| .. |
|
ComputationEnvironment.h
|
Fix gaps in sequence.reduce_sum and convolution
|
2017-03-09 21:45:46 -08:00 |
|
ComputationNetwork.cpp
|
Integrate vadimma/CTCCritNode into master
|
2017-02-19 00:22:27 -08:00 |
|
ComputationNetwork.h
|
Fix gaps in sequence.reduce_sum and convolution
|
2017-03-09 21:45:46 -08:00 |
|
ComputationNetworkAnalysis.cpp
|
…
|
|
|
ComputationNetworkBuilder.cpp
|
Merge remote-tracking branch 'origin/master' into v-yuxgu/pooling-include-padding
|
2017-03-22 17:37:34 +08:00 |
|
ComputationNetworkBuilder.h
|
Rename poolPadMode to includePad in python API
|
2017-03-17 15:11:06 +08:00 |
|
ComputationNetworkEditing.cpp
|
…
|
|
|
ComputationNetworkEvaluation.cpp
|
CNTK core: Made actual forward prop evaluation order consistent with the order in which we setup matrix sharing structure, to ensure proper evaluation of a set of nodes in accordance with the assumed evaluation order during allocating node value/gradient matrices.
|
2017-03-02 22:32:07 -08:00 |
|
ComputationNetworkLib.vcxproj
|
on build machine use the nvml.dll from the c:\local\bindrop if the directory exists
|
2017-03-27 15:46:16 +02:00 |
|
ComputationNetworkLib.vcxproj.filters
|
…
|
|
|
ComputationNetworkScripting.cpp
|
…
|
|
|
ComputationNode.cpp
|
Fix gaps in sequence.reduce_sum and convolution
|
2017-03-09 21:45:46 -08:00 |
|
ComputationNode.h
|
Merge remote-tracking branch 'origin/master' into v-yuxgu/pooling-include-padding
|
2017-03-22 17:37:34 +08:00 |
|
ComputationNodeScripting.cpp
|
…
|
|
|
ConvolutionalNodes.h
|
change pool pad into version 23
|
2017-03-22 17:37:58 +08:00 |
|
DeprecatedNodes.h
|
…
|
|
|
EvaluationNodes.h
|
fix build break
|
2017-03-26 17:53:27 -07:00 |
|
InputAndParamNodes.cpp
|
Enable bilinear initialization for ConvolutionTransposeLayer
|
2017-03-16 18:37:43 +01:00 |
|
InputAndParamNodes.h
|
CNTK v2 library: Add support for sparse inputs with sample shape > 1D
|
2017-03-09 17:41:09 -08:00 |
|
LinearAlgebraNodes.cpp
|
…
|
|
|
LinearAlgebraNodes.h
|
move one hot to evaluation nodes
|
2017-03-26 17:52:48 -07:00 |
|
MatrixPool.h
|
Adding a workspace memory in MatrixPool.h.
|
2017-03-02 12:08:41 -08:00 |
|
NonlinearityNodes.h
|
Address feedbacks.
|
2017-02-24 12:03:26 -08:00 |
|
PreComputeNodes.h
|
…
|
|
|
RNNNodes.cpp
|
…
|
|
|
RNNNodes.h
|
Slight code change to make memory allocation better when there's sparse matrices.
|
2017-02-17 17:07:42 -08:00 |
|
RecurrentNodes.cpp
|
removed a fragment of dead code that caused a bug
|
2017-02-15 18:15:10 -08:00 |
|
RecurrentNodes.h
|
pre-merged Layers-lib changes pertaining to the V1 execution engine and V2 wrapping:
|
2017-02-14 10:45:32 -08:00 |
|
ReshapingNodes.cpp
|
fix comments, add axis paramter, support invalid indices
|
2017-03-26 17:53:26 -07:00 |
|
ReshapingNodes.h
|
Multi-axis slice.
|
2017-03-21 17:13:35 -07:00 |
|
SpecialPurposeNodes.cpp
|
…
|
|
|
SpecialPurposeNodes.h
|
Add save and load to the CTC nodes
|
2017-03-14 18:21:04 -07:00 |
|
TrainingNodes.cpp
|
merged from master
|
2017-02-13 21:14:29 -08:00 |
|
TrainingNodes.h
|
addressed CR feedback
|
2017-02-23 17:16:00 -08:00 |
|
UserDefinedV2FunctionNode.h
|
CNTK v2 library: Several UserDefinedFunction features and bug fixes
|
2017-03-25 21:19:29 -07:00 |
|
stdafx.cpp
|
…
|
|
|
stdafx.h
|
…
|
|
|
targetver.h
|
…
|
|
