ce8ee68 | William Darling | 13 August 2016, 10:33:27 UTC | fixed tab use | 13 August 2016, 10:33:27 UTC |
722ee6f | William Darling | 13 August 2016, 10:09:28 UTC | fixed more conflicts | 13 August 2016, 10:09:28 UTC |
f382725 | William Darling | 13 August 2016, 10:05:14 UTC | fixed conflicts | 13 August 2016, 10:05:14 UTC |
36ecd96 | William Darling | 13 August 2016, 10:03:11 UTC | added note re code duplication | 13 August 2016, 10:03:11 UTC |
54fc327 | William Darling | 15 July 2016, 08:22:37 UTC | added full GRU implementation with same interface as LSTM so it can be a pop-in replacement | 13 August 2016, 10:00:07 UTC |
ded7fd7 | William Darling | 14 July 2016, 15:15:06 UTC | added returned outputDim in GRU | 13 August 2016, 10:00:07 UTC |
94c7ca8 | William Darling | 14 July 2016, 14:19:52 UTC | fixed tabs | 13 August 2016, 10:00:07 UTC |
8f362b9 | William Darling | 14 July 2016, 13:44:58 UTC | added stack of GRUs so we can use this with seq2seq | 13 August 2016, 10:00:07 UTC |
5a60d48 | William Darling | 13 July 2016, 08:13:15 UTC | fixed tab use; renamed privateInnards in LSTM function | 13 August 2016, 10:00:07 UTC |
fae8715 | William Darling | 12 July 2016, 14:46:34 UTC | fixed typo | 13 August 2016, 09:59:05 UTC |
71ce331 | William Darling | 12 July 2016, 14:45:29 UTC | added GRU implementation to CNTK.core.bs | 13 August 2016, 09:59:05 UTC |
1ff309f | William Darling | 15 July 2016, 08:22:37 UTC | added full GRU implementation with same interface as LSTM so it can be a pop-in replacement | 13 August 2016, 09:59:05 UTC |
55f55ae | William Darling | 14 July 2016, 15:15:06 UTC | added returned outputDim in GRU | 13 August 2016, 09:59:05 UTC |
6dfc00f | William Darling | 14 July 2016, 14:19:52 UTC | fixed tabs | 13 August 2016, 09:59:05 UTC |
cef8c81 | William Darling | 14 July 2016, 13:44:58 UTC | added stack of GRUs so we can use this with seq2seq | 13 August 2016, 09:59:05 UTC |
dc52c2c | William Darling | 13 July 2016, 08:13:15 UTC | fixed tab use; renamed privateInnards in LSTM function | 13 August 2016, 09:59:05 UTC |
730aaea | William Darling | 12 July 2016, 14:46:34 UTC | fixed typo | 13 August 2016, 09:56:57 UTC |
b795260 | William Darling | 12 July 2016, 14:45:29 UTC | added GRU implementation to CNTK.core.bs | 13 August 2016, 09:56:57 UTC |
a369a18 | Frank Seide | 12 August 2016, 23:16:20 UTC | BrainScriptNetworkBuilder now allows curlies | 12 August 2016, 23:16:20 UTC |
c5a9d41 | Frank Seide | 12 August 2016, 21:05:05 UTC | Merge branch 'master' of https://github.com/Microsoft/cntk into fseide/kdd | 12 August 2016, 21:05:05 UTC |
9859a36 | Frank Seide | 12 August 2016, 21:03:32 UTC | bug fix: ConvolutionalLayer{} should use old-style Parameter{} dimensions to be compatible with CNTK convolution engine | 12 August 2016, 21:03:32 UTC |
a269e0e | Project Philly | 12 August 2016, 20:45:12 UTC | Integrate thilow/FixTimes4SparseOnCPU into master | 12 August 2016, 20:45:12 UTC |
0692596 | Project Philly | 12 August 2016, 20:12:38 UTC | Integrate alexeyo/EvalWrapper-Strong-Name into master | 12 August 2016, 20:12:38 UTC |
8d7ed08 | Thilo Will | 12 August 2016, 14:24:01 UTC | Fix of fix | 12 August 2016, 14:24:01 UTC |
551f1df | Alexey Orlov | 12 August 2016, 14:17:46 UTC | Added *.snk (Strong Name key) to ,gitattribute as binary | 12 August 2016, 14:17:46 UTC |
6f7505f | Thilo Will | 12 August 2016, 12:52:27 UTC | Fixing another bug in Times(Dense,Sparse) and restructure code | 12 August 2016, 12:52:27 UTC |
aea8549 | Eldar Akchurin | 12 August 2016, 11:14:43 UTC | Fixing composite error to support sparse labels | 12 August 2016, 12:47:30 UTC |
66e4534 | Eldar Akchurin | 12 August 2016, 11:03:38 UTC | Fixing bug in sparse matrix buffer estimation | 12 August 2016, 12:47:30 UTC |
59fd877 | Eldar Akchurin | 11 August 2016, 15:37:00 UTC | Allowing sparse labels | 12 August 2016, 12:47:30 UTC |
edd3a94 | Thilo Will | 12 August 2016, 07:53:09 UTC | Fixing initialsation of result in Times(dense, sparse) on CPU | 12 August 2016, 07:53:09 UTC |
561d773 | Frank Seide | 12 August 2016, 07:34:49 UTC | addressed CR feedback | 12 August 2016, 07:34:49 UTC |
80d8ffd | Frank Seide | 12 August 2016, 07:28:13 UTC | reverted shareNodeValueMatrices back to false by default, since some Python tests fail | 12 August 2016, 07:28:13 UTC |
caef7e5 | Frank Seide | 12 August 2016, 04:20:15 UTC | added more initialization options to LearnableParameter | 12 August 2016, 04:20:15 UTC |
08730da | Frank Seide | 12 August 2016, 01:41:14 UTC | (addressed CR feedback) | 12 August 2016, 01:41:14 UTC |
7e5bc94 | Frank Seide | 12 August 2016, 00:47:50 UTC | Merge branch 'master' of https://github.com/Microsoft/cntk into fseide/kdd | 12 August 2016, 00:47:50 UTC |
f88fcdb | Frank Seide | 12 August 2016, 00:29:21 UTC | now accepts mismatching MBLayouts during validation, relying on runtime checks only. Updated ATIS sample. | 12 August 2016, 00:29:21 UTC |
b950b9e | Frank Seide | 11 August 2016, 22:09:09 UTC | changed apply function to apply() for clarity and familiarity; factored reporting of layout mismatches | 11 August 2016, 22:09:09 UTC |
072327b | Frank Seide | 11 August 2016, 21:02:32 UTC | TutorialImage simplifications | 11 August 2016, 21:02:32 UTC |
c9db38f | Alexey Orlov | 11 August 2016, 20:37:04 UTC | Enabling Strong Name for EvalWrapper | 11 August 2016, 20:37:04 UTC |
c0c9916 | Eldar Akchurin | 11 August 2016, 15:39:43 UTC | Addressing CR | 11 August 2016, 15:39:43 UTC |
0390abc | Eldar Akchurin | 11 August 2016, 14:38:10 UTC | Removing unused file | 11 August 2016, 14:38:10 UTC |
f4ffce2 | Eldar Akchurin | 11 August 2016, 14:34:50 UTC | Fixing crash in the transformers | 11 August 2016, 14:34:50 UTC |
474570d | Frank Seide | 11 August 2016, 06:47:44 UTC | first version of ResNet in TutorialImage.cntk; breaking change: ConvolutionalLayer{} and XXPoolingLayer{} now both default to padding=false, like Keras | 11 August 2016, 06:47:44 UTC |
281f1a3 | Project Philly | 11 August 2016, 05:24:46 UTC | Integrate nikosk/minor-directory-restructuring-for-Dockerfiles into master | 11 August 2016, 05:24:46 UTC |
8ecc7b1 | Frank Seide | 11 August 2016, 03:33:19 UTC | readded BN to TutorialImage.CNTK | 11 August 2016, 03:33:19 UTC |
8a79eda | Frank Seide | 11 August 2016, 01:53:39 UTC | got a new baseline for TutorialImage.cntk/simple network, with latest reader architecture | 11 August 2016, 01:53:39 UTC |
6e32e40 | Frank Seide | 11 August 2016, 01:18:34 UTC | switched convnet to new reader architecture | 11 August 2016, 01:18:34 UTC |
ea3b31f | Frank Seide | 11 August 2016, 00:42:46 UTC | added new reader to TutorialImage.cntk | 11 August 2016, 00:42:46 UTC |
e1d0cb2 | Frank Seide | 10 August 2016, 23:36:41 UTC | bug fix in GetMatrixInfo: should check gradient matrix ptr for being NULL instead of asking NeedsGradient() | 10 August 2016, 23:36:41 UTC |
83e3485 | Alexey Orlov | 10 August 2016, 23:20:09 UTC | Main ReadMe News, Aug 10, 2016 | 10 August 2016, 23:20:09 UTC |
19233d7 | Frank Seide | 10 August 2016, 19:06:40 UTC | changed shareNodeValueMatrices to true by default | 10 August 2016, 19:06:40 UTC |
34cb4a9 | Frank Seide | 10 August 2016, 18:08:09 UTC | created ConvNet.cntk | 10 August 2016, 18:08:09 UTC |
9f6306c | Frank Seide | 10 August 2016, 18:07:19 UTC | replaced 01_Convolution.bs.cntk with TutorialImage.cntk | 10 August 2016, 18:07:19 UTC |
03143a0 | Frank Seide | 10 August 2016, 17:47:25 UTC | printing matrix info no longer requires ElemType and has streamlined output; added parameter dimension inference to BatchNormalizationNode | 10 August 2016, 17:47:25 UTC |
d071351 | Frank Seide | 10 August 2016, 06:56:24 UTC | fragments of parameter inference for BN, but failed due to existing bug; added BN to TutorialImage | 10 August 2016, 06:56:24 UTC |
3be8fab | Frank Seide | 10 August 2016, 04:39:29 UTC | (made gcc happy) | 10 August 2016, 04:39:29 UTC |
7948ec4 | Frank Seide | 10 August 2016, 04:33:47 UTC | (minor cleanup) | 10 August 2016, 04:33:47 UTC |
6772d27 | Frank Seide | 10 August 2016, 04:33:21 UTC | added a BS version of 01_Conv | 10 August 2016, 04:33:21 UTC |
4cd66b6 | Frank Seide | 10 August 2016, 04:26:20 UTC | minor cleanup of TutorialImage.cntk | 10 August 2016, 04:26:20 UTC |
ce550d9 | Frank Seide | 10 August 2016, 04:24:17 UTC | added Sequential style to TutorialImage | 10 August 2016, 04:24:17 UTC |
5567398 | Frank Seide | 10 August 2016, 04:08:28 UTC | implemented dimension inference for Convolution() | 10 August 2016, 04:08:28 UTC |
afb0175 | Frank Seide | 10 August 2016, 00:54:20 UTC | ND-Pooling no longer requires to specify reduction dimensions for kernel etc. (they will be inferred) | 10 August 2016, 00:54:20 UTC |
e44b53e | Frank Seide | 09 August 2016, 23:38:42 UTC | adapted seqcla.cntk to a renamed optional parameter | 09 August 2016, 23:38:42 UTC |
b32a04e | Frank Seide | 09 August 2016, 23:35:53 UTC | bug fix: Times() should infer tensor ranks correctly | 09 August 2016, 23:35:53 UTC |
52126c3 | Nikos Karampatziakis | 09 August 2016, 23:10:53 UTC | adjust LD_LIBRARY_PATH in Dockerfile | 09 August 2016, 23:10:53 UTC |
9683d12 | Nikos Karampatziakis | 09 August 2016, 23:05:01 UTC | Merge branch 'nikosk/minor-directory-restructuring-for-Dockerfiles' of https://github.com/Microsoft/cntk into nikosk/minor-directory-restructuring-for-Dockerfiles | 09 August 2016, 23:05:01 UTC |
9046f9a | Frank Seide | 09 August 2016, 23:01:16 UTC | towards new structure for 01_Conv CIFAR-10 | 09 August 2016, 23:01:16 UTC |
0f9eadf | Nikos Karampatziakis | 03 August 2016, 22:22:23 UTC | update GPU Dockerfile to cuda 7.5 and add test dependencies to both CPU and GPU Dockerfiles | 09 August 2016, 22:58:16 UTC |
27c3697 | Frank Seide | 09 August 2016, 22:33:20 UTC | created a first BS version of CIFAR-10 01_Conv | 09 August 2016, 22:33:20 UTC |
8ad49c7 | Nikos Karampatziakis | 09 August 2016, 22:21:29 UTC | merge separate apt-get commands in Dockerfiles into one; update CPU Dockerfile to call MNIST and CIFAR python scripts | 09 August 2016, 22:21:29 UTC |
30ff99b | Frank Seide | 09 August 2016, 17:01:06 UTC | tried bidirectional intent classifier | 09 August 2016, 17:01:06 UTC |
26eb5af | Project Philly | 09 August 2016, 13:40:36 UTC | Integrate t-ivrodr/fix_unittests_build into master | 09 August 2016, 13:40:36 UTC |
3871b7f | Project Philly | 09 August 2016, 12:50:30 UTC | Integrate zhouwang/libzippath-docker into master | 09 August 2016, 12:50:30 UTC |
289f62f | Ivan Rodriguez | 09 August 2016, 12:08:26 UTC | Fix cudnn dll dependency for debug build | 09 August 2016, 12:08:43 UTC |
53d5222 | Frank Seide | 09 August 2016, 05:51:17 UTC | added intent classification to ATIS sample | 09 August 2016, 05:51:17 UTC |
f9c10a8 | Frank Seide | 09 August 2016, 05:08:54 UTC | created slot tagger in new style from Derek's example; added a layer-like LSTM called LSTMBlock{} and fixed RecurrentLSTMLayer{} with that; ComputationNetworkBuilder from BrainScript now force-uses top-level node names for all nodes that are reachable from outer record, as that is the name the user intended | 09 August 2016, 05:08:54 UTC |
71c2a94 | Frank Seide | 09 August 2016, 02:14:06 UTC | switched to new CTF files (not cleaned up yet); fixed a CTF preparation error | 09 August 2016, 02:14:06 UTC |
b96a508 | Frank Seide | 09 August 2016, 01:54:57 UTC | added pre-processed ATIS files and first step towards tutorials | 09 August 2016, 01:54:57 UTC |
2e59be9 | Nikos Karampatziakis | 08 August 2016, 22:57:03 UTC | update GPU Dockerfile to cuda 7.5 and add test dependencies to both CPU and GPU Dockerfiles | 08 August 2016, 22:57:03 UTC |
c8e309b | Nikos Karampatziakis | 03 August 2016, 22:22:23 UTC | move [CG]PU-Dockerfile to [CG]PU/Dockerfile | 08 August 2016, 22:30:52 UTC |
9db12dd | xiaohuliu | 08 August 2016, 22:23:32 UTC | Merge branch 'master' of https://github.com/Microsoft/cntk | 08 August 2016, 22:23:32 UTC |
eccd3d0 | xiaohuliu | 08 August 2016, 22:22:08 UTC | Update the README file about F1 score. | 08 August 2016, 22:22:08 UTC |
15d4045 | Zhou Wang | 08 August 2016, 20:05:09 UTC | Add libzip path to LD_LIBRARY_PATH | 08 August 2016, 20:05:09 UTC |
595c7ab | Frank Seide | 08 August 2016, 17:04:02 UTC | addressed review feedback | 08 August 2016, 17:04:02 UTC |
3cd32b0 | William Darling | 08 August 2016, 05:06:05 UTC | Merge branch 'wdarling/gru' of https://github.com/Microsoft/CNTK into wdarling/gru | 08 August 2016, 05:06:05 UTC |
cf70b01 | William Darling | 15 July 2016, 08:22:37 UTC | added full GRU implementation with same interface as LSTM so it can be a pop-in replacement | 08 August 2016, 05:05:06 UTC |
8dd5363 | William Darling | 14 July 2016, 15:15:06 UTC | added returned outputDim in GRU | 08 August 2016, 05:05:06 UTC |
240e348 | William Darling | 14 July 2016, 14:19:52 UTC | fixed tabs | 08 August 2016, 05:05:06 UTC |
81de2e4 | William Darling | 14 July 2016, 13:44:58 UTC | added stack of GRUs so we can use this with seq2seq | 08 August 2016, 05:05:06 UTC |
fb4fbc1 | William Darling | 13 July 2016, 08:13:15 UTC | fixed tab use; renamed privateInnards in LSTM function | 08 August 2016, 05:05:06 UTC |
d9ef6c5 | William Darling | 12 July 2016, 14:46:34 UTC | fixed typo | 08 August 2016, 05:05:06 UTC |
302c0fd | William Darling | 12 July 2016, 14:45:29 UTC | added GRU implementation to CNTK.core.bs | 08 August 2016, 05:05:06 UTC |
d6fb378 | Frank Seide | 08 August 2016, 04:27:54 UTC | bug fix: CPUSparseMatrix<ElemType>::MultiplyAndWeightedAdd() should handle transposed inputs in all combinations | 08 August 2016, 04:27:54 UTC |
784d72e | Frank Seide | 08 August 2016, 02:39:34 UTC | Merge branch 'master' of https://github.com/Microsoft/cntk into fseide/layerslib | 08 August 2016, 02:39:34 UTC |
8d7819c | Frank Seide | 08 August 2016, 02:13:53 UTC | deleted remnants | 08 August 2016, 02:13:53 UTC |
efae278 | Frank Seide | 08 August 2016, 02:11:03 UTC | seqcla changed to define the model through layer composition | 08 August 2016, 02:11:03 UTC |
441f828 | Frank Seide | 08 August 2016, 01:47:52 UTC | seqcla now using layers but in graph style | 08 August 2016, 01:47:52 UTC |
5cd5ec8 | Frank Seide | 08 August 2016, 01:34:14 UTC | converted seqcla to sparse input | 08 August 2016, 01:34:14 UTC |
8bfd693 | Frank Seide | 08 August 2016, 01:07:38 UTC | (more refacoring of seqcla test) | 08 August 2016, 01:07:38 UTC |
e4fd6c8 | Frank Seide | 08 August 2016, 00:59:59 UTC | added EmbeddingLayer{}; tuned LayerNormalizationLayer{}; added ReLU alias; bug fix: SGD should print the dimensions of the trained nodes; seqcla changed to model() pattern | 08 August 2016, 00:59:59 UTC |