763a225c6a
* initial commit Signed-off-by: raver119 <raver119@gmail.com> * - gruCell_bp further Signed-off-by: Yurii <yurii@skymind.io> * - further work on gruCell_bp Signed-off-by: Yurii <yurii@skymind.io> * Inverse matrix cublas implementation. Partial working revision. * Separation of segment ops helpers. Max separation. * Separated segment_min ops. * Separation of segment_mean/sum/prod/sqrtN ops heleprs. * Fixed diagonal processing with LUP decomposition. * Modified inversion approach using current state of LU decomposition. * Implementation of matrix_inverse op with cuda kernels. Working revision. * Implemented sequence_mask cuda helper. Eliminated waste printf with matrix_inverse implementation. Added proper tests. * - further work on gruCell_bp (ff/cuda) Signed-off-by: Yurii <yurii@skymind.io> * comment one test for gruCell_bp Signed-off-by: Yurii <yurii@skymind.io> * - provide cuda static_rnn Signed-off-by: Yurii <yurii@skymind.io> * Refactored random_shuffle op to use new random generator. * Refactored random_shuffle op helper. * Fixed debug tests with random ops tests. * Implement random_shuffle op cuda kernel helper and tests. * - provide cuda scatter_update Signed-off-by: Yurii <yurii@skymind.io> * Implementation of random_shuffle for linear case with cuda kernels and tests. * Implemented random_shuffle with cuda kernels. Final revision. * - finally gruCell_bp is completed Signed-off-by: Yurii <yurii@skymind.io> * Dropout op cuda helper implementation. * Implemented dropout_bp cuda helper. * Implemented alpha_dropout_bp with cuda kernel helpers. * Refactored helper. * Implementation of suppresion helper with cuda kernels. * - provide cpu code fot hsvToRgb, rgbToHsv, adjustHue Signed-off-by: Yurii <yurii@skymind.io> * Using sort by value method. * Implementation of image.non_max_suppression op cuda-based helper. * - correcting and testing adjust_hue, adjust_saturation cpu/cuda code Signed-off-by: Yurii <yurii@skymind.io> * Added cuda device prefixes to declarations. * Implementation of hashcode op with cuda helper. Initital revision. * rnn cu impl removed Signed-off-by: raver119 <raver119@gmail.com>
92 lines
3.7 KiB
C++
92 lines
3.7 KiB
C++
/*******************************************************************************
|
|
* 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 Created by raver119 on 24.11.17.
|
|
// @author Yurii Shyrma (iuriish@yahoo.com)
|
|
//
|
|
|
|
#include <op_boilerplate.h>
|
|
#if NOT_EXCLUDED(OP_scatter_add)
|
|
|
|
#include <ops/declarable/CustomOperations.h>
|
|
#include <ops/declarable/generic/helpers/ScatterHelper.h>
|
|
|
|
namespace nd4j {
|
|
namespace ops {
|
|
|
|
OP_IMPL(scatter_add, 3, 1, true) {
|
|
auto input = INPUT_VARIABLE(0);
|
|
auto indices = INPUT_VARIABLE(1);
|
|
auto updates = INPUT_VARIABLE(2);
|
|
|
|
auto output = OUTPUT_VARIABLE(0);
|
|
|
|
const bool lock = block.getBArguments()->empty() ? false : B_ARG(0);
|
|
|
|
const int inRank = input->rankOf();
|
|
const int indRank = indices->rankOf();
|
|
const int updRank = updates->rankOf();
|
|
const Nd4jLong indLen = indices->lengthOf();
|
|
|
|
REQUIRE_TRUE(inRank > 0, 0, "SCATTER_ADD OP: input should not be scalar !");
|
|
|
|
if(inRank == 1) {
|
|
REQUIRE_TRUE(indices->isSameShape(updates), 0, "SCATTER_ADD OP: when input array has rank = 1 then indices and updates must have the same shapes, but got %s and %s correspondingly !", ShapeUtils::shapeAsString(indices).c_str(), ShapeUtils::shapeAsString(updates).c_str());
|
|
}
|
|
else if (inRank == updRank && indices->isVector()) {
|
|
|
|
std::vector<Nd4jLong> updShape = updates->getShapeAsVector();
|
|
std::vector<Nd4jLong> inShape = input->getShapeAsVector();
|
|
std::vector<Nd4jLong> expectedUpdShape = {indices->lengthOf()};
|
|
expectedUpdShape.insert(expectedUpdShape.end(), inShape.begin()+1, inShape.end());
|
|
|
|
REQUIRE_TRUE(expectedUpdShape == updShape, 0, "SCATTER_ADD OP: wrong shape of updates array, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(expectedUpdShape).c_str(), ShapeUtils::shapeAsString(updShape).c_str());
|
|
}
|
|
else {
|
|
|
|
REQUIRE_TRUE(updRank == indRank + inRank - 1, 0, "SCATTER_ADD OP: wrong rank of updates array, expected is %i, but got %i instead !", indRank + inRank - 1 , updRank);
|
|
|
|
std::vector<Nd4jLong> updShape = updates->getShapeAsVector();
|
|
std::vector<Nd4jLong> inShape = input->getShapeAsVector();
|
|
std::vector<Nd4jLong> expectedUpdShape = indices->getShapeAsVector();
|
|
expectedUpdShape.insert(expectedUpdShape.end(), inShape.begin() + Nd4jLong(1L), inShape.end());
|
|
|
|
REQUIRE_TRUE(expectedUpdShape == updShape, 0, "SCATTER_ADD OP: wrong shape of updates array, expected is %s, but got %s instead !", ShapeUtils::shapeAsString(expectedUpdShape).c_str(), ShapeUtils::shapeAsString(updShape).c_str());
|
|
}
|
|
|
|
if (!block.isInplace())
|
|
output->assign(input);
|
|
|
|
helpers::scatter(block.launchContext(), pairwise::Add, *indices, *updates, *output, lock);
|
|
|
|
return Status::OK();
|
|
}
|
|
|
|
DECLARE_SYN(ScatterAdd, scatter_add);
|
|
|
|
DECLARE_TYPES(scatter_add) {
|
|
getOpDescriptor()
|
|
->setAllowedInputTypes(0, {ALL_INTS, ALL_FLOATS})
|
|
->setAllowedInputTypes(1, {ALL_INTS})
|
|
->setAllowedInputTypes(2, {ALL_INTS, ALL_FLOATS})
|
|
->setAllowedOutputTypes({ALL_INTS, ALL_FLOATS});
|
|
}
|
|
|
|
}
|
|
}
|
|
|
|
#endif |