2019-06-06 14:21:15 +02:00
/*******************************************************************************
* Copyright ( c ) 2015 - 2018 Skymind , Inc .
*
* This program and the accompanying materials are made available under the
* terms of the Apache License , Version 2.0 which is available at
* https : //www.apache.org/licenses/LICENSE-2.0.
*
* Unless required by applicable law or agreed to in writing , software
* distributed under the License is distributed on an " AS IS " BASIS , WITHOUT
* WARRANTIES OR CONDITIONS OF ANY KIND , either express or implied . See the
* License for the specific language governing permissions and limitations
* under the License .
*
* SPDX - License - Identifier : Apache - 2.0
* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * */
//
// Based on PyTorch - https://github.com/pytorch/pytorch
//
# ifndef LIBND4J_CONVOLUTIONS_H
# define LIBND4J_CONVOLUTIONS_H
# include <NDArray.h>
# include <graph/Context.h>
# include <execution/LaunchContext.h>
namespace nd4j {
namespace ops {
enum PoolingType {
MAX_POOL = 0 ,
AVG_POOL = 1 ,
PNORM_POOL = 2 ,
} ;
class ConvolutionUtils {
public :
2019-11-29 12:14:30 +01:00
static inline void calcOutSizePool2D ( int & oH , int & oW , const int kH , const int kW , const int sH , const int sW , const int pH , const int pW , const int dH , const int dW , const int iH , const int iW , const int paddingMode ) {
if ( paddingMode = = 0 ) { // valid
oH = ( iH - ( kH + ( kH - 1 ) * ( dH - 1 ) ) + 2 * pH ) / sH + 1 ;
oW = ( iW - ( kW + ( kW - 1 ) * ( dW - 1 ) ) + 2 * pW ) / sW + 1 ;
}
else if ( paddingMode = = 1 ) { // same
2019-06-06 14:21:15 +02:00
oH = ( int ) math : : nd4j_ceil < double , double > ( iH * 1. / sH ) ;
oW = ( int ) math : : nd4j_ceil < double , double > ( iW * 1. / sW ) ;
}
2019-11-29 12:14:30 +01:00
else { // causal
oH = ( iH - 1 ) / sH + 1 ; // 2*pH = (kH-1)*dH
oW = ( iW - 1 ) / sW + 1 ;
2019-06-06 14:21:15 +02:00
}
}
2019-11-29 12:14:30 +01:00
static inline void calcOutSizePool3D ( int & oD , int & oH , int & oW , const int kD , const int kH , const int kW , const int sD , const int sH , const int sW , const int pD , const int pH , const int pW , const int dD , const int dH , const int dW , const int iD , const int iH , const int iW , const int paddingMode ) {
2019-06-06 14:21:15 +02:00
2019-11-29 12:14:30 +01:00
if ( paddingMode = = 0 ) { // valid
2019-06-06 14:21:15 +02:00
oD = ( iD - ( kD + ( kD - 1 ) * ( dD - 1 ) ) + 2 * pD ) / sD + 1 ;
oH = ( iH - ( kH + ( kH - 1 ) * ( dH - 1 ) ) + 2 * pH ) / sH + 1 ;
oW = ( iW - ( kW + ( kW - 1 ) * ( dW - 1 ) ) + 2 * pW ) / sW + 1 ;
}
2019-11-29 12:14:30 +01:00
else if ( paddingMode = = 1 ) { // same
2019-06-06 14:21:15 +02:00
oD = ( int ) nd4j : : math : : nd4j_ceil < double , double > ( iD * 1. / sD ) ;
oH = ( int ) nd4j : : math : : nd4j_ceil < double , double > ( iH * 1. / sH ) ;
oW = ( int ) nd4j : : math : : nd4j_ceil < double , double > ( iW * 1. / sW ) ;
2019-11-29 12:14:30 +01:00
}
else { // causal
oD = ( iD - 1 ) / sD + 1 ;
oH = ( iH - 1 ) / sH + 1 ; // 2*pH = (kH-1)*dH
oW = ( iW - 1 ) / sW + 1 ;
2019-06-06 14:21:15 +02:00
}
}
2019-11-29 12:14:30 +01:00
static inline void calcPadding2D ( int & pH , int & pW , int oH , int oW , int iH , int iW , int kH , int kW , int sH , int sW , int dH , int dW , const int paddingMode = 1 /* default is same mode*/ ) {
2019-06-06 14:21:15 +02:00
2019-11-29 12:14:30 +01:00
if ( paddingMode = = 0 ) // valid
return ;
if ( paddingMode = = 1 ) { // same
2019-06-06 14:21:15 +02:00
2019-11-29 12:14:30 +01:00
const int eKH = ( kH - 1 ) * dH + 1 ;
const int eKW = ( kW - 1 ) * dW + 1 ;
pH = ( ( oH - 1 ) * sH + eKH - iH ) / 2 ; //Note that padBottom is 1 bigger than this if bracketed term is not divisible by 2
pW = ( ( oW - 1 ) * sW + eKW - iW ) / 2 ;
}
else { // causal
pH = ( kH - 1 ) * dH ;
pW = ( kW - 1 ) * dW ;
2019-06-06 14:21:15 +02:00
}
2019-11-29 12:14:30 +01:00
}
static inline void calcPadding3D ( int & pD , int & pH , int & pW , const int oD , const int oH , const int oW , const int iD , const int iH , const int iW , const int kD , const int kH , const int kW , const int sD , const int sH , const int sW , const int dD , const int dH , const int dW , const int paddingMode = 1 /* default is same mode*/ ) {
if ( paddingMode = = 0 ) // valid
return ;
if ( paddingMode = = 1 ) { // same
2019-06-06 14:21:15 +02:00
2019-11-29 12:14:30 +01:00
const int eKD = ( kD - 1 ) * dD + 1 ;
const int eKH = ( kH - 1 ) * dH + 1 ;
const int eKW = ( kW - 1 ) * dW + 1 ;
2019-06-06 14:21:15 +02:00
2019-11-29 12:14:30 +01:00
pD = ( ( oD - 1 ) * sD + eKD - iD ) / 2 ;
pH = ( ( oH - 1 ) * sH + eKH - iH ) / 2 ; //Note that padBottom is 1 bigger than this if bracketed term is not divisible by 2
pW = ( ( oW - 1 ) * sW + eKW - iW ) / 2 ;
}
else { // causal
pD = ( kD - 1 ) * dD ;
pH = ( kH - 1 ) * dH ;
pW = ( kW - 1 ) * dW ;
}
2019-06-06 14:21:15 +02:00
}
// calculation of output height and width in 2D deconvolution procedure
2019-11-29 12:14:30 +01:00
static inline void calcOutSizeDeconv2D ( int & oH , int & oW , const int kH , const int kW , const int sH , const int sW , const int pH , const int pW , const int dH , const int dW , const int iH , const int iW , const int paddingMode ) {
if ( paddingMode ) {
2019-06-06 14:21:15 +02:00
oH = sH * iH ;
oW = sW * iW ;
}
else {
2019-11-29 12:14:30 +01:00
const int ekH = ( kH - 1 ) * dH + 1 ;
const int ekW = ( kW - 1 ) * dW + 1 ;
2019-06-06 14:21:15 +02:00
oH = sH * ( iH - 1 ) + ekH - 2 * pH ;
oW = sW * ( iW - 1 ) + ekW - 2 * pW ;
}
}
// calculation of output height and width in 3D deconvolution procedure
2019-11-29 12:14:30 +01:00
static inline void calcOutSizeDeconv3D ( int & oD , int & oH , int & oW , const int kD , const int kH , const int kW , const int sD , const int sH , const int sW , const int pD , const int pH , const int pW , const int dD , const int dH , const int dW , const int iD , const int iH , const int iW , const int paddingMode ) {
if ( paddingMode ) {
2019-06-06 14:21:15 +02:00
oD = sD * iD ;
oH = sH * iH ;
oW = sW * iW ;
}
else {
2019-11-29 12:14:30 +01:00
const int ekD = ( kD - 1 ) * dD + 1 ;
const int ekH = ( kH - 1 ) * dH + 1 ;
const int ekW = ( kW - 1 ) * dW + 1 ;
2019-06-06 14:21:15 +02:00
oD = sD * ( iD - 1 ) + ekD - 2 * pD ;
oH = sH * ( iH - 1 ) + ekH - 2 * pH ;
oW = sW * ( iW - 1 ) + ekW - 2 * pW ;
}
}
// evaluates sizes values and indexes using input and output arrays depending on data format
static inline void getSizesAndIndexesConv2d ( const bool isNCHW , const NDArray & input , const NDArray & output , int & bS , int & iC , int & iH , int & iW , int & oC , int & oH , int & oW , int & indIOioC , int & indIiH , int & indWiC , int & indWoC , int & indWkH , int & indOoH ) {
getSizesAndIndexesConv2d ( isNCHW , input . getShapeInfo ( ) , output . getShapeInfo ( ) , bS , iC , iH , iW , oC , oH , oW , indIOioC , indIiH , indWiC , indWoC , indWkH , indOoH ) ;
}
static inline void getSizesAndIndexesConv2d ( const bool isNCHW , const Nd4jLong * inShapeInfo , const Nd4jLong * outShapeInfo , int & bS , int & iC , int & iH , int & iW , int & oC , int & oH , int & oW , int & indIOioC , int & indIiH , int & indWiC , int & indWoC , int & indWkH , int & indOoH ) {
// input [bS, iH, iW, iC] (NHWC) or [bS, iC, iH, iW] (NCHW)
// weights [kH, kW, iC, oC] always
// output [bS, oH, oW, oC] (NHWC) or [bS, oC, oH, oW] (NCHW)
indWkH = 0 ; indWiC = 2 ; indWoC = 3 ;
if ( ! isNCHW ) {
indIOioC = 3 ; indIiH = 1 ; indOoH = 1 ;
}
else {
indIOioC = 1 ; indIiH = 2 ; indOoH = 2 ;
}
bS = inShapeInfo [ 1 ] ; // batch size
iC = inShapeInfo [ indIOioC + 1 ] ; // input channels
iH = inShapeInfo [ indIiH + 1 ] ; // input height
iW = inShapeInfo [ indIiH + 2 ] ; // input width
oC = outShapeInfo [ indIOioC + 1 ] ; // output channels
oH = outShapeInfo [ indOoH + 1 ] ; // output height
oW = outShapeInfo [ indOoH + 2 ] ; // output width
}
// evaluates sizes values and indexes using input and output arrays depending on data format
static inline void getSizesAndIndexesConv3d ( const bool isNCDHW , const NDArray & input , const NDArray & output , int & bS , int & iC , int & iD , int & iH , int & iW , int & oC , int & oD , int & oH , int & oW , int & indIOioC , int & indIOioD , int & indWiC , int & indWoC , int & indWkD ) {
// input [bS, iD, iH, iW, iC] (NDHWC) or [bS, iC, iD, iH, iW] (NCDHW)
// weights [kD, kH, kW, iC, oC] (NDHWC) or [oC, iC, kD, kH, kW] (NCDHW)
// output [bS, oD, oH, oW, oC] (NDHWC) or [bS, oC, oD, oH, oW] (NCDHW)
indWkD = 0 ; indWiC = 3 ; indWoC = 4 ;
if ( ! isNCDHW ) {
indIOioC = 4 ; indIOioD = 1 ;
}
else {
indIOioC = 1 ; indIOioD = 2 ;
}
bS = input . sizeAt ( 0 ) ; // batch size
iC = input . sizeAt ( indIOioC ) ; // input channels
iD = input . sizeAt ( indIOioD ) ; // input depth
iH = input . sizeAt ( indIOioD + 1 ) ; // input height
iW = input . sizeAt ( indIOioD + 2 ) ; // input width
oC = output . sizeAt ( indIOioC ) ; // output channels
oD = output . sizeAt ( indIOioD ) ; // output depth
oH = output . sizeAt ( indIOioD + 1 ) ; // output height
oW = output . sizeAt ( indIOioD + 2 ) ; // output width
}
2019-11-29 12:14:30 +01:00
// static inline void calcPaddingAndDilationForConv2DMKL(const int iH, const int iW, const int oH, const int oW, const int kH, const int kW, const int sH, const int sW, const int paddingMode, int& pH, int& pW, int& dH, int& dW) {
2019-11-21 20:17:30 +01:00
// if(kH != 1) {
2019-11-29 12:14:30 +01:00
// if(paddingMode) {
2019-11-21 20:17:30 +01:00
// pH = (oH - 1) * sH - iH + kH - pH;
// dH = dH - 1;
// }
// else
// dH = (iH + 2*pH - (oH - 1) * sH - kH) / (kH - 1);
// }
// if(kW != 1) {
2019-11-29 12:14:30 +01:00
// if(paddingMode) {
2019-11-21 20:17:30 +01:00
// pW = (oW - 1) * sW - iW + kW - pW;
// dW = dW - 1;
// }
// else
// dW = (iW + 2*pW - (oW - 1) * sW - kW) / (kW - 1);
// }
// }
2019-11-29 12:14:30 +01:00
// static inline void calcPaddingAndDilationForConv3DMKL(const int iD, const int iH, const int iW, const int oD, const int oH, const int oW, const int kD, const int kH, const int kW, const int sD, const int sH, const int sW, const int paddingMode, int& pD, int& pH, int& pW, int& dD, int& dH, int& dW) {
2019-11-21 20:17:30 +01:00
// if(kD != 1) {
2019-11-29 12:14:30 +01:00
// if(paddingMode) {
2019-11-21 20:17:30 +01:00
// pD = (oD - 1) * sD - iD + kD - pD;
// dD = dD - 1;
// }
// else
// dD = (iD + 2*pD - (oD - 1) * sD - kD) / (kD - 1);
// }
// if(kH != 1) {
2019-11-29 12:14:30 +01:00
// if(paddingMode) {
2019-11-21 20:17:30 +01:00
// pH = (oH - 1) * sH - iH + kH - pH;
// dH = dH - 1;
// }
// else
// dH = (iH + 2*pH - (oH - 1) * sH - kH) / (kH - 1);
// }
// if(kW != 1) {
2019-11-29 12:14:30 +01:00
// if(paddingMode) {
2019-11-21 20:17:30 +01:00
// pW = (oW - 1) * sW - iW + kW - pW;
// dW = dW - 1;
// }
// else
// dW = (iW + 2*pW - (oW - 1) * sW - kW) / (kW - 1);
// }
// }
2019-11-14 18:21:22 +01:00
2019-11-29 12:14:30 +01:00
static void conv2d ( nd4j : : graph : : Context & context , const NDArray * input , const NDArray * weights , const NDArray * bias , NDArray * output , const int kH , const int kW , const int sH , const int sW , int pH , int pW , const int dH , const int dW , const int paddingMode , const int isNCHW ) ;
2019-06-06 14:21:15 +02:00
Merge master to upstream (#7945)
* Shugeo strided slice zeros (#14)
* Modified strided_slice op to properly work with empty-like shapes.
* Fixed test for reduce_mean with empty-like input.
* [WIP] Last merge (#15)
* correct logsoftmax looss (#2)
* Small SameDiff listener fix (#4)
* Various fixes (#6)
* #7839 Fix for asXMatrix and tests
* #7866 EmbeddingSequenceLayer dtype fix + test
* #7856 SameDiff save/load stream methods
* #7859 RegressionEvaluation rank 4 fix + tests + axis configuration
* EvaluationBinary 3d/4d
* More evaluation 3d/4d tests
* #7847 Evaluation empty checks
* Small test ifx
* #7848 Fix median edge case
* Improve DL4J samediff layer tests
* [WIP] FastText wrapper implemented (#8)
* FastText implemented
* Some fixes
* Fix shapes for wordsNearest
* Validation of input vectors
* Fixes
* Fixed test
* Thread tagged
* Some tweaks
* setContextClassLoader for DeallocatorServiceThread
* Numpy format tests (#1)
* Various fixes (#11)
* #7852 SameDiff gather fix
* #7892 SameDiff placeholder to constant conversion
* #7890 validate input rank for MLN/CG init methods
* Fix broken permute shape calculation
* Permute and gather fixes
* Tests
* #7850 LogSumExp fix + test
* Handful of test fixes
* Empty arrays with non-scalar shapes (#10)
* minor rearrangements for lambdas
* empty tensors with non-scalar shapes
* numpy empty tensors with non-scalar shapes
* few more empty tweaks
* Small fixes
* conv3d signature update
* micro fix in batchnorm mkldnn
* Import fixes
* Fix
* MKL-DNN update
* Small fill fix
* fill with empty input + test
* Fixes
* Small error improvement
* Fix
* one special test
* couple of fixes for lstm
* Rewrite TFGraphMapper.getNDArrayFromTensor to be maintainable and less error prone
* Fixes
* FP16
* Unsigned
* BFloat16
* Fill op - empty tweaks
* - couple of fixes for empty arrays construction
- stack updated
* strided slice fix
* one transform test
* provide method for reducing shapeInfo in case of input array is empty
* Fixed reduceAlongDimensions to use empty input properly.
* couple of broadcast tests
* couple of tests broadcast tests + tweak to make them pass
* add check of non-empty to methods producing sub-arrays
* Fixed reshapeC with zeros in shape.
* complete empty check in reduce_... legacy ops
* Concat and cumsum/prod
* Tweak to empty shape inference on import
* add empty check to the rest of reduce legacy ops
* one more test
* correct typo in evalReduceShapeInfoEmpty
* Added tests for reduce_* ops to tests with zero shapes.
* few more tests for empty reductions
* Fixed strided_slice op with empty case and tests.
* one more empty reduction test
* Fixed strided_slice test.
* add empty check to NDArray::reshapei
* infOrMax
* empty min/max with infinity tests
* made unstack working correctly with empty arrays
* few IndexReduce tests + tweaks for empty shapes
* add test for empty concat
* few tests fixed
* Validation fix for reductions on empty shapes
* Reverse fix
* Reduction shape calc fixes
* SameDiff.generateOutputVariable: don't use shape function to determine number of outputs
* Range fix
* - NDArray constructor updated for scalars/empty arrays
- few tests fixed
* More fixes
* Empty creator fixes
* concat fix
* concat fix
* TF import tests: allow 'both all NaN' and 'both all inf' to pass
* Slice, zero fraction, and reshape fixes
* transpose, gather
* Zero fraction
* scalar cast fix
* Empty reduction axis support
* few more tests fixed
* Fixed input checks conforming with TF for concat op and tests.
* few tests fixed
* matmul scalar shape fix
* Fixed checkout for data type and scalarity with concat to allow non-empty scalars with vector concats.
* broadcast bool fix
* few more tests
* few more tests
* correct evalReduceShapeInfoEmpty
* argmax/argmin + tests
* one more empty edge case + one more test
* argmax/argmin/realdiv_bp tweaks
* empty reshape test + fix
* Helper fixes
* Small fixes
* Gather test fix
* Gather test fix
* Small fixes
* reduce scalar zero values
* scalar mean workaround
* Remove debug code
* along dim mean workaround
* one more test
* - equalsTo() tweak for empty arrays
- one more test
* broadcast tweaks
* [WIP] Fixing outstanding issues for NLP (#9)
* Avoid using not-inited objects
* Test fixed.
* Redundant method avoided for models like FastText
* KMeans++ implementation
* KMeans++ implementation
* Disable parallel execution
* KMeans++
* Tests
* Dev branch merge (#16)
* SameDiff: convertDataType and gradient check util improvements (#12)
* GradCheck util improvements
* StopGradient constructor + test
* SameDiff: Add datatype conversion
* Javadoc and add DataType.isNumerical()
* Small fix
* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)
* TFGraphTestAllHelper: check intermediates in execution order
* Add missing debug listener
* [WIP] lstmBlock fix + other changes (#13)
- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite
* Small test fix
* CheckNumerics op wrapper
* Fix some issues on master (#17)
* Fix DataVec test issue
* Fix issue with dl4j SameDiff output layer
* Dtype fix for lambda layers
* #7912 BertIterator dtype fix (use float32 not global default)
* [WIP] Next set of CUDA stuff (#7)
New CUDA implementations and improvements
* bad file
* Dev branch master merge (#23)
* SameDiff: convertDataType and gradient check util improvements (#12)
* GradCheck util improvements
* StopGradient constructor + test
* SameDiff: Add datatype conversion
* Javadoc and add DataType.isNumerical()
* Small fix
* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)
* TFGraphTestAllHelper: check intermediates in execution order
* Add missing debug listener
* [WIP] lstmBlock fix + other changes (#13)
- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite
* Small test fix
* CheckNumerics op wrapper
* Compatibility of deserialization (#18)
Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>
* SameDiff: add activation gradient checking support for debugging (#19)
* SameDiff gradient checker: first pass on activation gradient checks
* Fixes + tests for activation gradient checking
* Javadoc
* [WIP] Some nd4j data type corrections (#20)
* Adjust data type
* Set correct Data type.
* Size of proper data type.
* fix averaged cpu load (#22)
* SameDiff ops, TF import and fixes (#24)
* CheckNumerics tests + fixes + misc fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fake quant
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* FakeQuantWithMinMaxArgs
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* CheckNumerics fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix libnd4j ALL_INTS and ALL_FLOATS declaration (uint and bfloat types)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Small fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Javadoc
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Exception tweak
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix for out of scope stack allocated var use
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Ignores
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Ignore for known failing test (already logged issue)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Merge upstream to fork (#25)
* Add thousand-separator commas to TotalParams (#7915)
* Add thousand-separator commas to TotalParams
The number of parameters can be quite large, and it would help the reading of the summary printout to have the TotalParams column & values at the bottom have thousand-separator-commas in them.
* Add thousand-separator commas to MultiLayerNetwork
Corresponding change to MultiLayerNetwork
Signed-off-by: Jxtps Jxtps <jxtps435@gmail.com>
* Update contributing and issue/PR templates (#7934)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix link to AdaDelta paper (#7942)
Fix link to AdaDelta paper hosted on matthewzeiler.com
Signed-off-by: Jxtps
* Fixes, and ignores for known/logged failing issues (#7943)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* SameDiff + DL4J/SameDiff: Multiple fixes (#28)
* #7919 HDF5 attribute buffer length fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7909 Arbiter constructor exception ux improvements
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7925 RNN output layer length checks
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7939 Add listener for validating inputs are not incorrectly modified
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7939 Integrate NonInplaceValidationListener into tests
* #7844 DL4J SameDiff fixes for variable minibatch size
* DL4J SameDiff fixes - ensure gradient for input placeholder is available
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Tweaks to ExternalErrorsFunction - use placeholders, make more robust
* Another fix
* More fixes
* More SameDiff/DL4J fixes
* Scope out scalar array creation in BaseScalarOp
* Remove debug code
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* [WIP] Final dev branch merge (#29)
* SameDiff: convertDataType and gradient check util improvements (#12)
* GradCheck util improvements
* StopGradient constructor + test
* SameDiff: Add datatype conversion
* Javadoc and add DataType.isNumerical()
* Small fix
* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)
* TFGraphTestAllHelper: check intermediates in execution order
* Add missing debug listener
* [WIP] lstmBlock fix + other changes (#13)
- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite
* Small test fix
* CheckNumerics op wrapper
* Compatibility of deserialization (#18)
Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>
* SameDiff: add activation gradient checking support for debugging (#19)
* SameDiff gradient checker: first pass on activation gradient checks
* Fixes + tests for activation gradient checking
* Javadoc
* [WIP] Some nd4j data type corrections (#20)
* Adjust data type
* Set correct Data type.
* Size of proper data type.
* fix averaged cpu load (#22)
* [WIP] Multiple dataset iterators (#27)
* Splitting dataset into arbitrary number
* Fixes
* Multiple split of iterator
* Test
* Test
* Some fixes
* signature change
* one more tweak
Signed-off-by: raver119 <raver119@gmail.com>
* one more test for sequential use of DataSetIteratorSplitter
Signed-off-by: raver119 <raver119@gmail.com>
* Fixes
* Fixes
* one more test for Alexander
Signed-off-by: raver119 <raver119@gmail.com>
* Some fixes
* Some fixes
* one more test for Alexander
Signed-off-by: raver119 <raver119@gmail.com>
* minor test fix
Signed-off-by: raver119 <raver119@gmail.com>
* Some fixes
* Some fixes
* couple of assertions tweaked
Signed-off-by: raver119 <raver119@gmail.com>
* MDS splitter test :/
Signed-off-by: raver119 <raver119@gmail.com>
* Minor refactoring
* Multi dataset
* Some fixes
* More tests
* Small number of test fixes/improvements (failures on CI) (#31)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* [WIP] More CUDA stuff (#26)
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* LRN BP CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* less memory
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed bug with crop_and_resize op helper.
* get rid of unnecessary index-calculation dunction
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed sort with nth_element cuda-based helper.
* Refactored nth_element.
* Refactored nth_element op and tests.
* Modified usage of dim array with sortTad routine.
* Refactored main routine of helper for non_max_image_suppression op.
* non_max_image_suppression op helper with cuda kernel implementation. Initial revision.
* fix vol2col cuda kernel
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* topK concept
Signed-off-by: raver119 <raver119@gmail.com>
* unsorted topK with scanWitdh of 1
Signed-off-by: raver119 <raver119@gmail.com>
* correct vol2col tests
* sorted/unsorted topK
Signed-off-by: raver119 <raver119@gmail.com>
* implementation and fixing col2im/col2vol
* Corrected usage flags with input/output with reverse op.
* dup is const now
Signed-off-by: raver119 <raver119@gmail.com>
* percentile op
Signed-off-by: raver119 <raver119@gmail.com>
* group tests for mapool2d
Signed-off-by: Yurii <yurii@skymind.io>
* special test for george
Signed-off-by: raver119 <raver119@gmail.com>
* less threads for sortTad
Signed-off-by: raver119 <raver119@gmail.com>
* provide conv2d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* remove auther in sort tad kernel code
Signed-off-by: Yurii <yurii@skymind.io>
* provide depthwise_conv2d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* - max_pooling_with_argmax
- null check for special use
Signed-off-by: raver119 <raver119@gmail.com>
* dts cuda
Signed-off-by: raver119 <raver119@gmail.com>
* provide sconv2d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* std cuda
Signed-off-by: raver119 <raver119@gmail.com>
* Refactored non_max_suppression op to conform TF implementation.
* Improved suppression helper.
* provide pooling3d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* minor lstm rearrangements
Signed-off-by: raver119 <raver119@gmail.com>
* more of minor lstm rearrangements
Signed-off-by: raver119 <raver119@gmail.com>
* (bi)dynamic_rnn
Signed-off-by: raver119 <raver119@gmail.com>
* templates init order
Signed-off-by: raver119 <raver119@gmail.com>
* Refactored non_max_suppression op.
* Added cuda kernel for non_max_suppression.
* CPU sort by key/value
Signed-off-by: raver119 <raver119@gmail.com>
* CPU sort TAD by key/value
Signed-off-by: raver119 <raver119@gmail.com>
* CPU sort TAD by key/value tests
Signed-off-by: raver119 <raver119@gmail.com>
* Eliminate compiler error with cuda implementation.
* - repaired gradCheck in cuda
- provide conv2d_bp for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* missed signature
Signed-off-by: raver119 <raver119@gmail.com>
* provide depthwise_conv2d_bp for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* Implementation of lup helper with cuda kernel. Initial commit.
* further work on backprops for convolutions
Signed-off-by: Yurii <yurii@skymind.io>
* CUDA linear sort by key/val
Signed-off-by: raver119 <raver119@gmail.com>
* CUDA tad sort by key/val
Signed-off-by: raver119 <raver119@gmail.com>
* start providing of backprop for pooling2d/3d
Signed-off-by: Yurii <yurii@skymind.io>
* Added atomicAdd for bool datatype.
* dynamic partition concept
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic partition concept
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic partition scalar CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* important comment
Signed-off-by: raver119 <raver119@gmail.com>
* fix pooling2d/3d backprop helpers
Signed-off-by: Yurii <yurii@skymind.io>
* Added non-linear test with dynamic_partition.
* Improved test for dynamic_partition.
* dynamic_partition TAD concept
Signed-off-by: raver119 <raver119@gmail.com>
* - dynamic_partition TAD CUDA impl
- dynamic_partition TAD CPU fix
Signed-off-by: raver119 <raver119@gmail.com>
* - rewrite cpu code for usampling2d/3d
- write cuda code for usampling2d/3d
Signed-off-by: Yurii <yurii@skymind.io>
* dynamic_stitch CUDA vector case
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic_stitch CUDA TAD case concept
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic_stitch CUDA TAD case impl
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for dynamic_stitch 3D-4D cases.
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed type check for dynamic stitch.
* min/max bp
Signed-off-by: raver119 <raver119@gmail.com>
* rewrite code for upsampling2d/3d cpu
Signed-off-by: Yurii <yurii@skymind.io>
* reduce min/max/norm_max bp
Signed-off-by: raver119 <raver119@gmail.com>
* lup implementation. Additional enhancements.
* provide code for upsamling2d/3d backprop
Signed-off-by: Yurii <yurii@skymind.io>
* weightedCrossEntropyWithLogits
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed template math atomicMul for 64bit ints.
* Refactored dynamic_partition_bp op.
* inverseBroadcast fix
Signed-off-by: raver119 <raver119@gmail.com>
* DynamicPartitionBP test datatype fixed.
* - nd4j_atomicMul Windows fix
- cpu/NDArrayLambda.hpp excluded from CUDA
Signed-off-by: raver119 <raver119@gmail.com>
2019-06-27 17:37:04 +02:00
// static void conv2d(nd4j::graph::Context & block, const std::vector<NDArray*>& inArrs, NDArray* output, const std::vector<int>& intArgs);
2019-06-06 14:21:15 +02:00
Merge master to upstream (#7945)
* Shugeo strided slice zeros (#14)
* Modified strided_slice op to properly work with empty-like shapes.
* Fixed test for reduce_mean with empty-like input.
* [WIP] Last merge (#15)
* correct logsoftmax looss (#2)
* Small SameDiff listener fix (#4)
* Various fixes (#6)
* #7839 Fix for asXMatrix and tests
* #7866 EmbeddingSequenceLayer dtype fix + test
* #7856 SameDiff save/load stream methods
* #7859 RegressionEvaluation rank 4 fix + tests + axis configuration
* EvaluationBinary 3d/4d
* More evaluation 3d/4d tests
* #7847 Evaluation empty checks
* Small test ifx
* #7848 Fix median edge case
* Improve DL4J samediff layer tests
* [WIP] FastText wrapper implemented (#8)
* FastText implemented
* Some fixes
* Fix shapes for wordsNearest
* Validation of input vectors
* Fixes
* Fixed test
* Thread tagged
* Some tweaks
* setContextClassLoader for DeallocatorServiceThread
* Numpy format tests (#1)
* Various fixes (#11)
* #7852 SameDiff gather fix
* #7892 SameDiff placeholder to constant conversion
* #7890 validate input rank for MLN/CG init methods
* Fix broken permute shape calculation
* Permute and gather fixes
* Tests
* #7850 LogSumExp fix + test
* Handful of test fixes
* Empty arrays with non-scalar shapes (#10)
* minor rearrangements for lambdas
* empty tensors with non-scalar shapes
* numpy empty tensors with non-scalar shapes
* few more empty tweaks
* Small fixes
* conv3d signature update
* micro fix in batchnorm mkldnn
* Import fixes
* Fix
* MKL-DNN update
* Small fill fix
* fill with empty input + test
* Fixes
* Small error improvement
* Fix
* one special test
* couple of fixes for lstm
* Rewrite TFGraphMapper.getNDArrayFromTensor to be maintainable and less error prone
* Fixes
* FP16
* Unsigned
* BFloat16
* Fill op - empty tweaks
* - couple of fixes for empty arrays construction
- stack updated
* strided slice fix
* one transform test
* provide method for reducing shapeInfo in case of input array is empty
* Fixed reduceAlongDimensions to use empty input properly.
* couple of broadcast tests
* couple of tests broadcast tests + tweak to make them pass
* add check of non-empty to methods producing sub-arrays
* Fixed reshapeC with zeros in shape.
* complete empty check in reduce_... legacy ops
* Concat and cumsum/prod
* Tweak to empty shape inference on import
* add empty check to the rest of reduce legacy ops
* one more test
* correct typo in evalReduceShapeInfoEmpty
* Added tests for reduce_* ops to tests with zero shapes.
* few more tests for empty reductions
* Fixed strided_slice op with empty case and tests.
* one more empty reduction test
* Fixed strided_slice test.
* add empty check to NDArray::reshapei
* infOrMax
* empty min/max with infinity tests
* made unstack working correctly with empty arrays
* few IndexReduce tests + tweaks for empty shapes
* add test for empty concat
* few tests fixed
* Validation fix for reductions on empty shapes
* Reverse fix
* Reduction shape calc fixes
* SameDiff.generateOutputVariable: don't use shape function to determine number of outputs
* Range fix
* - NDArray constructor updated for scalars/empty arrays
- few tests fixed
* More fixes
* Empty creator fixes
* concat fix
* concat fix
* TF import tests: allow 'both all NaN' and 'both all inf' to pass
* Slice, zero fraction, and reshape fixes
* transpose, gather
* Zero fraction
* scalar cast fix
* Empty reduction axis support
* few more tests fixed
* Fixed input checks conforming with TF for concat op and tests.
* few tests fixed
* matmul scalar shape fix
* Fixed checkout for data type and scalarity with concat to allow non-empty scalars with vector concats.
* broadcast bool fix
* few more tests
* few more tests
* correct evalReduceShapeInfoEmpty
* argmax/argmin + tests
* one more empty edge case + one more test
* argmax/argmin/realdiv_bp tweaks
* empty reshape test + fix
* Helper fixes
* Small fixes
* Gather test fix
* Gather test fix
* Small fixes
* reduce scalar zero values
* scalar mean workaround
* Remove debug code
* along dim mean workaround
* one more test
* - equalsTo() tweak for empty arrays
- one more test
* broadcast tweaks
* [WIP] Fixing outstanding issues for NLP (#9)
* Avoid using not-inited objects
* Test fixed.
* Redundant method avoided for models like FastText
* KMeans++ implementation
* KMeans++ implementation
* Disable parallel execution
* KMeans++
* Tests
* Dev branch merge (#16)
* SameDiff: convertDataType and gradient check util improvements (#12)
* GradCheck util improvements
* StopGradient constructor + test
* SameDiff: Add datatype conversion
* Javadoc and add DataType.isNumerical()
* Small fix
* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)
* TFGraphTestAllHelper: check intermediates in execution order
* Add missing debug listener
* [WIP] lstmBlock fix + other changes (#13)
- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite
* Small test fix
* CheckNumerics op wrapper
* Fix some issues on master (#17)
* Fix DataVec test issue
* Fix issue with dl4j SameDiff output layer
* Dtype fix for lambda layers
* #7912 BertIterator dtype fix (use float32 not global default)
* [WIP] Next set of CUDA stuff (#7)
New CUDA implementations and improvements
* bad file
* Dev branch master merge (#23)
* SameDiff: convertDataType and gradient check util improvements (#12)
* GradCheck util improvements
* StopGradient constructor + test
* SameDiff: Add datatype conversion
* Javadoc and add DataType.isNumerical()
* Small fix
* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)
* TFGraphTestAllHelper: check intermediates in execution order
* Add missing debug listener
* [WIP] lstmBlock fix + other changes (#13)
- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite
* Small test fix
* CheckNumerics op wrapper
* Compatibility of deserialization (#18)
Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>
* SameDiff: add activation gradient checking support for debugging (#19)
* SameDiff gradient checker: first pass on activation gradient checks
* Fixes + tests for activation gradient checking
* Javadoc
* [WIP] Some nd4j data type corrections (#20)
* Adjust data type
* Set correct Data type.
* Size of proper data type.
* fix averaged cpu load (#22)
* SameDiff ops, TF import and fixes (#24)
* CheckNumerics tests + fixes + misc fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fake quant
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* FakeQuantWithMinMaxArgs
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* CheckNumerics fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix libnd4j ALL_INTS and ALL_FLOATS declaration (uint and bfloat types)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Small fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Javadoc
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Exception tweak
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix for out of scope stack allocated var use
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Ignores
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Ignore for known failing test (already logged issue)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Merge upstream to fork (#25)
* Add thousand-separator commas to TotalParams (#7915)
* Add thousand-separator commas to TotalParams
The number of parameters can be quite large, and it would help the reading of the summary printout to have the TotalParams column & values at the bottom have thousand-separator-commas in them.
* Add thousand-separator commas to MultiLayerNetwork
Corresponding change to MultiLayerNetwork
Signed-off-by: Jxtps Jxtps <jxtps435@gmail.com>
* Update contributing and issue/PR templates (#7934)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Fix link to AdaDelta paper (#7942)
Fix link to AdaDelta paper hosted on matthewzeiler.com
Signed-off-by: Jxtps
* Fixes, and ignores for known/logged failing issues (#7943)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* SameDiff + DL4J/SameDiff: Multiple fixes (#28)
* #7919 HDF5 attribute buffer length fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7909 Arbiter constructor exception ux improvements
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7925 RNN output layer length checks
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7939 Add listener for validating inputs are not incorrectly modified
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7939 Integrate NonInplaceValidationListener into tests
* #7844 DL4J SameDiff fixes for variable minibatch size
* DL4J SameDiff fixes - ensure gradient for input placeholder is available
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Tweaks to ExternalErrorsFunction - use placeholders, make more robust
* Another fix
* More fixes
* More SameDiff/DL4J fixes
* Scope out scalar array creation in BaseScalarOp
* Remove debug code
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* [WIP] Final dev branch merge (#29)
* SameDiff: convertDataType and gradient check util improvements (#12)
* GradCheck util improvements
* StopGradient constructor + test
* SameDiff: Add datatype conversion
* Javadoc and add DataType.isNumerical()
* Small fix
* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)
* TFGraphTestAllHelper: check intermediates in execution order
* Add missing debug listener
* [WIP] lstmBlock fix + other changes (#13)
- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite
* Small test fix
* CheckNumerics op wrapper
* Compatibility of deserialization (#18)
Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>
* SameDiff: add activation gradient checking support for debugging (#19)
* SameDiff gradient checker: first pass on activation gradient checks
* Fixes + tests for activation gradient checking
* Javadoc
* [WIP] Some nd4j data type corrections (#20)
* Adjust data type
* Set correct Data type.
* Size of proper data type.
* fix averaged cpu load (#22)
* [WIP] Multiple dataset iterators (#27)
* Splitting dataset into arbitrary number
* Fixes
* Multiple split of iterator
* Test
* Test
* Some fixes
* signature change
* one more tweak
Signed-off-by: raver119 <raver119@gmail.com>
* one more test for sequential use of DataSetIteratorSplitter
Signed-off-by: raver119 <raver119@gmail.com>
* Fixes
* Fixes
* one more test for Alexander
Signed-off-by: raver119 <raver119@gmail.com>
* Some fixes
* Some fixes
* one more test for Alexander
Signed-off-by: raver119 <raver119@gmail.com>
* minor test fix
Signed-off-by: raver119 <raver119@gmail.com>
* Some fixes
* Some fixes
* couple of assertions tweaked
Signed-off-by: raver119 <raver119@gmail.com>
* MDS splitter test :/
Signed-off-by: raver119 <raver119@gmail.com>
* Minor refactoring
* Multi dataset
* Some fixes
* More tests
* Small number of test fixes/improvements (failures on CI) (#31)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* [WIP] More CUDA stuff (#26)
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* LRN BP CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* less memory
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed bug with crop_and_resize op helper.
* get rid of unnecessary index-calculation dunction
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed sort with nth_element cuda-based helper.
* Refactored nth_element.
* Refactored nth_element op and tests.
* Modified usage of dim array with sortTad routine.
* Refactored main routine of helper for non_max_image_suppression op.
* non_max_image_suppression op helper with cuda kernel implementation. Initial revision.
* fix vol2col cuda kernel
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* topK concept
Signed-off-by: raver119 <raver119@gmail.com>
* unsorted topK with scanWitdh of 1
Signed-off-by: raver119 <raver119@gmail.com>
* correct vol2col tests
* sorted/unsorted topK
Signed-off-by: raver119 <raver119@gmail.com>
* implementation and fixing col2im/col2vol
* Corrected usage flags with input/output with reverse op.
* dup is const now
Signed-off-by: raver119 <raver119@gmail.com>
* percentile op
Signed-off-by: raver119 <raver119@gmail.com>
* group tests for mapool2d
Signed-off-by: Yurii <yurii@skymind.io>
* special test for george
Signed-off-by: raver119 <raver119@gmail.com>
* less threads for sortTad
Signed-off-by: raver119 <raver119@gmail.com>
* provide conv2d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* remove auther in sort tad kernel code
Signed-off-by: Yurii <yurii@skymind.io>
* provide depthwise_conv2d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* - max_pooling_with_argmax
- null check for special use
Signed-off-by: raver119 <raver119@gmail.com>
* dts cuda
Signed-off-by: raver119 <raver119@gmail.com>
* provide sconv2d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* std cuda
Signed-off-by: raver119 <raver119@gmail.com>
* Refactored non_max_suppression op to conform TF implementation.
* Improved suppression helper.
* provide pooling3d for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* minor lstm rearrangements
Signed-off-by: raver119 <raver119@gmail.com>
* more of minor lstm rearrangements
Signed-off-by: raver119 <raver119@gmail.com>
* (bi)dynamic_rnn
Signed-off-by: raver119 <raver119@gmail.com>
* templates init order
Signed-off-by: raver119 <raver119@gmail.com>
* Refactored non_max_suppression op.
* Added cuda kernel for non_max_suppression.
* CPU sort by key/value
Signed-off-by: raver119 <raver119@gmail.com>
* CPU sort TAD by key/value
Signed-off-by: raver119 <raver119@gmail.com>
* CPU sort TAD by key/value tests
Signed-off-by: raver119 <raver119@gmail.com>
* Eliminate compiler error with cuda implementation.
* - repaired gradCheck in cuda
- provide conv2d_bp for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* missed signature
Signed-off-by: raver119 <raver119@gmail.com>
* provide depthwise_conv2d_bp for cuda
Signed-off-by: Yurii <yurii@skymind.io>
* Implementation of lup helper with cuda kernel. Initial commit.
* further work on backprops for convolutions
Signed-off-by: Yurii <yurii@skymind.io>
* CUDA linear sort by key/val
Signed-off-by: raver119 <raver119@gmail.com>
* CUDA tad sort by key/val
Signed-off-by: raver119 <raver119@gmail.com>
* start providing of backprop for pooling2d/3d
Signed-off-by: Yurii <yurii@skymind.io>
* Added atomicAdd for bool datatype.
* dynamic partition concept
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic partition concept
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic partition scalar CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* important comment
Signed-off-by: raver119 <raver119@gmail.com>
* fix pooling2d/3d backprop helpers
Signed-off-by: Yurii <yurii@skymind.io>
* Added non-linear test with dynamic_partition.
* Improved test for dynamic_partition.
* dynamic_partition TAD concept
Signed-off-by: raver119 <raver119@gmail.com>
* - dynamic_partition TAD CUDA impl
- dynamic_partition TAD CPU fix
Signed-off-by: raver119 <raver119@gmail.com>
* - rewrite cpu code for usampling2d/3d
- write cuda code for usampling2d/3d
Signed-off-by: Yurii <yurii@skymind.io>
* dynamic_stitch CUDA vector case
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic_stitch CUDA TAD case concept
Signed-off-by: raver119 <raver119@gmail.com>
* dynamic_stitch CUDA TAD case impl
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for dynamic_stitch 3D-4D cases.
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed type check for dynamic stitch.
* min/max bp
Signed-off-by: raver119 <raver119@gmail.com>
* rewrite code for upsampling2d/3d cpu
Signed-off-by: Yurii <yurii@skymind.io>
* reduce min/max/norm_max bp
Signed-off-by: raver119 <raver119@gmail.com>
* lup implementation. Additional enhancements.
* provide code for upsamling2d/3d backprop
Signed-off-by: Yurii <yurii@skymind.io>
* weightedCrossEntropyWithLogits
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed template math atomicMul for 64bit ints.
* Refactored dynamic_partition_bp op.
* inverseBroadcast fix
Signed-off-by: raver119 <raver119@gmail.com>
* DynamicPartitionBP test datatype fixed.
* - nd4j_atomicMul Windows fix
- cpu/NDArrayLambda.hpp excluded from CUDA
Signed-off-by: raver119 <raver119@gmail.com>
2019-06-27 17:37:04 +02:00
// static void conv2dBP(nd4j::graph::Context & block, const std::vector<NDArray*>& inArrs, const std::vector<NDArray*>& outArrs, const std::vector<int>& intArgs);
2019-06-06 14:21:15 +02:00
2019-11-29 12:14:30 +01:00
static void conv2dBP ( nd4j : : graph : : Context & block , const NDArray * input , const NDArray * weights , const NDArray * bias , const NDArray * gradO , NDArray * gradI , NDArray * gradW , NDArray * gradB , const int kH , const int kW , const int sH , const int sW , int pH , int pW , const int dH , const int dW , const int paddingMode , const int isNCHW ) ;
2019-06-06 14:21:15 +02:00
2019-11-29 12:14:30 +01:00
static void depthwiseConv2d ( nd4j : : graph : : Context & block , const NDArray * input , const NDArray * weights , const NDArray * bias , NDArray * output , const int kH , const int kW , const int sH , const int sW , int pH , int pW , const int dH , const int dW , const int paddingMode , const int isNCHW ) ;
2019-06-06 14:21:15 +02:00
2019-11-29 12:14:30 +01:00
static void depthwiseConv2dBP ( nd4j : : graph : : Context & block , const NDArray * input , const NDArray * weights , const NDArray * bias , const NDArray * gradO , NDArray * gradI , NDArray * gradW , NDArray * gradB , const int kH , const int kW , const int sH , const int sW , int pH , int pW , const int dH , const int dW , const int paddingMode , const int isNCHW ) ;
2019-06-06 14:21:15 +02:00
2019-11-29 12:14:30 +01:00
static void sconv2d ( nd4j : : graph : : Context & block , const NDArray * input , const NDArray * weightsDepth , const NDArray * weightsPoint , const NDArray * bias , NDArray * output , const int kH , const int kW , const int sH , const int sW , int pH , int pW , const int dH , const int dW , const int paddingMode , const int isNCHW ) ;
2019-06-06 14:21:15 +02:00
2019-06-15 13:34:34 +02:00
static void vol2col ( nd4j : : graph : : Context & block , const NDArray & vol , NDArray & col , const int sD , const int sH , const int sW , const int pD , const int pH , const int pW , const int dD , const int dH , const int dW ) ;
2019-06-06 14:21:15 +02:00
2019-06-15 13:34:34 +02:00
static void col2vol ( nd4j : : graph : : Context & block , const NDArray & col , NDArray & vol , const int sD , const int sH , const int sW , const int pD , const int pH , const int pW , const int dD , const int dH , const int dW ) ;
2019-06-06 14:21:15 +02:00
2019-06-15 13:34:34 +02:00
static void upsampling2d ( nd4j : : graph : : Context & block , const NDArray & input , NDArray & output , const int factorH , const int factorW , const bool isNCHW ) ;
2019-06-06 14:21:15 +02:00
2019-06-15 13:34:34 +02:00
static void upsampling3d ( nd4j : : graph : : Context & block , const NDArray & input , NDArray & output , const int factorD , const int factorH , const int factorW , const bool isNCDHW ) ;
2019-06-06 14:21:15 +02:00
2019-06-15 13:34:34 +02:00
static void upsampling2dBP ( nd4j : : graph : : Context & block , const NDArray & gradO , NDArray & gradI , const bool isNCHW ) ;
2019-06-06 14:21:15 +02:00
2019-06-15 13:34:34 +02:00
static void upsampling3dBP ( nd4j : : graph : : Context & block , const NDArray & gradO , NDArray & gradI , const bool isNCDHW ) ;
2019-06-06 14:21:15 +02:00
2019-06-15 13:34:34 +02:00
static void pooling2d ( nd4j : : graph : : Context & block , const NDArray & input , NDArray & output , const int kH , const int kW , const int sH , const int sW , const int pH , const int pW , const int dH , const int dW , const PoolingType poolingMode , const int extraParam0 ) ;
2019-06-06 14:21:15 +02:00
2019-06-15 13:34:34 +02:00
static void pooling3d ( nd4j : : graph : : Context & block , const NDArray & input , NDArray & output , const int kD , const int kH , const int kW , const int sD , const int sH , const int sW , const int pD , const int pH , const int pW , const int dD , const int dH , const int dW , const int poolingMode , const int extraParam0 ) ;
2019-06-06 14:21:15 +02:00
2019-06-15 13:34:34 +02:00
static void pooling2dBP ( nd4j : : graph : : Context & block , const NDArray & input , const NDArray & gradO , NDArray & gradI , const int kH , const int kW , const int sH , const int sW , const int pH , const int pW , const int dH , const int dW , const int poolingMode , const int extraParam0 ) ;
2019-06-06 14:21:15 +02:00
2019-06-15 13:34:34 +02:00
static void pooling3dBP ( nd4j : : graph : : Context & block , const NDArray & input , const NDArray & gradO , NDArray & gradI , const int kD , const int kH , const int kW , const int sD , const int sH , const int sW , const int pD , const int pH , const int pW , const int dD , const int dH , const int dW , const int poolingMode , const int extraParam0 ) ;
2019-06-06 14:21:15 +02:00
} ;
}
}
# endif //LIBND4J_CONVOLUTIONS_H
