cavis/libnd4j/include/ops/declarable/generic/broadcastable/floormod.cpp

106 lines
3.6 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 raver119@gmail.com
// modified by sgazeos@gmail.com with backprop implementation.
//
#include <system/op_boilerplate.h>
2019-06-06 14:21:15 +02:00
#if NOT_EXCLUDED(OP_floormod)
#include <ops/declarable/generic/helpers/BroadcastHelper.h>
#include <ops/declarable/CustomOperations.h>
namespace sd {
2019-06-06 14:21:15 +02:00
namespace ops {
BROADCASTABLE_OP_IMPL(floormod, 0, 0) {
auto x = INPUT_VARIABLE(0);
auto y = INPUT_VARIABLE(1);
auto z = OUTPUT_VARIABLE(0);
BROADCAST_CHECK_EMPTY(x,y,z);
REQUIRE_TRUE(!y->isB(), 0, "FLOORMOD OP: you can't divide by bool array!");
auto tZ = BroadcastHelper::broadcastApply(BROADCAST(FloorMod), x, y, z);
if (tZ == nullptr)
return ND4J_STATUS_KERNEL_FAILURE;
else if (tZ != z) {
OVERWRITE_RESULT(tZ);
}
return Status::OK();
}
DECLARE_TYPES(floormod) {
getOpDescriptor()
->setAllowedInputTypes(0, DataType::ANY)
->setAllowedInputTypes(1, DataType::ANY)
->setAllowedOutputTypes(0, DataType::INHERIT);
}
DECLARE_TYPES(floormod_bp) {
getOpDescriptor()
->setAllowedInputTypes(DataType::ANY)
->setAllowedOutputTypes({ALL_FLOATS});
}
CUSTOM_OP_IMPL(floormod_bp, 3, 2, false, 0, 0) {
auto x = INPUT_VARIABLE(0);
auto y = INPUT_VARIABLE(1);
auto epsNext = INPUT_VARIABLE(2);
auto gradX = OUTPUT_VARIABLE(0);
auto gradY = OUTPUT_VARIABLE(1);
gradX->assign(epsNext);
sd::ops::floormod op;
auto tmpResult(op.evaluate({x, y}));
2019-06-06 14:21:15 +02:00
if (gradY->rankOf() == gradX->rankOf())
epsNext->applyPairwiseTransform(pairwise::Multiply, *tmpResult.at(0), *gradY);
2019-06-06 14:21:15 +02:00
else // epsNext is greater than gradY
{
std::vector<Nd4jLong> dims(epsNext->rankOf() * 2);
Nd4jLong gap = epsNext->rankOf() - gradY->rankOf();
for (Nd4jLong d = 0; d < gap; d++) {
dims[d * 2 + 1] = 1;
}
auto tempIn((*tmpResult.at(0))(dims));
Shyrma temp (#131) * - specifying template instantiation for certain types in float16 and bloat16 Signed-off-by: Yurii <iuriish@yahoo.com> * - polishing bfloat16 and float16 member functions template specialization Signed-off-by: Yurii <iuriish@yahoo.com> * - rewrite and overload array +-*/ scalar and scalar +-*/ arr in NDAray class Signed-off-by: Yurii <iuriish@yahoo.com> * - make corrections which have to do with and rvalue lvalue conversions Signed-off-by: Yurii <iuriish@yahoo.com> * - provide move semantic in NDArray operators array +-/* array Signed-off-by: Yurii <iuriish@yahoo.com> * float16/bfloat16 tweaks Signed-off-by: raver119 <raver119@gmail.com> * one more tweak Signed-off-by: raver119 <raver119@gmail.com> * - make float16 and bfloat16 to compile successfully on cuda Signed-off-by: Yurii <iuriish@yahoo.com> * - do not use resources of view-like arrays when move semantics is applied Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of pointers in signatures NDArray methods 1 Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of signature of NDArray::dup method Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of signature of NDArray::reduceAlongDimension method Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyIndexReduce and applyTrueBroadcast methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyReduce3 and varianceAlongDimension methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::tensorsAlongDimension and diagonal methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::allTensorsAlongDimension Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::reduceAlongDimension 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyTransform 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyPairwiseTransform 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyBroadcast 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyTrueBroadcast 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyScalar and applyScalarArr Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::lambda methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::reduce3 methods 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of following NDArray methods: add/sub/mul/div row/column and fillAsTriangular Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::tileToShape methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::isShapeSameStrict method Signed-off-by: Yurii <iuriish@yahoo.com> * minor corrections in tests Signed-off-by: Yurii <iuriish@yahoo.com> * - replace reduce op in batchnorm mkldnn Signed-off-by: Yurii <iuriish@yahoo.com> * - add explicit templates instantiations for operator+(NDArray&&. const scalar) Signed-off-by: Yurii <iuriish@yahoo.com> * - corrections of casts in float16/bfloat16 Signed-off-by: Yurii <iuriish@yahoo.com> * - provide move semantics in following NDArray methods: transform, applyTrueBroadcast, transpose, reshape, permute Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of input array A duplicate in svd cuda op Signed-off-by: Yurii <iuriish@yahoo.com> * - avoid available bug in svd cuda API Signed-off-by: Yurii <iuriish@yahoo.com> * - add temporary global memory buffer in svd cuda when calcUV = false and m != n Signed-off-by: Yurii <iuriish@yahoo.com> * - remove test with blfoat16 type for betainC Signed-off-by: Yurii <iuriish@yahoo.com> * - resolve conflicts after master has been merged in Signed-off-by: Yurii <iuriish@yahoo.com> * - changed type of affected input array in fused_batch_norm Signed-off-by: Yurii <iuriish@yahoo.com> * - add several explicit type castings Signed-off-by: Yurii <iuriish@yahoo.com> * - add ND4J_EXPORT to operators Signed-off-by: Yurii <iuriish@yahoo.com> * - add explicit template types in instantiations of template arithm operators of NDArray class Signed-off-by: Yurii <iuriish@yahoo.com> * - one more test fix Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com>
2019-12-20 20:35:39 +01:00
(*epsNext)(dims).applyPairwiseTransform(pairwise::Multiply, tempIn, *gradY);
2019-06-06 14:21:15 +02:00
}
return Status::OK();
}
DECLARE_SHAPE_FN(floormod_bp) {
auto x = inputShape->at(0);
auto y = inputShape->at(1);
auto e = inputShape->at(2);
// eps always has shape of x
// grad always has shape of y
Nd4jLong *shapeE;
Nd4jLong *shapeG;
COPY_SHAPE(x, shapeE);
COPY_SHAPE(y, shapeG);
return SHAPELIST(CONSTANT(shapeE), CONSTANT(shapeG));
}
}
}
#endif