cavis/libnd4j/include/ops/declarable/generic/nn/recurrent/lstmCell.cpp

148 lines
10 KiB
C++
Raw Normal View History

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
******************************************************************************/
//
// @author Yurii Shyrma, created on 30.11.2017
//
#include <system/op_boilerplate.h>
2019-06-06 14:21:15 +02:00
#if NOT_EXCLUDED(OP_lstmCell)
#include <ops/declarable/CustomOperations.h>
#include<ops/declarable/helpers/lstm.h>
namespace sd {
2019-06-06 14:21:15 +02:00
namespace ops {
//////////////////////////////////////////////////////////////////////////
CUSTOM_OP_IMPL(lstmCell, 8, 2, false, 3, 2) {
auto xt = INPUT_VARIABLE(0); // input [bS x inSize]
auto ht_1 = INPUT_VARIABLE(1); // previous cell output [bS x numProj], that is at previous time step t-1, in case of projection=false -> numProj=numUnits!!!
auto ct_1 = INPUT_VARIABLE(2); // previous cell state [bS x numUnits], that is at previous time step t-1
auto Wx = INPUT_VARIABLE(3); // input-to-hidden weights, [inSize x 4*numUnits]
auto Wh = INPUT_VARIABLE(4); // hidden-to-hidden weights, [numProj x 4*numUnits]
auto Wc = INPUT_VARIABLE(5); // diagonal weights for peephole connections [3*numUnits]
auto Wp = INPUT_VARIABLE(6); // projection weights [numUnits x numProj]
auto b = INPUT_VARIABLE(7); // biases, [4*numUnits]
profiling of stack and unstack ops (#261) * - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
2020-03-03 05:32:37 +01:00
2019-06-06 14:21:15 +02:00
auto ht = OUTPUT_VARIABLE(0); // current cell output [bS x numProj], that is at current time step t
auto ct = OUTPUT_VARIABLE(1); // current cell state [bS x numUnits], that is at current time step t
profiling of stack and unstack ops (#261) * - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
2020-03-03 05:32:37 +01:00
2019-06-06 14:21:15 +02:00
const int peephole = INT_ARG(0); // if 1, provide peephole connections
const int projection = INT_ARG(1); // if 1, then projection is performed, if false then numProj==numUnits is mandatory!!!!
// FIXME: double?
const double clippingCellValue = T_ARG(0); // clipping value for ct, if it is not equal to zero, then cell state is clipped
const double clippingProjValue = T_ARG(1); // clipping value for projected ht, if it is not equal to zero, then projected cell output is clipped
const double forgetBias = T_ARG(2);
profiling of stack and unstack ops (#261) * - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
2020-03-03 05:32:37 +01:00
const int rank = xt->rankOf();
2019-06-06 14:21:15 +02:00
const int bS = xt->sizeAt(0);
const int inSize = xt->sizeAt(1);
const int numProj = ht_1->sizeAt(1);
profiling of stack and unstack ops (#261) * - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
2020-03-03 05:32:37 +01:00
const int numUnits = ct_1->sizeAt(1);
2019-06-06 14:21:15 +02:00
// input shapes validation
profiling of stack and unstack ops (#261) * - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
2020-03-03 05:32:37 +01:00
const std::vector<Nd4jLong> correctHt_1Shape = {bS, numProj};
const std::vector<Nd4jLong> correctCt_1Shape = {bS, numUnits};
const std::vector<Nd4jLong> correctWxShape = {inSize, 4*numUnits};
const std::vector<Nd4jLong> correctWhShape = {numProj, 4*numUnits};
const std::vector<Nd4jLong> correctWcShape = {3*numUnits};
const std::vector<Nd4jLong> correctWpShape = {numUnits, numProj};
const std::vector<Nd4jLong> correctBShape = {4*numUnits};
REQUIRE_TRUE(ht_1->isSameShape(correctHt_1Shape), 0, "LSTMCELL operation: wrong shape of initial cell output, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(correctHt_1Shape).c_str(), ShapeUtils::shapeAsString(ht_1).c_str());
REQUIRE_TRUE(ct_1->isSameShape(correctCt_1Shape), 0, "LSTMCELL operation: wrong shape of initial cell state, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(correctCt_1Shape).c_str(), ShapeUtils::shapeAsString(ct_1).c_str());
REQUIRE_TRUE(Wx->isSameShape(correctWxShape), 0, "LSTMCELL operation: wrong shape of input-to-hidden weights, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(correctWxShape).c_str(), ShapeUtils::shapeAsString(Wx).c_str());
REQUIRE_TRUE(Wh->isSameShape(correctWhShape), 0, "LSTMCELL operation: wrong shape of hidden-to-hidden weights, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(correctWhShape).c_str(), ShapeUtils::shapeAsString(Wh).c_str());
REQUIRE_TRUE(Wc->isSameShape(correctWcShape), 0, "LSTMCELL operation: wrong shape of diagonal weights for peephole connections, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(correctWcShape).c_str(), ShapeUtils::shapeAsString(Wc).c_str());
REQUIRE_TRUE(Wp->isSameShape(correctWpShape), 0, "LSTMCELL operation: wrong shape of projection weights, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(correctWpShape).c_str(), ShapeUtils::shapeAsString(Wp).c_str());
REQUIRE_TRUE(b->isSameShape(correctBShape), 0, "LSTMCELL operation: wrong shape of biases, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(correctBShape).c_str(), ShapeUtils::shapeAsString(b).c_str());
2019-06-06 14:21:15 +02:00
REQUIRE_TRUE(!(!projection && numUnits != numProj), 0, "LSTMCELL operation: projection option is switched of, and in this case output dimensionality for the projection matrices (numProj) must be equal to number of units in lstmCell !");
profiling of stack and unstack ops (#261) * - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
2020-03-03 05:32:37 +01:00
// calculations
2019-06-06 14:21:15 +02:00
helpers::lstmCell(block.launchContext(), xt,ht_1,ct_1, Wx,Wh,Wc,Wp, b, ht,ct, {(double)peephole, (double)projection, clippingCellValue, clippingProjValue, forgetBias});
profiling of stack and unstack ops (#261) * - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
2020-03-03 05:32:37 +01:00
2019-06-06 14:21:15 +02:00
return Status::OK();
}
DECLARE_TYPES(lstmCell) {
getOpDescriptor()
->setAllowedInputTypes(sd::DataType::ANY)
2019-06-06 14:21:15 +02:00
->setAllowedOutputTypes({ALL_FLOATS});
}
profiling of stack and unstack ops (#261) * - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
2020-03-03 05:32:37 +01:00
DECLARE_SHAPE_FN(lstmCell) {
2019-06-06 14:21:15 +02:00
auto xtShapeInfo = inputShape->at(0); // input [bS x inSize]
profiling of stack and unstack ops (#261) * - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
2020-03-03 05:32:37 +01:00
auto ht_1ShapeInfo = inputShape->at(1); // previous cell output [bS x numProj], that is at previous time step t-1, in case of projection=false -> numProj=numUnits!!!
auto ct_1ShapeInfo = inputShape->at(2); // previous cell state [bS x numUnits], that is at previous time step t-1
auto WxShapeInfo = inputShape->at(3); // input-to-hidden weights, [inSize x 4*numUnits]
auto WhShapeInfo = inputShape->at(4); // hidden-to-hidden weights, [numProj x 4*numUnits]
auto WcShapeInfo = inputShape->at(5); // diagonal weights for peephole connections [3*numUnits]
auto WpShapeInfo = inputShape->at(6); // projection weights [numUnits x numProj]
auto bShapeInfo = inputShape->at(7); // biases, [4*numUnits]
2019-06-06 14:21:15 +02:00
const int rank = shape::rank(xtShapeInfo);
const auto bS = xtShapeInfo[1];
const auto inSize = xtShapeInfo[2];
const auto numProj = ht_1ShapeInfo[2];
const auto numUnits = ct_1ShapeInfo[2];
profiling of stack and unstack ops (#261) * - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
2020-03-03 05:32:37 +01:00
2019-06-06 14:21:15 +02:00
// input shapes validation
profiling of stack and unstack ops (#261) * - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
2020-03-03 05:32:37 +01:00
const std::vector<Nd4jLong> correctHt_1Shape = {bS, numProj};
const std::vector<Nd4jLong> correctCt_1Shape = {bS, numUnits};
const std::vector<Nd4jLong> correctWxShape = {inSize, 4*numUnits};
const std::vector<Nd4jLong> correctWhShape = {numProj, 4*numUnits};
const std::vector<Nd4jLong> correctWcShape = {3*numUnits};
const std::vector<Nd4jLong> correctWpShape = {numUnits, numProj};
const std::vector<Nd4jLong> correctBShape = {4*numUnits};
REQUIRE_TRUE(ShapeUtils::areShapesEqual(ht_1ShapeInfo, correctHt_1Shape), 0, "LSTMCELL operation: wrong shape of initial cell output, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(correctHt_1Shape).c_str(), ShapeUtils::shapeAsString(ht_1ShapeInfo).c_str());
REQUIRE_TRUE(ShapeUtils::areShapesEqual(ct_1ShapeInfo, correctCt_1Shape), 0, "LSTMCELL operation: wrong shape of initial cell state, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(correctCt_1Shape).c_str(), ShapeUtils::shapeAsString(ct_1ShapeInfo).c_str());
REQUIRE_TRUE(ShapeUtils::areShapesEqual(WxShapeInfo, correctWxShape), 0, "LSTMCELL operation: wrong shape of input-to-hidden weights, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(correctWxShape).c_str(), ShapeUtils::shapeAsString(WxShapeInfo).c_str());
REQUIRE_TRUE(ShapeUtils::areShapesEqual(WhShapeInfo, correctWhShape), 0, "LSTMCELL operation: wrong shape of hidden-to-hidden weights, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(correctWhShape).c_str(), ShapeUtils::shapeAsString(WhShapeInfo).c_str());
REQUIRE_TRUE(ShapeUtils::areShapesEqual(WcShapeInfo, correctWcShape), 0, "LSTMCELL operation: wrong shape of diagonal weights for peephole connections, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(correctWcShape).c_str(), ShapeUtils::shapeAsString(WcShapeInfo).c_str());
REQUIRE_TRUE(ShapeUtils::areShapesEqual(WpShapeInfo, correctWpShape), 0, "LSTMCELL operation: wrong shape of projection weights, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(correctWpShape).c_str(), ShapeUtils::shapeAsString(WpShapeInfo).c_str());
REQUIRE_TRUE(ShapeUtils::areShapesEqual(bShapeInfo, correctBShape), 0, "LSTMCELL operation: wrong shape of biases, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(correctBShape).c_str(), ShapeUtils::shapeAsString(bShapeInfo).c_str());
2019-06-06 14:21:15 +02:00
// evaluate output shapeInfos
Nd4jLong *hShapeInfo(nullptr), *cShapeInfo(nullptr);
ALLOCATE(hShapeInfo, block.getWorkspace(), shape::shapeInfoLength(rank), Nd4jLong); // [bS x numProj]
ALLOCATE(cShapeInfo, block.getWorkspace(), shape::shapeInfoLength(rank), Nd4jLong); // [bS x numUnits]
profiling of stack and unstack ops (#261) * - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
2020-03-03 05:32:37 +01:00
2019-06-06 14:21:15 +02:00
hShapeInfo[0] = cShapeInfo[0] = rank;
hShapeInfo[1] = cShapeInfo[1] = bS;
hShapeInfo[2] = numProj;
cShapeInfo[2] = numUnits;
ShapeUtils::updateStridesAndType(hShapeInfo, xtShapeInfo, shape::order(ht_1ShapeInfo));
ShapeUtils::updateStridesAndType(cShapeInfo, xtShapeInfo, shape::order(ct_1ShapeInfo));
auto result = SHAPELIST(ConstantShapeHelper::getInstance().createShapeInfo(hShapeInfo), ConstantShapeHelper::getInstance().createShapeInfo(cShapeInfo));
2019-06-06 14:21:15 +02:00
RELEASE(hShapeInfo, block.workspace());
RELEASE(cShapeInfo, block.workspace());
return result;
profiling of stack and unstack ops (#261) * - profiling of stack and unstack ops Signed-off-by: Yurii <iuriish@yahoo.com> * - fix bug in cpu concat op Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of cuda stack and unstack Signed-off-by: Yurii <iuriish@yahoo.com> * - change shape.h method which operates with unity dimensions strides Signed-off-by: Yurii <iuriish@yahoo.com> * - rearrange stack tests Signed-off-by: Yurii <iuriish@yahoo.com> * - correct evaluation of smallest stride for moving through contiguous axis Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to update signature of function strideOverContigAxis in cuda concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - remove ShapeUtils::shapeAsString method applied before input arrays validations Signed-off-by: Yurii <iuriish@yahoo.com> * - further removing of ShapeUtils::shapeAsString Signed-off-by: Yurii <iuriish@yahoo.com> * - take sub-array shapeIndo/offset calculation out of NDArray class - add possibility of contiguous memory copy in execTransformAny op if opNum == assign Signed-off-by: Yurii <iuriish@yahoo.com> * - correct test_empty_scatter_2 in EmptyTests.cpp Signed-off-by: Yurii <iuriish@yahoo.com> * - profiling of slice op Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of contiguous memcpy for some cases in concat and split ops Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to declare oid nd4j::SpecialMethods<T>::splitCpuGeneric Signed-off-by: Yurii <iuriish@yahoo.com> * - correct typo in calculation of threads in cuda split op Signed-off-by: Yurii <iuriish@yahoo.com> * - forgot to correct another set of threads variables in split cuda ops Signed-off-by: Yurii <iuriish@yahoo.com> * - further conflicts resolving Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
2020-03-03 05:32:37 +01:00
}
2019-06-06 14:21:15 +02:00
}
}
#endif