https://github.com/Microsoft/CNTK

sort by:
Revision Author Date Message Commit Date
9ed50a8 Merge pull request #3711 from Veason-silverbullet/mergedist Distributed training update 09 July 2019, 13:35:32 UTC
ce777cf fix 09 July 2019, 12:50:29 UTC
7b5b912 fix 09 July 2019, 10:00:40 UTC
8c4943d fix 09 July 2019, 09:37:05 UTC
67dc388 fix 09 July 2019, 09:06:37 UTC
066c421 fix 09 July 2019, 08:04:30 UTC
d58bef6 merge dist 09 July 2019, 07:42:56 UTC
f9c60db Merge pull request #3700 from Veason-silverbullet/lewlu/msra-face bug fix 18 June 2019, 07:42:38 UTC
78a42c4 bug fix 18 June 2019, 07:40:09 UTC
d1fb6c1 Merge pull request #3698 from Veason-silverbullet/lewlu/msra-face bug fix 17 June 2019, 06:17:59 UTC
d488c8b bug fix 17 June 2019, 06:16:44 UTC
9f3e47b Merge pull request #3697 from Veason-silverbullet/lewlu/msra-face bug fix 16 June 2019, 19:06:53 UTC
23aae8c bug fix 16 June 2019, 19:05:25 UTC
81f3f44 Merge pull request #3694 from Veason-silverbullet/lewlu/msra-face refix dropout node 14 June 2019, 06:06:14 UTC
e21d4e1 refix dropout node 14 June 2019, 06:03:52 UTC
219e82f Merge pull request #3689 from Veason-silverbullet/lewlu/msra-face bug fix 11 June 2019, 18:19:49 UTC
d685cca bug fix 11 June 2019, 18:17:35 UTC
c5e1b17 Merge pull request #3688 from Veason-silverbullet/lewlu/msra-face Globalconcat layer 11 June 2019, 18:11:18 UTC
50cad8f Globalconcat layer 11 June 2019, 18:09:22 UTC
80a737c Merge pull request #3682 from Veason-silverbullet/lewlu/msra-face dropout node 11 June 2019, 16:26:35 UTC
41a2cfb dropout node 11 June 2019, 16:22:01 UTC
235469c Merge pull request #3681 from Veason-silverbullet/lewlu/msra-face bn momentum 11 June 2019, 15:59:05 UTC
3337cf9 bn momentum 11 June 2019, 15:19:58 UTC
673eee5 Merge pull request #3663 from Veason-silverbullet/epsfix change eps 1e-6 to 1e-12 07 June 2019, 06:55:08 UTC
ec8c670 Merge pull request #3612 from lygztq/tizhan/msra-face-disableReg Tizhan/msra face disable reg 05 June 2019, 06:29:38 UTC
2a0c648 Update ImageRecognitionAppCS.csproj 05 June 2019, 06:28:11 UTC
fa14a34 Update ImageRecognitionAppCS.csproj 05 June 2019, 06:25:59 UTC
0f05f65 Merge pull request #3677 from lygztq/lewlu/msra-face add adabound and amsbound 04 June 2019, 09:47:31 UTC
20c81b4 add adabound and amsbound 04 June 2019, 09:03:56 UTC
12bec72 Merge pull request #3675 from lygztq/lewlu/msra-face fix bug in adamUpdate 04 June 2019, 09:00:54 UTC
e213879 fix bug in adamUpdate 02 June 2019, 13:09:12 UTC
1bd45d0 change eps 1e-6 to 1e-12 13 May 2019, 06:31:04 UTC
80887e2 Merge pull request #3591 from lygztq/tizhan/msra-face-adam Add adam and adaMax optimizer for BS 07 May 2019, 08:02:36 UTC
6ab2576 Merge pull request #3645 from Cizoux/zichen/msra-face fix load final model file 19 April 2019, 06:03:51 UTC
7e56e28 fix load final model file 16 April 2019, 11:14:11 UTC
e069d05 Merge pull request #3635 from Cizoux/zichen/msra-face fix noisy bug, add subfolder, load model from whatever subfolder 11 April 2019, 08:24:10 UTC
22f19b6 fix noisy bug, add subfolder, load model from whatever subfolder 11 April 2019, 07:33:00 UTC
a6b45ef Merge pull request #3623 from Veason-silverbullet/lewlu/msra-face Lewlu/msra face 10 April 2019, 03:42:57 UTC
fed0bf3 minor fix 06 April 2019, 11:38:21 UTC
99df007 Support label smoothing 27 March 2019, 11:30:26 UTC
df09a5a change 'disableReg' to 'disableRegularization' 27 March 2019, 07:34:21 UTC
6834d49 Merge branch 'lewlu/msra-face' into tizhan/msra-face-disableReg 26 March 2019, 07:34:36 UTC
64c2564 Merge pull request #3602 from Veason-silverbullet/lewlu/msra-face Lewlu/msra face 18 March 2019, 09:23:55 UTC
ae7aa40 fix a reader parser bug 18 March 2019, 07:43:22 UTC
08e27a6 fix cast bug for epsilon 15 March 2019, 13:26:28 UTC
5d7cff1 use clipped sqrt for adam 15 March 2019, 09:02:19 UTC
2876f8b fix adamax parameter name 15 March 2019, 07:06:17 UTC
0c7f890 modity epsilon for adam, adamax and rmsprop 15 March 2019, 06:35:11 UTC
82d3dd9 add additional optimizer information 15 March 2019, 06:34:48 UTC
74ec2eb minor fix 14 March 2019, 04:50:00 UTC
92c4a7e Fix group convolution 13 March 2019, 08:19:19 UTC
0f12a48 Merge pull request #3594 from Cizoux/lewlu/msra-face Lewlu/msra face 13 March 2019, 03:27:09 UTC
126847c fix normal distribution generator 09 March 2019, 14:11:44 UTC
4149745 minor fix 08 March 2019, 08:02:51 UTC
0ba93ea add cosine, linear cosine, noisy_linear_cosine lr dacay 08 March 2019, 04:35:12 UTC
4e0c93b Merge branch 'lewlu/msra-face' of https://github.com/Cizoux/CNTK into lewlu/msra-face 07 March 2019, 09:57:05 UTC
a66979c fix nosiy_cosine_linear 07 March 2019, 09:53:28 UTC
47e1233 Add disable regularization choice for convolution and dense layer 06 March 2019, 11:29:20 UTC
c427953 Add adam and adaMax optimizer for BS 22 February 2019, 06:32:47 UTC
f4ca0a3 add noisy liner cosine and fix liner cosine 07 January 2019, 04:42:46 UTC
b931f47 cosine and liner cosine by iter 04 January 2019, 09:30:22 UTC
89fa861 Merge pull request #3495 from hzy46/lewlu/msra-face add disableMomentumUnitGain 05 November 2018, 09:53:15 UTC
8c9ef5f fix RMSProp unitGain 05 November 2018, 09:19:58 UTC
eed5ad8 Merge branch 'lewlu/msra-face' of https://github.com/Microsoft/CNTK into lewlu/msra-face 05 November 2018, 06:06:59 UTC
d2f9627 Merge pull request #3494 from Cizoux/rmsprop-optimizer final rmsprop update 05 November 2018, 05:55:47 UTC
b7ce1a6 final rmsprop update 30 October 2018, 15:32:16 UTC
1e2dd8e add disableMomentumUnitGain 30 October 2018, 08:14:28 UTC
d14782b minor fix 22 September 2018, 09:05:05 UTC
d6fdac9 support group convolution 22 September 2018, 06:58:27 UTC
5842ea2 fix PrimitiveFunctionAttribute 20 September 2018, 12:28:47 UTC
af70f2d merge 2.6.0 20 September 2018, 08:49:00 UTC
0a3eb3b Update onnx_model_test with tests on cntk pretrained models 19 September 2018, 18:27:55 UTC
6f09c39 Merge branch 'release/2.6' 18 September 2018, 02:33:30 UTC
4ed1896 set public_build to "no"/false 17 September 2018, 23:10:48 UTC
1be3b64 update readme for .net support 15 September 2018, 01:07:45 UTC
d355c1c Updated current_iteration with .net support 14 September 2018, 20:07:24 UTC
04caa9d Updated current_iteration with .net support 14 September 2018, 19:29:51 UTC
7c1b0fa udpate readme with current iteration 14 September 2018, 00:01:45 UTC
da31ba0 Update current_iteration.md 13 September 2018, 23:57:44 UTC
e4d7081 Update current_iteration.md. 13 September 2018, 23:57:30 UTC
4f965aa update version # in cntk_common.cmake 13 September 2018, 23:34:30 UTC
82d350d bump up version number 13 September 2018, 22:52:47 UTC
d264a26 Update current_iteration.md 13 September 2018, 20:44:42 UTC
be28e86 Update current_iteration.md. 13 September 2018, 18:18:53 UTC
deda94b Support pooling(cpu) where kernel center is on pads. - Previous implementation has the assumption that (0 <= dk < width). This assumption doesn't stand when lo >(kernel - 1) / 2. The updated calculation supports arbitrary lo & hi non-negative integer value. The new calculation has dk in range (0, width + hi + lo]. - Enables onnx backend test {averagepool_2d_pads, maxpool_2d_pads} to pass. 13 September 2018, 04:37:21 UTC
62e18f4 Improve clarity in pads calculation for conv/pool - Refactor function CalcPaddingForSameLowerOrUpperAutoPad in conv/pool import, changing parameter "const Variable& input" to "const NDShape& inputWithBatchAxisShape", to specify the required shape format as [N x C x H x W]. 13 September 2018, 04:37:21 UTC
35e3701 Merge branch 'sedymche/onnx-min-max' 13 September 2018, 02:42:25 UTC
d33b7b4 update iteration plan 13 September 2018, 00:24:45 UTC
6a4ec05 Merge branch 'peykash/batchnorm_and_pooling_fixes' 13 September 2018, 00:13:46 UTC
61d7dab Support more than 2 inputs for ONNX Min/Max import. 12 September 2018, 22:12:14 UTC
8b48976 Adding CNTK 2.6 release work summary to current_iteration.md 12 September 2018, 18:12:10 UTC
b374e14 fixes on Batchnorm and Pooling for v1 pretrained models after removal of sequence axis from input 12 September 2018, 17:02:52 UTC
5897265 small patch on conv/pooling export - when pads are all zero, check if autopad is true. - when pads are all zero, check if ceilOutDim is true, and extra cells are needed. 11 September 2018, 15:52:22 UTC
61572e8 Update onnx_model_test skip list 11 September 2018, 15:51:45 UTC
0754b38 update onnx_model_test with tests from onnx backend test 09 September 2018, 20:53:26 UTC
2f52f22 update conv/convtranspose/pooling import. pad values are explicitly computed based on ONNX spec equations during import in the following cases: - case 1: when auto_pad is SAME_UPPER | SAME_LOWER for convolution, convolution transpose and pooling. - case 2: when output_shape is explicitly set for convolution transpose. note: output_shape in ONNX spec can have the two below format: 1. [X1 * X2 * ... * Xn] 2. [N * O * X1 * X2 * ... * Xn] 09 September 2018, 20:41:04 UTC
d877233 Make broadcast ops compitable between CNTK and ONNX, Enable ONNX export/import for optimizedRNN op, More ONNX support for Sequence ops 09 September 2018, 15:59:33 UTC
fcf9f48 Overhaul conv/convTrans/pooling pads value export - Update exporting of conv/pooling to always export pad values. - Enable correct exporting of multiple pretrained models (ResNet50/ResNet101/ResNet152_ImageNet_Caffe, etc). - Overhaul convtranspose pads exporting - Support conv weight export with omitted out channel axis (LRN). - Add tests in onnx_op_test to cover the above changes 06 September 2018, 18:46:14 UTC
e3a1acf Resolve dependencies and build issues -Temporary add importorskip around import onnx -bump up .yml matplotlib version 05 September 2018, 22:02:23 UTC
dc5e482 fix onnx average pooling export. - this fix solves the issue that ceilOutDim == true will enforce exporting auto_pad as true, even if autoPadding is explicitly set to false. 31 August 2018, 01:19:04 UTC
back to top