shugeo 330a69d4e2
Shugeo solve ls (#203)
* lstsq op. Initial commit.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Least squares linear problem solve op (lstsq). Cpu draft implementation.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed shape routine and tests.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added test for lstsq op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Rectification for lstsq op implementation.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Corrected test to avoid numerical inconsistensy.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added prints for check computing.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Corrected tests to use evalueate facility instead.

Signed-off-by: shugeo <sgazeos@gmail.com>

* CPU implementation of MatrixSolveLs op and tests.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added cuda implementation for helpers with lstsq op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored tests for lstsq op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added processing for empty inputs.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Merged tests.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored lstsq op for fast case.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed test.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored lstsq op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed some issues with solve.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed lstsq op to avoid erros.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added kernel for giagonal factor

Signed-off-by: shugeo <sgazeos@gmail.com>

* lstsq wrapper and triangular_solve fixed

* Added proper processing empty inputs and test.

Signed-off-by: shugeo <sgazeos@gmail.com>

* SequenceMask test

* Build fixed

* Added proper processing of empty inputs with solve op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Mapping added

* Added check of input shapes with solve op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added a couple of tests for lstsq op and minor changes with cuda helper for one.'

Signed-off-by: shugeo <sgazeos@gmail.com>

* Tests on

* Refactored test for lstsq op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed test

* Added another approach for lstsq op aka solve_ls.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Finished cpu part for solve_ls op helpers.

* Added helper for low triangular matrix inversion.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored alternate solve_ls cpu implementation.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Removed alternate approach for solve_ls op. Added multithreading with matrix inversion.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Assert fixed

* Refactored multithreading for inverse matricies.

Signed-off-by: shugeo <sgazeos@gmail.com>

Co-authored-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>
2020-02-28 11:37:26 +03:00

78 lines
3.1 KiB
C++

/*******************************************************************************
* Copyright (c) 2020 Konduit, K.K.
*
* 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
******************************************************************************/
//
// Created by GS <sgazeos@gmail.com> at 01/22/2020
//
#include <op_boilerplate.h>
#if NOT_EXCLUDED(OP_solve)
#include <ops/declarable/CustomOperations.h>
#include <ops/declarable/helpers/solve.h>
namespace nd4j {
namespace ops {
CUSTOM_OP_IMPL(solve, 2, 1, false, 0, 0) {
auto a = INPUT_VARIABLE(0);
auto b = INPUT_VARIABLE(1);
auto z = OUTPUT_VARIABLE(0);
bool useAdjoint = false;
if (block.numB() > 0) {
useAdjoint = B_ARG(0);
}
REQUIRE_TRUE(shape::shapeEquals(a->rankOf() - 2, a->shapeInfo(), b->rankOf() - 2, b->shapeInfo()), 0, "solve: Input shapes should be alike.");
REQUIRE_TRUE(a->rankOf() >=2, 0, "solve: The rank of input left tensor should not be less than 2, but %i is given", a->rankOf());
REQUIRE_TRUE(b->rankOf() >=2, 0, "solve: The rank of input right tensor should not be less than 2, but %i is given", b->rankOf());
REQUIRE_TRUE(a->sizeAt(-1) == a->sizeAt(-2), 0, "solve: The last two dimmensions should be equal, but %i and %i are given", a->sizeAt(-1), a->sizeAt(-2));
REQUIRE_TRUE(a->sizeAt(-1) == b->sizeAt(-2), 0, "solve: The last dimmension of left part should be equal to prelast of right part, but %i and %i are given", a->sizeAt(-1), b->sizeAt(-2));
if (a->isEmpty() || b->isEmpty() || z->isEmpty())
return Status::OK();
auto input = a;
if (useAdjoint) {
auto adjointA = a->ulike();
helpers::adjointMatrix(block.launchContext(), a, &adjointA);
input = new NDArray(adjointA); //.detach();
};
auto res = helpers::solveFunctor(block.launchContext(), input, b, useAdjoint, z);
if (input != a)
delete input;
return Status::OK();
}
DECLARE_SHAPE_FN(solve) {
auto in0 = inputShape->at(1);
auto in1 = inputShape->at(1);
auto luShape = ShapeBuilders::copyShapeInfoAndType(in1, in0, true, block.workspace());
return SHAPELIST(CONSTANT(luShape));
}
DECLARE_TYPES(solve) {
getOpDescriptor()
->setAllowedInputTypes({ALL_FLOATS})
->setAllowedOutputTypes({ALL_FLOATS})
->setSameMode(false);
}
}
}
#endif