* fix jenkins tests failed
* change l1 implementation
* improve layerwise regularization performance test
* improve layerwise regularization performance test
* delete layerwise regularization perform test
2017-05-08 16:26:52 +08:00
jenniew
3e6e055cdc
merge master
2017-05-05 13:34:15 -07:00
jenniew
708cbe73f2
set weights per layer
...
remove return value of set weights
update setWeights in scala side and add negative test case
update setweights
2017-05-05 12:54:44 -07:00
Yiheng Wang
75c96b523d
revise Graph and DirectedGraph
2017-05-05 15:28:54 +08:00
Xianyan
442ea61112
add VolumetricMaxPooling ( #829 )
...
* add VolumetricMaxPooling
2017-04-28 17:30:42 +08:00
yangw
bd61037ded
update biRecurrent and add adam optim method in python api
2017-04-26 14:07:02 +08:00
Yiheng Wang
27b8319723
refactor squeeze layer
2017-04-26 13:58:18 +08:00
seaofocean
57bcf13300
add 4d normalize support
2017-04-25 15:17:28 +08:00
seaofocean
080d726bd8
remove unnecessary clone in FlattenTable
2017-04-25 15:17:07 +08:00
zhangli
3e95bab852
add docs for lookuptable
2017-04-25 14:58:04 +08:00
seaofocean
2d917167fd
assign updateOutput return value to output
2017-04-25 13:23:56 +08:00
plrectco
3c3bae9361
change some vars to vals
2017-04-21 12:24:25 +08:00
zhangli
069c023a50
add evaluator
2017-04-21 10:44:27 +08:00
JerryYanWan
c225959f28
revise Parallel to serial in spec
...
gradient check for DiceCoefficient
2017-04-20 12:55:44 +08:00
JerryYanWan
790c2569c6
support DiceCoefficient
2017-04-20 12:55:44 +08:00
Yiheng Wang
ee6adf0813
checkin graph
2017-04-18 10:23:16 +08:00
seaofocean
1ecfdad0c2
add VolumetricConvolution
2017-04-14 14:49:56 +08:00
Yao
8fa9229208
add more comments
2017-04-12 03:16:15 +08:00
Yao
d14969f7d8
add dropout to lstmPeepwhole
2017-04-12 03:16:15 +08:00
Yao
d6215bff3d
add more docuemnts to Cell class
2017-04-12 03:16:15 +08:00
Yao
6e6262d58c
remove isLazy and flag from Dropout and add isResampleing
...
meet review
2017-04-12 03:16:15 +08:00
Yao
c6de79c903
fix a bug for droput when input is not contiguous
2017-04-12 03:16:15 +08:00
Yao
8efdb5c653
Add test of recurrent dropout
2017-04-12 03:16:15 +08:00
Yao
db5a34b780
add comments to Dropout
2017-04-12 03:16:15 +08:00
Yao
efb7b097cf
Add Dropout api to LSTM
...
fig a bug in PythonBigDL
fix a bug in LSTMSpec
2017-04-12 03:16:15 +08:00
Yao
80db4b9ab5
Make Recurrent support lazy Dropout
2017-04-12 03:16:15 +08:00
Yao Zhang
c182728d84
Merge pull request #498 from psyyz10/sequential
...
Add accGradParameters to Sequential and test it
2017-04-11 09:38:30 +08:00
JerryYanWan
a32e029750
remove Array[Future]; make it run in single thread
2017-04-07 11:30:38 +08:00
Yao
54db853717
add backward to sequential
...
refine the test
2017-04-06 10:37:18 +08:00
JerryYanWan
7da379d25f
cloned module weights.set()
2017-04-01 15:50:27 +08:00
JerryYanWan
a490064b84
clear the gradWeights
2017-04-01 15:50:27 +08:00
