https://github.com/Microsoft/CNTK

sort by:
Revision Author Date Message Commit Date
b252b1d Removing last vestiges of dataDecimationFactor 24 August 2016, 22:29:17 UTC
373adfd Changes Addressing Code Review for CUDNN RNNStack Node 23 August 2016, 17:40:34 UTC
2fa1b70 Merge commit 'origin/master' 8493f11 into jdroppo/cudnn-rnn-lstm 22 August 2016, 20:28:42 UTC
8493f11 CNTK v2 library: Clone constants to right device when user supplied value is not on the target compute device 22 August 2016, 18:54:21 UTC
37b6897 Merge branch 'master' of https://github.com/Microsoft/CNTK into amitaga/cntkv2Library 22 August 2016, 17:48:54 UTC
4e174f2 Integrate eldak/mtNonUniform2 into master 22 August 2016, 13:45:48 UTC
6a063e2 Integrate zhouwang/fix-deviceid-threadlocal into master 22 August 2016, 13:01:46 UTC
6566012 Add comment to use thread_local after uprade to VS2015 22 August 2016, 08:04:47 UTC
d5f47f1 Updating sources and baselines to use MT 22 August 2016, 07:49:08 UTC
b856ab7 Adding support for mersenne twister rand 21 August 2016, 19:08:25 UTC
45f4cbb CNTK v2 library: Linux build fixes 21 August 2016, 11:25:53 UTC
668b6a4 Merge branch 'master' of https://github.com/Microsoft/CNTK into amitaga/cntkv2Library 21 August 2016, 10:52:37 UTC
fa4b99d CNTK v2 Library: a) Add dynamic axis support b) New primitive functions and some higher level functions and c) Sequence classification test 21 August 2016, 10:49:03 UTC
a236139 Bug fix for format checking. 19 August 2016, 23:16:11 UTC
d52a02c Fix bug on n-dimensional convolution input format checking. 19 August 2016, 23:16:11 UTC
19d24e8 Ensure that network is created prior to reading features. This optimizes two scenarios: (1) allows to fail faster, when network definition has errors (2) when startEpoch==maxEpoch 19 August 2016, 16:22:48 UTC
008f2f1 Adding verbosity 19 August 2016, 13:11:44 UTC
d4275b4 Fixing linux build 19 August 2016, 11:49:48 UTC
f27b1ce Small refactoring 19 August 2016, 11:37:32 UTC
702aa2d Hiding unsued variable 19 August 2016, 11:34:04 UTC
9165b43 Restructuring how zip index is built 19 August 2016, 11:32:56 UTC
3d80725 Define THREAD_LOCAL and force currentDevice to be THREAD_LOCAL 19 August 2016, 09:16:33 UTC
971b7d0 Change PrepareDevice() to have a Thread Dependent Value Cache The cached value of currentDevice is meant to avoid redundant calls to cudaSetDevice(). But, this setting is tread specific. So, the cache should be thread specific. This fixes the problem on Windows. 18 August 2016, 22:41:59 UTC
9bd9308 Improve V2 Learner API, add basic serialization. FSAdaGrad, RMSProp: pre-allocate smoothed gradients with expected number of columns. Improve configuring built-in learners: add learning rates and momentums schedules. Add NDArrayView as a DictionaryValue type. Add tests for serialization and basic learner functionality. 18 August 2016, 13:06:54 UTC
4ef4b25 Merge remote-tracking branch 'origin/jdroppo/cudnn-rnn-lstm' into jdroppo/cudnn-rnn-lstm 17 August 2016, 22:49:02 UTC
b0d4756 Frank Implemented CopyTo() for RNNNode class 17 August 2016, 22:33:40 UTC
32f97fd Integrate alrezni/output_fix into master 17 August 2016, 12:21:05 UTC
03a2be0 A few minor changes in the BlockRandomizer output 17 August 2016, 10:54:43 UTC
fa39bab remove acml references from Kaldi readme 17 August 2016, 08:04:56 UTC
786ec99 fixed broken ifdef statement 17 August 2016, 08:04:56 UTC
79cfcf7 more acml removal 17 August 2016, 08:04:56 UTC
40d2478 remove reference to acml math library 17 August 2016, 08:04:56 UTC
41fb7ad Fix for linux build 17 August 2016, 06:12:03 UTC
e69c28b Delete actual dumps and fix dependency on Cudnn64_4.dll 17 August 2016, 06:12:03 UTC
ba8f952 Add test cases 17 August 2016, 06:12:03 UTC
3b6f687 Modify brainscript tests projects to start with computation network tests 17 August 2016, 06:12:03 UTC
b99b383 CuDNN-RNN Fix Merge Error in Math/*filters Visual Studio files 16 August 2016, 22:50:56 UTC
2fb185b CUDNN-RNN Fix Parameter Count in Error Message 16 August 2016, 17:10:06 UTC
d965072 fix bug in m_featureElmentType initialization 16 August 2016, 15:49:06 UTC
46a10ad Merge branch 'master' into blis/PythonV2 16 August 2016, 07:47:04 UTC
1c98108 Merge branch 'master' of https://github.com/Microsoft/CNTK into dongyu/getevalorder 16 August 2016, 00:08:26 UTC
fcb74ca Support GetEvalOder call in MEL. 15 August 2016, 23:41:16 UTC
80d0770 Merge branch 'master' into jdroppo/cudnn-rnn-lstm 15 August 2016, 23:11:16 UTC
8c809d2 make the name resolution for new helper explicit 15 August 2016, 21:06:15 UTC
586bfba correct the bracketing of tricky expression in sequence parser; fix a potentially infinite loop 15 August 2016, 18:39:10 UTC
ce8ee68 fixed tab use 13 August 2016, 10:33:27 UTC
722ee6f fixed more conflicts 13 August 2016, 10:09:28 UTC
f382725 fixed conflicts 13 August 2016, 10:05:14 UTC
36ecd96 added note re code duplication 13 August 2016, 10:03:11 UTC
54fc327 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 added returned outputDim in GRU 13 August 2016, 10:00:07 UTC
94c7ca8 fixed tabs 13 August 2016, 10:00:07 UTC
8f362b9 added stack of GRUs so we can use this with seq2seq 13 August 2016, 10:00:07 UTC
5a60d48 fixed tab use; renamed privateInnards in LSTM function 13 August 2016, 10:00:07 UTC
fae8715 fixed typo 13 August 2016, 09:59:05 UTC
71ce331 added GRU implementation to CNTK.core.bs 13 August 2016, 09:59:05 UTC
1ff309f 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 added returned outputDim in GRU 13 August 2016, 09:59:05 UTC
6dfc00f fixed tabs 13 August 2016, 09:59:05 UTC
cef8c81 added stack of GRUs so we can use this with seq2seq 13 August 2016, 09:59:05 UTC
dc52c2c fixed tab use; renamed privateInnards in LSTM function 13 August 2016, 09:59:05 UTC
730aaea fixed typo 13 August 2016, 09:56:57 UTC
b795260 added GRU implementation to CNTK.core.bs 13 August 2016, 09:56:57 UTC
a369a18 BrainScriptNetworkBuilder now allows curlies 12 August 2016, 23:16:20 UTC
c5a9d41 Merge branch 'master' of https://github.com/Microsoft/cntk into fseide/kdd 12 August 2016, 21:05:05 UTC
9859a36 bug fix: ConvolutionalLayer{} should use old-style Parameter{} dimensions to be compatible with CNTK convolution engine 12 August 2016, 21:03:32 UTC
a269e0e Integrate thilow/FixTimes4SparseOnCPU into master 12 August 2016, 20:45:12 UTC
0692596 Integrate alexeyo/EvalWrapper-Strong-Name into master 12 August 2016, 20:12:38 UTC
fa23b38 remove tester files that are not needed anymore 12 August 2016, 15:44:20 UTC
29317e7 Merge branch 'master' into blis/PythonV2 12 August 2016, 15:29:42 UTC
e8b623c reverse axes in swig for ndshape.dimensions() and ndarrayview 12 August 2016, 15:28:22 UTC
8d7ed08 Fix of fix 12 August 2016, 14:24:01 UTC
551f1df Added *.snk (Strong Name key) to ,gitattribute as binary 12 August 2016, 14:17:46 UTC
f9b3ac3 automatic generation of pythonic names 12 August 2016, 13:16:42 UTC
6f7505f Fixing another bug in Times(Dense,Sparse) and restructure code 12 August 2016, 12:52:27 UTC
aea8549 Fixing composite error to support sparse labels 12 August 2016, 12:47:30 UTC
66e4534 Fixing bug in sparse matrix buffer estimation 12 August 2016, 12:47:30 UTC
59fd877 Allowing sparse labels 12 August 2016, 12:47:30 UTC
e4c2de1 address cr comments part2 12 August 2016, 10:02:53 UTC
edd3a94 Fixing initialsation of result in Times(dense, sparse) on CPU 12 August 2016, 07:53:09 UTC
561d773 addressed CR feedback 12 August 2016, 07:34:49 UTC
80d8ffd reverted shareNodeValueMatrices back to false by default, since some Python tests fail 12 August 2016, 07:28:13 UTC
caef7e5 added more initialization options to LearnableParameter 12 August 2016, 04:20:15 UTC
08730da (addressed CR feedback) 12 August 2016, 01:41:14 UTC
7e5bc94 Merge branch 'master' of https://github.com/Microsoft/cntk into fseide/kdd 12 August 2016, 00:47:50 UTC
f88fcdb now accepts mismatching MBLayouts during validation, relying on runtime checks only. Updated ATIS sample. 12 August 2016, 00:29:21 UTC
b950b9e changed apply function to apply() for clarity and familiarity; factored reporting of layout mismatches 11 August 2016, 22:09:09 UTC
072327b TutorialImage simplifications 11 August 2016, 21:02:32 UTC
c9db38f Enabling Strong Name for EvalWrapper 11 August 2016, 20:37:04 UTC
b3adc1b use facade sigmoid for mnist 11 August 2016, 16:07:19 UTC
9cd7525 helper function for mb_source 11 August 2016, 16:00:40 UTC
c0c9916 Addressing CR 11 August 2016, 15:39:43 UTC
0390abc Removing unused file 11 August 2016, 14:38:10 UTC
f4ffce2 Fixing crash in the transformers 11 August 2016, 14:34:50 UTC
927750c address cr comments 11 August 2016, 08:35:10 UTC
474570d 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 Integrate nikosk/minor-directory-restructuring-for-Dockerfiles into master 11 August 2016, 05:24:46 UTC
8ecc7b1 readded BN to TutorialImage.CNTK 11 August 2016, 03:33:19 UTC
8a79eda got a new baseline for TutorialImage.cntk/simple network, with latest reader architecture 11 August 2016, 01:53:39 UTC
6e32e40 switched convnet to new reader architecture 11 August 2016, 01:18:34 UTC
back to top