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
|
|
|
|
******************************************************************************/
|
|
|
|
|
|
|
|
//
|
|
|
|
// Created by raver119 on 16.10.2017.
|
|
|
|
//
|
|
|
|
|
|
|
|
#include "testlayers.h"
|
2020-03-02 10:49:41 +01:00
|
|
|
#include <array/NDArray.h>
|
|
|
|
#include <helpers/ShapeUtils.h>
|
|
|
|
#include <loops/reduce3.h>
|
2019-06-06 14:21:15 +02:00
|
|
|
#include <ops/declarable/LegacyTransformOp.h>
|
|
|
|
#include <ops/declarable/LegacyPairwiseTransformOp.h>
|
|
|
|
#include <ops/declarable/LegacyScalarOp.h>
|
|
|
|
#include <ops/declarable/LegacyReduceSameOp.h>
|
|
|
|
#include <ops/declarable/LegacyReduceFloatOp.h>
|
|
|
|
#include <ops/declarable/LegacyIndexReduceOp.h>
|
|
|
|
#include <ops/declarable/LegacyBroadcastOp.h>
|
|
|
|
#include <helpers/TAD.h>
|
|
|
|
#include <helpers/ConstantTadHelper.h>
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
using namespace sd;
|
|
|
|
using namespace sd::ops;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
class LegacyOpsTests : public testing::Test {
|
|
|
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, TransformTests_1) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
x.assign(1.0);
|
|
|
|
auto z = NDArrayFactory::create<float>('c', {5,5});
|
|
|
|
auto exp = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
exp.assign(-1.0);
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyTransformSameOp op(transform::Neg); // Neg
|
2019-06-06 14:21:15 +02:00
|
|
|
auto status = op.execute({&x}, {&z}, {}, {}, {});
|
|
|
|
ASSERT_EQ(status, ND4J_STATUS_OK);
|
|
|
|
//z.printIndexedBuffer("Output NEG");
|
|
|
|
ASSERT_TRUE(z.equalsTo(&exp));
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, TransformTests_2) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
x.assign(1.0);
|
|
|
|
|
|
|
|
auto exp = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
exp.assign(-1.0);
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyTransformSameOp op(transform::Neg); // Neg
|
2020-01-30 08:07:24 +01:00
|
|
|
auto result = op.evaluate({&x}, {}, {});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
ASSERT_EQ(1, result->size());
|
|
|
|
|
|
|
|
auto z = result->at(0);
|
|
|
|
|
|
|
|
ASSERT_TRUE(exp.equalsTo(z));
|
|
|
|
|
|
|
|
delete result;
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, Reciprocal_1) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
x.assign(2.0f);
|
|
|
|
|
|
|
|
auto ethalon = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
ethalon.assign(0.5f);
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyTransformSameOp op(transform::Reciprocal); // Reciprocal
|
2019-06-06 14:21:15 +02:00
|
|
|
Nd4jStatus status = op.execute({&x}, {&x}, {}, {}, {});
|
|
|
|
|
|
|
|
ASSERT_EQ(ND4J_STATUS_OK, status);
|
|
|
|
ASSERT_TRUE(ethalon.equalsTo(&x));
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, PWT_Tests_1) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
x.assign(2.0);
|
|
|
|
|
|
|
|
auto y = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
y.assign(3.0);
|
|
|
|
|
|
|
|
auto exp = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
exp.assign(6.0);
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyPairwiseTransformOp op(pairwise::Multiply); // Multiply
|
2019-06-06 14:21:15 +02:00
|
|
|
Nd4jStatus status = op.execute({&x, &y}, {&x}, {}, {}, {});
|
|
|
|
|
|
|
|
ASSERT_EQ(ND4J_STATUS_OK, status);
|
|
|
|
|
|
|
|
ASSERT_TRUE(exp.equalsTo(&x));
|
|
|
|
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, PWT_Tests_2) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
x.assign(2.0);
|
|
|
|
|
|
|
|
auto y = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
y.assign(3.0);
|
|
|
|
|
|
|
|
auto exp = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
exp.assign(6.0);
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyPairwiseTransformOp op(pairwise::Multiply); // Multiply
|
2020-01-30 08:07:24 +01:00
|
|
|
auto result = op.evaluate({&x, &y}, {}, {});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
auto z = result->at(0);
|
|
|
|
|
|
|
|
//z->printBuffer("Z");
|
|
|
|
ASSERT_TRUE(exp.equalsTo(z));
|
|
|
|
|
|
|
|
delete result;
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, Scalar_Test_1) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
x.assign(2.0);
|
|
|
|
|
|
|
|
auto exp = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
exp.assign(7.0);
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyScalarOp op(scalar::Add);
|
2019-06-06 14:21:15 +02:00
|
|
|
op.execute({&x}, {&x}, {5.0}, {}, {}); //
|
|
|
|
|
|
|
|
ASSERT_TRUE(exp.equalsTo(&x));
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, Scalar_Test_2) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
x.assign(2.0);
|
|
|
|
|
|
|
|
auto exp = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
exp.assign(7.0);
|
|
|
|
|
|
|
|
auto y = NDArrayFactory::create<float>(5.0f);
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyScalarOp op(scalar::Add, y);
|
2020-01-30 08:07:24 +01:00
|
|
|
auto result = op.evaluate({&x}, {}, {});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
auto z = result->at(0);
|
|
|
|
ASSERT_TRUE(exp.equalsTo(z));
|
|
|
|
|
|
|
|
delete result;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, ReduceTests_1) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
x.assign(1.0);
|
|
|
|
int opNum = reduce::Sum;
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyReduceSameOp op(opNum);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2020-01-30 08:07:24 +01:00
|
|
|
auto result = op.evaluate({&x}, {}, {});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
ASSERT_EQ(1, result->size());
|
|
|
|
|
|
|
|
auto z = result->at(0);
|
2019-08-02 19:01:03 +02:00
|
|
|
// z->printBuffer("ReduceTest1");
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(z->isScalar());
|
|
|
|
ASSERT_NEAR(x.sumNumber().e<float>(0), z->e<float>(0), 1e-5f);
|
|
|
|
|
|
|
|
delete result;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, ReduceTests_2) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
x.assign(1.0);
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyReduceSameOp op(reduce::Sum);
|
2019-06-06 14:21:15 +02:00
|
|
|
auto axis = NDArrayFactory::create<Nd4jLong>('c', {1}, {1});
|
2020-01-30 08:07:24 +01:00
|
|
|
auto result = op.evaluate({&x, &axis}, {}, {});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
ASSERT_EQ(1, result->size());
|
|
|
|
|
|
|
|
auto z = result->at(0);
|
|
|
|
|
|
|
|
auto exp = x.reduceAlongDimension(reduce::Sum, {1});
|
|
|
|
|
2019-12-20 20:35:39 +01:00
|
|
|
ASSERT_TRUE(exp.isSameShape(z));
|
|
|
|
ASSERT_TRUE(exp.equalsTo(z));
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
delete result;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, ReduceTests_3) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {3, 5});
|
|
|
|
x.linspace(1);
|
|
|
|
auto indices = NDArrayFactory::create<int>('c', {1,1}, {1});
|
|
|
|
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyReduceSameOp op(reduce::Sum);
|
2020-01-30 08:07:24 +01:00
|
|
|
auto result = op.evaluate({&x, &indices}, {}, {});
|
2019-06-06 14:21:15 +02:00
|
|
|
auto z = result->at(0);
|
2019-12-20 20:35:39 +01:00
|
|
|
auto exp = x.reduceAlongDimension(reduce::Sum,{1});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
ASSERT_EQ(ND4J_STATUS_OK, result->status());
|
|
|
|
|
|
|
|
ASSERT_TRUE(exp.isSameShape(z));
|
|
|
|
ASSERT_TRUE(exp.equalsTo(z));
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
delete result;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, ReduceTests_4) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {2, 3, 5});
|
|
|
|
x.linspace(1);
|
|
|
|
auto indices = NDArrayFactory::create<int>('c', {1, 1}, {1});
|
|
|
|
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyReduceSameOp op(reduce::Sum);
|
2020-01-30 08:07:24 +01:00
|
|
|
auto result = op.evaluate({&x, &indices}, {}, {}, {true});
|
2019-06-06 14:21:15 +02:00
|
|
|
auto z = result->at(0);
|
2019-12-20 20:35:39 +01:00
|
|
|
auto exp = x.reduceAlongDimension(reduce::Sum, {1}, true);
|
2019-08-02 19:01:03 +02:00
|
|
|
// indices.printShapeInfo("Indices shape");
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_EQ(ND4J_STATUS_OK, result->status());
|
2019-08-02 19:01:03 +02:00
|
|
|
// z->printIndexedBuffer("Output reduce 4");
|
|
|
|
// exp.printIndexedBuffer("Expected reduce 4");
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(exp.isSameShape(z));
|
|
|
|
ASSERT_TRUE(exp.equalsTo(z));
|
|
|
|
|
|
|
|
delete result;
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, ReduceTests_5) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
x.assign(1.0);
|
|
|
|
int opNum = reduce::Mean;
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyReduceFloatOp op(opNum);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2020-01-30 08:07:24 +01:00
|
|
|
auto result = op.evaluate({&x});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
ASSERT_EQ(1, result->size());
|
|
|
|
|
|
|
|
auto z = result->at(0);
|
2019-08-02 19:01:03 +02:00
|
|
|
// z->printBuffer("ReduceTest1");
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(z->isScalar());
|
|
|
|
ASSERT_NEAR(x.meanNumber().e<float>(0), z->e<float>(0), 1e-5f);
|
|
|
|
|
|
|
|
delete result;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, ReduceTests_6) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
x.assign(1.0);
|
|
|
|
auto axis = NDArrayFactory::create<int>('c', {1}, {1});
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyReduceFloatOp op(reduce::Mean);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2020-01-30 08:07:24 +01:00
|
|
|
auto result = op.evaluate({&x, &axis}, {}, {});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
ASSERT_EQ(1, result->size());
|
|
|
|
|
|
|
|
auto z = result->at(0);
|
|
|
|
|
|
|
|
auto exp = x.reduceAlongDimension(reduce::Mean, {1});
|
|
|
|
|
2019-12-20 20:35:39 +01:00
|
|
|
ASSERT_TRUE(exp.isSameShape(z));
|
|
|
|
ASSERT_TRUE(exp.equalsTo(z));
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
delete result;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, ReduceTests_7) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {3, 5});
|
|
|
|
x.linspace(1);
|
|
|
|
auto indices = NDArrayFactory::create<int>('c', {1,1}, {1});
|
|
|
|
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyReduceFloatOp op(reduce::Mean);
|
2020-01-30 08:07:24 +01:00
|
|
|
auto result = op.evaluate({&x, &indices}, {}, {});
|
2019-06-06 14:21:15 +02:00
|
|
|
auto z = result->at(0);
|
2019-12-20 20:35:39 +01:00
|
|
|
auto exp = x.reduceAlongDimension(reduce::Mean,{1});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
ASSERT_EQ(ND4J_STATUS_OK, result->status());
|
|
|
|
|
|
|
|
ASSERT_TRUE(exp.isSameShape(z));
|
|
|
|
ASSERT_TRUE(exp.equalsTo(z));
|
|
|
|
|
|
|
|
delete result;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, ReduceTests_8) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {2, 3, 5});
|
|
|
|
x.linspace(1);
|
|
|
|
auto indices = NDArrayFactory::create<int>('c', {1}, {1});
|
|
|
|
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyReduceFloatOp op(reduce::Mean);
|
2020-01-30 08:07:24 +01:00
|
|
|
auto result = op.evaluate({&x, &indices}, {}, {}, {true});
|
2019-06-06 14:21:15 +02:00
|
|
|
auto z = result->at(0);
|
2019-12-20 20:35:39 +01:00
|
|
|
auto exp = x.reduceAlongDimension(reduce::Mean, {1}, true);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
ASSERT_EQ(ND4J_STATUS_OK, result->status());
|
2019-08-02 19:01:03 +02:00
|
|
|
// z->printIndexedBuffer("Reduce8 output");
|
|
|
|
// z->printShapeInfo("Reduce8 shape");
|
|
|
|
// exp.printShapeInfo("Reduce8 expected shape");
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(exp.isSameShape(z));
|
|
|
|
ASSERT_TRUE(exp.equalsTo(z));
|
|
|
|
|
|
|
|
delete result;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, IndexReduceTests_1) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
x.linspace(1);
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyIndexReduceOp op(indexreduce::IndexMax);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2020-01-30 08:07:24 +01:00
|
|
|
auto result = op.evaluate({&x}, {}, {});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
ASSERT_EQ(1, result->size());
|
|
|
|
|
|
|
|
auto z = result->at(0);
|
|
|
|
|
|
|
|
ASSERT_TRUE(z->isScalar());
|
|
|
|
ASSERT_EQ(24, z->e<int>(0));
|
|
|
|
|
|
|
|
delete result;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, IndexReduceTests_2) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
auto indices = NDArrayFactory::create<int>('c', {1}, {1});
|
|
|
|
x.linspace(1);
|
|
|
|
auto exp = NDArrayFactory::create<Nd4jLong>({4,4,4,4,4});
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyIndexReduceOp op(indexreduce::IndexMax);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2020-01-30 08:07:24 +01:00
|
|
|
auto result = op.evaluate({&x, &indices}, {}, {});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
ASSERT_EQ(1, result->size());
|
|
|
|
|
|
|
|
auto z = result->at(0);
|
2019-08-02 19:01:03 +02:00
|
|
|
// z->printIndexedBuffer("Hello indexreduce2");
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(exp.equalsTo(z));
|
|
|
|
//ASSERT_EQ(4, z->e<int>(0));
|
|
|
|
//ASSERT_EQ(4, z->e<int>(1));
|
|
|
|
//ASSERT_EQ(4, z->e<int>(2));
|
|
|
|
//ASSERT_EQ(4, z->e<int>(3));
|
|
|
|
//ASSERT_EQ(4, z->e<int>(4));
|
|
|
|
|
|
|
|
delete result;
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, BroadcastingTests_1) {
|
|
|
|
auto x = NDArrayFactory::create<double>('c', {5, 5});
|
|
|
|
x.assign(0.0f);
|
|
|
|
|
|
|
|
auto row = NDArrayFactory::create<double>('c', {1, 5});
|
|
|
|
row.linspace(1);
|
|
|
|
auto axis = NDArrayFactory::create<int>('c', {1}, {1});
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::ops::LegacyBroadcastOp op(broadcast::Add);
|
2019-06-06 14:21:15 +02:00
|
|
|
Nd4jStatus status = op.execute({&x, &row, &axis}, {&x}, {}, {}, {});
|
|
|
|
|
|
|
|
ASSERT_EQ(ND4J_STATUS_OK, status);
|
|
|
|
|
|
|
|
auto list = x.allTensorsAlongDimension({1});
|
2019-08-02 19:01:03 +02:00
|
|
|
// x.printIndexedBuffer("Output broadcast");
|
|
|
|
// list->at(0)->printIndexedBuffer("Column 0:");
|
2019-12-20 20:35:39 +01:00
|
|
|
for (int e = 0; e < list.size(); e++)
|
|
|
|
ASSERT_TRUE(row.equalsTo(list.at(e)));
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, BroadcastingTests_2) {
|
|
|
|
auto x = NDArrayFactory::create<double>('c', {5}, {1, 1, 1, 1, 1});
|
|
|
|
auto y = NDArrayFactory::create<double>('c', {10, 5});
|
|
|
|
auto e = NDArrayFactory::create<double>('c', {10, 5});
|
|
|
|
y.assign(3.0);
|
|
|
|
e.assign(4.0);
|
|
|
|
|
|
|
|
int axis = 1;
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
// shape::printShapeInfoLinear("tad shape", tad.tadOnlyShapeInfo);
|
2020-03-02 10:49:41 +01:00
|
|
|
auto packY = sd::ConstantTadHelper::getInstance()->tadForDimensions(y.shapeInfo(), {axis});
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
NDArray::prepareSpecialUse({&y}, {&x});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
NativeOpExecutioner::execInverseBroadcast(LaunchContext::defaultContext(), broadcast::Add, x.buffer(), x.shapeInfo(), x.specialBuffer(), x.specialShapeInfo(), y.buffer(), y.shapeInfo(), y.specialBuffer(), y.specialShapeInfo(), y.buffer(), y.shapeInfo(), y.specialBuffer(), y.specialShapeInfo(), &axis, 1, packY.platformShapeInfo(), packY.platformOffsets(), packY.platformShapeInfo(), packY.platformOffsets());
|
|
|
|
|
|
|
|
NDArray::registerSpecialUse({&y}, {&x});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
ASSERT_EQ(e, y);
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, PowDerivative_1) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
auto exp = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
x.assign(3.f);
|
|
|
|
exp.assign(6.f);
|
|
|
|
|
|
|
|
float p = 2.0f;
|
|
|
|
|
2019-12-20 20:35:39 +01:00
|
|
|
x.applyScalar(scalar::PowDerivative, p, x);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
ASSERT_TRUE(exp.equalsTo(&x));
|
|
|
|
}
|
|
|
|
|
[WIP] multi-device support (#80)
* fix pad javadoc and @see links. (#72)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* [WIP] More fixes (#73)
* special tests for ConstantTadHelper/ConstantShapeHelper
Signed-off-by: raver119 <raver119@gmail.com>
* release methods for data buffers
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary buffer Java side
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary buffer Java side
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary TadPack C++/Java side (#74)
Signed-off-by: raver119 <raver119@gmail.com>
* Zoo model TF import test updates (#75)
* argLine fix, update compression_gru comment
* updated comment for xception
* undid but commented argLine change
* updated xlnet comment
* copyright headers
* - new NDArray methods like()/ulike() (#77)
- fix for depthwise_conv2d_bp + special test
Signed-off-by: raver119 <raver119@gmail.com>
* upsampling2d fix CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* DL4J trace logging (#79)
* MLN/CG trace logging for debugging
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Tiny tweak
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* strided_slice_bp shape fn leak fix
Signed-off-by: raver119 <raver119@gmail.com>
* SameDiff fixes and naming (#78)
* remove SDVariable inplace methods
* import methods
* npe fix in OpVal
* removed SameDiff inplace ops from tests
* Naming updates, moved to centralized methods in SameDiff, should use op_#:# for everything
* quick fixes
* javadoc
* SDVariable eval with placeholders
* use regex match
* better matching
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* fix javadoc. (#76)
* fix javadoc.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* replace most @see with @link s.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* 4 additional tests
Signed-off-by: raver119 <raver119@gmail.com>
* launch context reorganization
Signed-off-by: raver119 <raver119@gmail.com>
* LaunchContext reorganization
Signed-off-by: raver119 <raver119@gmail.com>
* per-device LaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* Various DL4J/ND4J fixes (#81)
* #7954 Force refresh of UI when switching tabs on overview page
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8017 Concurrent modification exception (synchronize) fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8033 Don't initialize updater in middle of writing memory crash dump
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8208 Fix shape checks for ND4J int[] creator methods
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #6385 #7992 Keras import naming fixes + cleanup
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8016 Upsampling3D - add NDHWC format support
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* Refactor NativeOps.h to export C functions
* Actually export functions from NativeOps.h
* Adapt the Java wrappers in ND4J generated with JavaCPP
* Create C wrappers for some of the C++ classes currently used by ND4J
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* remove duplicate code in createBufferDetached. (#83)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Keras model import - updater lr fix (#84)
* Keras model import - updater lr fix
Signed-off-by: eraly <susan.eraly@gmail.com>
* Keras model import - updater lr fix, cleanup
Signed-off-by: eraly <susan.eraly@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* Fix functions of OpaqueVariablesSet
* thread-local buffers/affinity
Signed-off-by: raver119 <raver119@gmail.com>
* thread safety for LaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* more of thread safety
Signed-off-by: raver119 <raver119@gmail.com>
* one more multi threaded test
Signed-off-by: raver119 <raver119@gmail.com>
* SameDiff Convolution Config validation, better output methods (#82)
* Conv Config validation & tests
Signed-off-by: Ryan Nett <rnett@skymind.io>
* stackOutputs utility method
Signed-off-by: Ryan Nett <rnett@skymind.io>
* use constructor for validation, support negative kernel sizes (infered from weights)
Signed-off-by: Ryan Nett <rnett@skymind.io>
* better output methods
Signed-off-by: Ryan Nett <rnett@skymind.io>
* move output to be with fit and evaluate
Signed-off-by: Ryan Nett <rnett@skymind.io>
* fixes
Signed-off-by: Ryan Nett <rnett@skymind.io>
* more fixes
Signed-off-by: Ryan Nett <rnett@skymind.io>
* refactor duplicate code from pad methods. (#86)
* refactor duplicate code from pad methods.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* replace switch with if.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Various ND4J/DL4J fixes and improvements (#87)
* Reshape and reallocate - small fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Reshape and reallocate - small fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #6488 ElementWiseVertex broadcast support
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Constructors and broadcast supported it Transforms.max/min
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8054 ElementWiseVertex now supports broadcast inputs
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8057 Nd4j.create overload dtype fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7551 ND4J Shape validation fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* [WIP] Numpy boolean import (#91)
* numpy bool type
Signed-off-by: raver119 <raver119@gmail.com>
* numpy bool java side
Signed-off-by: raver119 <raver119@gmail.com>
* remove create method with unused parameter. (#89)
* remove create method with unused parameter.
* removed more unused methods.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* removing more unused code.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* last removal of unused code.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* remove createSparse methods. (#92)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Various ND4J/DL4J fixes (#90)
* Deprecate Old*Op instances
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8063 #8054 Broadcast exceptions + cleanup inplace ops
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Small fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Remove bad test condition
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7993 Fix shape function issue in crop_and_resize op
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* DL4J SameDiff lambda layer fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8029 Fix for pnorm backprop math
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8038 Fix Op profiler NaN/Inf triggering + add tests (#93)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* createUninitializedDetached refactoring. (#94)
* wip
* update interface, add null implementations.
* Breaking one test in a weird way.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* createUninitializedDetached refactored.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* cuda build fix for issues introduced by recent refactoring
Signed-off-by: raver119 <raver119@gmail.com>
* [WIP] More of CUDA (#95)
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* Implementation of hashcode cuda helper. Working edition.
* Fixed parallel test input arangements.
* Fixed tests for hashcode op.
* Fixed shape calculation for image:crop_and_resize op and test.
* NativeOps tests. Initial test suite.
* Added tests for indexReduce methods.
* Added test on execBroadcast with NDArray as dimensions.
* Added test on execBroadcastBool with NDArray as dimensions.
* Added tests on execPairwiseTransform and execPairwiseTransofrmBool.
* Added tests for execReduce with scalar results.
* Added reduce tests for non-empty dims array.
* Added tests for reduce3.
* Added tests for execScalar.
* Added tests for execSummaryStats.
* - provide cpu/cuda code for batch_to_space
- testing it
Signed-off-by: Yurii <yurii@skymind.io>
* - remove old test for batch_to_space (had wrong format and numbers were not checked)
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed complilation errors with test.
* Added test for execTransformFloat.
* Added test for execTransformSame.
* Added test for execTransformBool.
* Added test for execTransformStrict.
* Added tests for execScalar/execScalarBool with TADs.
* Added test for flatten.
* - provide cpu/cuda code for space_to_Batch operaion
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for concat.
* comment unnecessary stuff in s_t_b
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for specialConcat.
* Added tests for memcpy/set routines.
* Fixed pullRow cuda test.
* Added pullRow test.
* Added average test.
* - correct typo in NDArray::applyPairwiseTransform(nd4j::pairwise::BoolOps op...)
Signed-off-by: Yurii <yurii@skymind.io>
* - debugging and fixing cuda tests in JavaInteropTests file
Signed-off-by: Yurii <yurii@skymind.io>
* - correct some tests
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for shuffle.
* Fixed ops declarations.
* Restored omp and added shuffle test.
* Added convertTypes test.
* Added tests for execRandom. Eliminated usage of RandomBuffer with NativeOps.
* Added sort tests.
* Added tests for execCustomOp.
* - further debuging and fixing tests terminated with crash
Signed-off-by: Yurii <yurii@skymind.io>
* Added tests for calculateOutputShapes.
* Addded Benchmarks test.
* Commented benchmark tests.
* change assertion
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for apply_sgd op. Added cpu helper for that op.
* Implement cuda helper for aplly_sgd op. Fixed tests for NativeOps.
* Added test for assign broadcastable.
* Added tests for assign_bp op.
* Added tests for axpy op.
* - assign/execScalar/execTransformAny signature change
- minor test fix
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed axpy op.
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* - fix tests for nativeOps::concat
Signed-off-by: Yurii <yurii@skymind.io>
* sequential transform/scalar
Signed-off-by: raver119 <raver119@gmail.com>
* allow nested parallelism
Signed-off-by: raver119 <raver119@gmail.com>
* assign_bp leak fix
Signed-off-by: raver119 <raver119@gmail.com>
* block setRNG fix
Signed-off-by: raver119 <raver119@gmail.com>
* enable parallelism by default
Signed-off-by: raver119 <raver119@gmail.com>
* enable nested parallelism by default
Signed-off-by: raver119 <raver119@gmail.com>
* Added cuda implementation for row_count helper.
* Added implementation for tnse gains op helper.
* - take into account possible situations when input arrays are empty in reduce_ cuda stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Implemented tsne/edge_forces op cuda-based helper. Parallelized cpu-based helper for edge_forces.
* Added kernel for tsne/symmetrized op heleper.
* Implementation of tsne/symmetrized op cuda helper. Working edition.
* Eliminated waste printfs.
* Added test for broadcastgradientargs op.
* host-only fallback for empty reduce float
Signed-off-by: raver119 <raver119@gmail.com>
* - some tests fixes
Signed-off-by: Yurii <yurii@skymind.io>
* - correct the rest of reduce_ stuff
Signed-off-by: Yurii <yurii@skymind.io>
* - further correction of reduce_ stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for Cbow op. Also added cuda implementation for cbow helpers.
* - improve code of stack operation for scalar case
Signed-off-by: Yurii <yurii@skymind.io>
* - provide cuda kernel for gatherND operation
Signed-off-by: Yurii <yurii@skymind.io>
* Implementation of cbow helpers with cuda kernels.
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* - further correction of cuda stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Implementatation of cbow op helper with cuda kernels. Working edition.
* Skip random testing for cudablas case.
* lstmBlockCell context fix
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for ELU and ELU_BP ops.
* Added tests for eq_scalar, gt_scalar, gte_scalar and lte_scalar ops.
* Added tests for neq_scalar.
* Added test for noop.
* - further work on clipbynorm_bp
Signed-off-by: Yurii <yurii@skymind.io>
* - get rid of concat op call, use instead direct concat helper call
Signed-off-by: Yurii <yurii@skymind.io>
* lstmBlockCell context fix
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for lrelu and lrelu_bp.
* Added tests for selu and selu_bp.
* Fixed lrelu derivative helpers.
* - some corrections in lstm
Signed-off-by: Yurii <yurii@skymind.io>
* operator * result shape fix
Signed-off-by: raver119 <raver119@gmail.com>
* - correct typo in lstmCell
Signed-off-by: Yurii <yurii@skymind.io>
* few tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* CUDA inverse broadcast bool fix
Signed-off-by: raver119 <raver119@gmail.com>
* disable MMAP test for CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* BooleanOp syncToDevice
Signed-off-by: raver119 <raver119@gmail.com>
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* additional data types for im2col/col2im
Signed-off-by: raver119 <raver119@gmail.com>
* Added test for firas_sparse op.
* one more RandomBuffer test excluded
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for flatten op.
* Added test for Floor op.
* bunch of tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* mmulDot tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Implemented floordiv_bp op and tests.
* Fixed scalar case with cuda implementation for bds.
* - work on cuda kernel for clip_by_norm backprop op is completed
Signed-off-by: Yurii <yurii@skymind.io>
* Eliminate cbow crach.
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Eliminated abortion with batched nlp test.
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed shared flag initializing.
* disabled bunch of cpu workspaces tests
Signed-off-by: raver119 <raver119@gmail.com>
* scalar operators fix: missing registerSpecialUse call
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed logdet for cuda and tests.
* - correct clipBynorm_bp
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed crop_and_resize shape datatype.
* - correct some mmul tests
Signed-off-by: Yurii <yurii@skymind.io>
* build fix
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI (#97)
Signed-off-by: raver119 <raver119@gmail.com>
* temporary stack fix
Signed-off-by: raver119 <raver119@gmail.com>
* round robin affinity test
Signed-off-by: raver119 <raver119@gmail.com>
* get rid of legacy CudaContext methods
Signed-off-by: raver119 <raver119@gmail.com>
* get rid of legacy ContextPool classes/methods
Signed-off-by: raver119 <raver119@gmail.com>
* one legacy test removed
Signed-off-by: raver119 <raver119@gmail.com>
* few more fields rearranged
Signed-off-by: raver119 <raver119@gmail.com>
* OpaqueLaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* OpaqueLaunchContext++
Signed-off-by: raver119 <raver119@gmail.com>
* more of OpaqueLaunchContext methods
Signed-off-by: raver119 <raver119@gmail.com>
* LaunchContext -> CudaContext
Signed-off-by: raver119 <raver119@gmail.com>
* AffinityManger changes
Signed-off-by: raver119 <raver119@gmail.com>
* AffinityManger changes
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver handles
Signed-off-by: raver119 <raver119@gmail.com>
* typo
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver method
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver handle propagated
Signed-off-by: raver119 <raver119@gmail.com>
* blas/solver handles
Signed-off-by: raver119 <raver119@gmail.com>
* one more test
Signed-off-by: raver119 <raver119@gmail.com>
* legacy concat implementations replaced with new CustomOp
Signed-off-by: raver119 <raver119@gmail.com>
* one more test
Signed-off-by: raver119 <raver119@gmail.com>
* concat now uses way more blocks
Signed-off-by: raver119 <raver119@gmail.com>
* print
Signed-off-by: raver119 <raver119@gmail.com>
* no more triple template mmul
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of kernels have dtypes reconsidered
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of kernels have dtypes reconsidered
Signed-off-by: raver119 <raver119@gmail.com>
* bitonic sort reorganized
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of cpu stuff removed from cuda scope
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of cpu stuff removed from cuda scope
Signed-off-by: raver119 <raver119@gmail.com>
* type conversions moved to generic impl
Signed-off-by: raver119 <raver119@gmail.com>
* cpu data types pass
Signed-off-by: raver119 <raver119@gmail.com>
* non_max_suppression
Signed-off-by: raver119 <raver119@gmail.com>
* sortByValue fix
Signed-off-by: raver119 <raver119@gmail.com>
* ignore all mixed datatype tests for mmul
Signed-off-by: raver119 <raver119@gmail.com>
* special handling of OpProfiler exceptions
Signed-off-by: raver119 <raver119@gmail.com>
* - one failing concat test in cpp
- Nd4j.tile now uses op internally
Signed-off-by: raver119 <raver119@gmail.com>
* get back dtype exception for legacy arrays deserialization
Signed-off-by: raver119 <raver119@gmail.com>
2019-08-14 15:52:34 +02:00
|
|
|
#ifndef __CUDABLAS__
|
2019-06-06 14:21:15 +02:00
|
|
|
TEST_F(LegacyOpsTests, reduce3_1) {
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
Nd4jLong yShape[2] = {4,4};
|
|
|
|
Nd4jLong xShape[1] = {4};
|
|
|
|
float y[16] ={1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16};
|
|
|
|
float x[4] = {1,2,3,4};
|
|
|
|
int dimension[1] = {1};
|
|
|
|
int dimensionLength = 1;
|
|
|
|
int opNum = 1;
|
|
|
|
float extraVals[1] = {0};
|
|
|
|
float result[4] = {0.0,0.0,0.0,0.0};
|
|
|
|
|
|
|
|
std::vector<int> dim = {1};
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
auto shapeBuffer = sd::ShapeBuilders::createShapeInfo(sd::DataType::FLOAT32, 'c', 2, yShape);
|
|
|
|
auto xShapeBuffer = sd::ShapeBuilders::createShapeInfo(sd::DataType::FLOAT32, 'c', 1, xShape);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
//int *tadShapeBuffer = shape::computeResultShape(shapeBuffer,dimension,dimensionLength);
|
2020-03-02 10:49:41 +01:00
|
|
|
auto tadShapeBuffer = sd::ShapeUtils::evalReduceShapeInfo('c', dim, shapeBuffer, false, true, nullptr);
|
2019-11-13 15:15:18 +01:00
|
|
|
functions::reduce3::Reduce3<float, float>::exec(opNum, x, xShapeBuffer, extraVals, y, shapeBuffer, result, tadShapeBuffer, dimension, dimensionLength, 0, 4);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
float distancesAssertion[4] = {0.0,8.0,16.0,24.0};
|
2019-08-02 19:01:03 +02:00
|
|
|
for(int i = 0; i < 4; i++)
|
2019-11-13 15:15:18 +01:00
|
|
|
ASSERT_NEAR(distancesAssertion[i],result[i], 1e-5);
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
delete[] shapeBuffer;
|
|
|
|
delete[] xShapeBuffer;
|
|
|
|
}
|
|
|
|
|
[WIP] multi-device support (#80)
* fix pad javadoc and @see links. (#72)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* [WIP] More fixes (#73)
* special tests for ConstantTadHelper/ConstantShapeHelper
Signed-off-by: raver119 <raver119@gmail.com>
* release methods for data buffers
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary buffer Java side
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary buffer Java side
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary TadPack C++/Java side (#74)
Signed-off-by: raver119 <raver119@gmail.com>
* Zoo model TF import test updates (#75)
* argLine fix, update compression_gru comment
* updated comment for xception
* undid but commented argLine change
* updated xlnet comment
* copyright headers
* - new NDArray methods like()/ulike() (#77)
- fix for depthwise_conv2d_bp + special test
Signed-off-by: raver119 <raver119@gmail.com>
* upsampling2d fix CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* DL4J trace logging (#79)
* MLN/CG trace logging for debugging
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Tiny tweak
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* strided_slice_bp shape fn leak fix
Signed-off-by: raver119 <raver119@gmail.com>
* SameDiff fixes and naming (#78)
* remove SDVariable inplace methods
* import methods
* npe fix in OpVal
* removed SameDiff inplace ops from tests
* Naming updates, moved to centralized methods in SameDiff, should use op_#:# for everything
* quick fixes
* javadoc
* SDVariable eval with placeholders
* use regex match
* better matching
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* fix javadoc. (#76)
* fix javadoc.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* replace most @see with @link s.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* 4 additional tests
Signed-off-by: raver119 <raver119@gmail.com>
* launch context reorganization
Signed-off-by: raver119 <raver119@gmail.com>
* LaunchContext reorganization
Signed-off-by: raver119 <raver119@gmail.com>
* per-device LaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* Various DL4J/ND4J fixes (#81)
* #7954 Force refresh of UI when switching tabs on overview page
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8017 Concurrent modification exception (synchronize) fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8033 Don't initialize updater in middle of writing memory crash dump
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8208 Fix shape checks for ND4J int[] creator methods
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #6385 #7992 Keras import naming fixes + cleanup
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8016 Upsampling3D - add NDHWC format support
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* Refactor NativeOps.h to export C functions
* Actually export functions from NativeOps.h
* Adapt the Java wrappers in ND4J generated with JavaCPP
* Create C wrappers for some of the C++ classes currently used by ND4J
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* remove duplicate code in createBufferDetached. (#83)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Keras model import - updater lr fix (#84)
* Keras model import - updater lr fix
Signed-off-by: eraly <susan.eraly@gmail.com>
* Keras model import - updater lr fix, cleanup
Signed-off-by: eraly <susan.eraly@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* Fix functions of OpaqueVariablesSet
* thread-local buffers/affinity
Signed-off-by: raver119 <raver119@gmail.com>
* thread safety for LaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* more of thread safety
Signed-off-by: raver119 <raver119@gmail.com>
* one more multi threaded test
Signed-off-by: raver119 <raver119@gmail.com>
* SameDiff Convolution Config validation, better output methods (#82)
* Conv Config validation & tests
Signed-off-by: Ryan Nett <rnett@skymind.io>
* stackOutputs utility method
Signed-off-by: Ryan Nett <rnett@skymind.io>
* use constructor for validation, support negative kernel sizes (infered from weights)
Signed-off-by: Ryan Nett <rnett@skymind.io>
* better output methods
Signed-off-by: Ryan Nett <rnett@skymind.io>
* move output to be with fit and evaluate
Signed-off-by: Ryan Nett <rnett@skymind.io>
* fixes
Signed-off-by: Ryan Nett <rnett@skymind.io>
* more fixes
Signed-off-by: Ryan Nett <rnett@skymind.io>
* refactor duplicate code from pad methods. (#86)
* refactor duplicate code from pad methods.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* replace switch with if.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Various ND4J/DL4J fixes and improvements (#87)
* Reshape and reallocate - small fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Reshape and reallocate - small fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #6488 ElementWiseVertex broadcast support
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Constructors and broadcast supported it Transforms.max/min
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8054 ElementWiseVertex now supports broadcast inputs
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8057 Nd4j.create overload dtype fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7551 ND4J Shape validation fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* [WIP] Numpy boolean import (#91)
* numpy bool type
Signed-off-by: raver119 <raver119@gmail.com>
* numpy bool java side
Signed-off-by: raver119 <raver119@gmail.com>
* remove create method with unused parameter. (#89)
* remove create method with unused parameter.
* removed more unused methods.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* removing more unused code.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* last removal of unused code.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* remove createSparse methods. (#92)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Various ND4J/DL4J fixes (#90)
* Deprecate Old*Op instances
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8063 #8054 Broadcast exceptions + cleanup inplace ops
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Small fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Remove bad test condition
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7993 Fix shape function issue in crop_and_resize op
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* DL4J SameDiff lambda layer fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8029 Fix for pnorm backprop math
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8038 Fix Op profiler NaN/Inf triggering + add tests (#93)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* createUninitializedDetached refactoring. (#94)
* wip
* update interface, add null implementations.
* Breaking one test in a weird way.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* createUninitializedDetached refactored.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* cuda build fix for issues introduced by recent refactoring
Signed-off-by: raver119 <raver119@gmail.com>
* [WIP] More of CUDA (#95)
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* Implementation of hashcode cuda helper. Working edition.
* Fixed parallel test input arangements.
* Fixed tests for hashcode op.
* Fixed shape calculation for image:crop_and_resize op and test.
* NativeOps tests. Initial test suite.
* Added tests for indexReduce methods.
* Added test on execBroadcast with NDArray as dimensions.
* Added test on execBroadcastBool with NDArray as dimensions.
* Added tests on execPairwiseTransform and execPairwiseTransofrmBool.
* Added tests for execReduce with scalar results.
* Added reduce tests for non-empty dims array.
* Added tests for reduce3.
* Added tests for execScalar.
* Added tests for execSummaryStats.
* - provide cpu/cuda code for batch_to_space
- testing it
Signed-off-by: Yurii <yurii@skymind.io>
* - remove old test for batch_to_space (had wrong format and numbers were not checked)
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed complilation errors with test.
* Added test for execTransformFloat.
* Added test for execTransformSame.
* Added test for execTransformBool.
* Added test for execTransformStrict.
* Added tests for execScalar/execScalarBool with TADs.
* Added test for flatten.
* - provide cpu/cuda code for space_to_Batch operaion
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for concat.
* comment unnecessary stuff in s_t_b
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for specialConcat.
* Added tests for memcpy/set routines.
* Fixed pullRow cuda test.
* Added pullRow test.
* Added average test.
* - correct typo in NDArray::applyPairwiseTransform(nd4j::pairwise::BoolOps op...)
Signed-off-by: Yurii <yurii@skymind.io>
* - debugging and fixing cuda tests in JavaInteropTests file
Signed-off-by: Yurii <yurii@skymind.io>
* - correct some tests
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for shuffle.
* Fixed ops declarations.
* Restored omp and added shuffle test.
* Added convertTypes test.
* Added tests for execRandom. Eliminated usage of RandomBuffer with NativeOps.
* Added sort tests.
* Added tests for execCustomOp.
* - further debuging and fixing tests terminated with crash
Signed-off-by: Yurii <yurii@skymind.io>
* Added tests for calculateOutputShapes.
* Addded Benchmarks test.
* Commented benchmark tests.
* change assertion
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for apply_sgd op. Added cpu helper for that op.
* Implement cuda helper for aplly_sgd op. Fixed tests for NativeOps.
* Added test for assign broadcastable.
* Added tests for assign_bp op.
* Added tests for axpy op.
* - assign/execScalar/execTransformAny signature change
- minor test fix
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed axpy op.
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* - fix tests for nativeOps::concat
Signed-off-by: Yurii <yurii@skymind.io>
* sequential transform/scalar
Signed-off-by: raver119 <raver119@gmail.com>
* allow nested parallelism
Signed-off-by: raver119 <raver119@gmail.com>
* assign_bp leak fix
Signed-off-by: raver119 <raver119@gmail.com>
* block setRNG fix
Signed-off-by: raver119 <raver119@gmail.com>
* enable parallelism by default
Signed-off-by: raver119 <raver119@gmail.com>
* enable nested parallelism by default
Signed-off-by: raver119 <raver119@gmail.com>
* Added cuda implementation for row_count helper.
* Added implementation for tnse gains op helper.
* - take into account possible situations when input arrays are empty in reduce_ cuda stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Implemented tsne/edge_forces op cuda-based helper. Parallelized cpu-based helper for edge_forces.
* Added kernel for tsne/symmetrized op heleper.
* Implementation of tsne/symmetrized op cuda helper. Working edition.
* Eliminated waste printfs.
* Added test for broadcastgradientargs op.
* host-only fallback for empty reduce float
Signed-off-by: raver119 <raver119@gmail.com>
* - some tests fixes
Signed-off-by: Yurii <yurii@skymind.io>
* - correct the rest of reduce_ stuff
Signed-off-by: Yurii <yurii@skymind.io>
* - further correction of reduce_ stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for Cbow op. Also added cuda implementation for cbow helpers.
* - improve code of stack operation for scalar case
Signed-off-by: Yurii <yurii@skymind.io>
* - provide cuda kernel for gatherND operation
Signed-off-by: Yurii <yurii@skymind.io>
* Implementation of cbow helpers with cuda kernels.
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* - further correction of cuda stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Implementatation of cbow op helper with cuda kernels. Working edition.
* Skip random testing for cudablas case.
* lstmBlockCell context fix
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for ELU and ELU_BP ops.
* Added tests for eq_scalar, gt_scalar, gte_scalar and lte_scalar ops.
* Added tests for neq_scalar.
* Added test for noop.
* - further work on clipbynorm_bp
Signed-off-by: Yurii <yurii@skymind.io>
* - get rid of concat op call, use instead direct concat helper call
Signed-off-by: Yurii <yurii@skymind.io>
* lstmBlockCell context fix
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for lrelu and lrelu_bp.
* Added tests for selu and selu_bp.
* Fixed lrelu derivative helpers.
* - some corrections in lstm
Signed-off-by: Yurii <yurii@skymind.io>
* operator * result shape fix
Signed-off-by: raver119 <raver119@gmail.com>
* - correct typo in lstmCell
Signed-off-by: Yurii <yurii@skymind.io>
* few tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* CUDA inverse broadcast bool fix
Signed-off-by: raver119 <raver119@gmail.com>
* disable MMAP test for CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* BooleanOp syncToDevice
Signed-off-by: raver119 <raver119@gmail.com>
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* additional data types for im2col/col2im
Signed-off-by: raver119 <raver119@gmail.com>
* Added test for firas_sparse op.
* one more RandomBuffer test excluded
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for flatten op.
* Added test for Floor op.
* bunch of tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* mmulDot tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Implemented floordiv_bp op and tests.
* Fixed scalar case with cuda implementation for bds.
* - work on cuda kernel for clip_by_norm backprop op is completed
Signed-off-by: Yurii <yurii@skymind.io>
* Eliminate cbow crach.
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Eliminated abortion with batched nlp test.
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed shared flag initializing.
* disabled bunch of cpu workspaces tests
Signed-off-by: raver119 <raver119@gmail.com>
* scalar operators fix: missing registerSpecialUse call
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed logdet for cuda and tests.
* - correct clipBynorm_bp
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed crop_and_resize shape datatype.
* - correct some mmul tests
Signed-off-by: Yurii <yurii@skymind.io>
* build fix
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI (#97)
Signed-off-by: raver119 <raver119@gmail.com>
* temporary stack fix
Signed-off-by: raver119 <raver119@gmail.com>
* round robin affinity test
Signed-off-by: raver119 <raver119@gmail.com>
* get rid of legacy CudaContext methods
Signed-off-by: raver119 <raver119@gmail.com>
* get rid of legacy ContextPool classes/methods
Signed-off-by: raver119 <raver119@gmail.com>
* one legacy test removed
Signed-off-by: raver119 <raver119@gmail.com>
* few more fields rearranged
Signed-off-by: raver119 <raver119@gmail.com>
* OpaqueLaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* OpaqueLaunchContext++
Signed-off-by: raver119 <raver119@gmail.com>
* more of OpaqueLaunchContext methods
Signed-off-by: raver119 <raver119@gmail.com>
* LaunchContext -> CudaContext
Signed-off-by: raver119 <raver119@gmail.com>
* AffinityManger changes
Signed-off-by: raver119 <raver119@gmail.com>
* AffinityManger changes
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver handles
Signed-off-by: raver119 <raver119@gmail.com>
* typo
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver method
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver handle propagated
Signed-off-by: raver119 <raver119@gmail.com>
* blas/solver handles
Signed-off-by: raver119 <raver119@gmail.com>
* one more test
Signed-off-by: raver119 <raver119@gmail.com>
* legacy concat implementations replaced with new CustomOp
Signed-off-by: raver119 <raver119@gmail.com>
* one more test
Signed-off-by: raver119 <raver119@gmail.com>
* concat now uses way more blocks
Signed-off-by: raver119 <raver119@gmail.com>
* print
Signed-off-by: raver119 <raver119@gmail.com>
* no more triple template mmul
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of kernels have dtypes reconsidered
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of kernels have dtypes reconsidered
Signed-off-by: raver119 <raver119@gmail.com>
* bitonic sort reorganized
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of cpu stuff removed from cuda scope
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of cpu stuff removed from cuda scope
Signed-off-by: raver119 <raver119@gmail.com>
* type conversions moved to generic impl
Signed-off-by: raver119 <raver119@gmail.com>
* cpu data types pass
Signed-off-by: raver119 <raver119@gmail.com>
* non_max_suppression
Signed-off-by: raver119 <raver119@gmail.com>
* sortByValue fix
Signed-off-by: raver119 <raver119@gmail.com>
* ignore all mixed datatype tests for mmul
Signed-off-by: raver119 <raver119@gmail.com>
* special handling of OpProfiler exceptions
Signed-off-by: raver119 <raver119@gmail.com>
* - one failing concat test in cpp
- Nd4j.tile now uses op internally
Signed-off-by: raver119 <raver119@gmail.com>
* get back dtype exception for legacy arrays deserialization
Signed-off-by: raver119 <raver119@gmail.com>
2019-08-14 15:52:34 +02:00
|
|
|
#endif
|
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, Reduce3_2) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {5, 5});
|
|
|
|
auto y = NDArrayFactory::create<float>('c', {5});
|
|
|
|
auto z = NDArrayFactory::create<float>('c', {5});
|
|
|
|
|
|
|
|
auto dim = NDArrayFactory::create<int>('c', {1}, {1});
|
2019-08-02 19:01:03 +02:00
|
|
|
dim.syncToHost();
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::LaunchContext* context = sd::LaunchContext::defaultContext();
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
Nd4jPointer* extraPointers = nullptr;
|
|
|
|
#ifdef __CUDABLAS__
|
|
|
|
extraPointers = new Nd4jPointer[7] {nullptr, context->getCudaStream(), context->getScalarPointer(), nullptr, context->getCudaSpecialStream(), context->getReductionPointer(), context->getAllocationPointer()};
|
|
|
|
#endif
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
auto packX = sd::ConstantTadHelper::getInstance()->tadForDimensions(x.getShapeInfo(), {1});
|
|
|
|
auto packY = sd::ConstantTadHelper::getInstance()->tadForDimensions(y.getShapeInfo(), {1});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray::prepareSpecialUse({&z}, {&x, &y, &dim});
|
2020-01-04 11:27:50 +01:00
|
|
|
OpaqueDataBuffer xBuf(x.dataBuffer());
|
|
|
|
OpaqueDataBuffer yBuf(y.dataBuffer());
|
|
|
|
OpaqueDataBuffer zBuf(z.dataBuffer());
|
|
|
|
OpaqueDataBuffer dimBuf(dim.dataBuffer());
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
execReduce3Tad(extraPointers, reduce3::CosineSimilarity,
|
2020-01-04 11:27:50 +01:00
|
|
|
&xBuf, x.shapeInfo(), x.specialShapeInfo(),
|
|
|
|
nullptr, &yBuf, y.shapeInfo(), y.specialShapeInfo(),
|
|
|
|
&zBuf, z.shapeInfo(), z.specialShapeInfo(),
|
|
|
|
&dimBuf, dim.shapeInfo(), dim.specialShapeInfo(),
|
2019-08-02 19:01:03 +02:00
|
|
|
packX.platformShapeInfo(), packX.platformOffsets(), packY.platformShapeInfo(), packY.platformOffsets());
|
|
|
|
|
|
|
|
NDArray::registerSpecialUse({&z}, {&x, &y, &dim});
|
|
|
|
|
|
|
|
delete []extraPointers;
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, Reduce3_3) {
|
|
|
|
auto x = NDArrayFactory::create<double>('c', {3, 5}, {-0.84443557262, -0.06822254508, 0.74266910552, 0.61765557527, -0.77555125951,
|
|
|
|
-0.99536740779, -0.0257304441183, -0.6512106060, -0.345789492130, -1.25485503673,
|
|
|
|
0.62955373525, -0.31357592344, 1.03362500667, -0.59279078245, 1.1914824247});
|
|
|
|
|
|
|
|
auto y = NDArrayFactory::create<double>('c', {5}, {-0.99536740779, -0.0257304441183, -0.6512106060, -0.345789492130, -1.25485503673});
|
|
|
|
auto e = NDArrayFactory::create<double>('c', {3}, {0.577452, 0.0, 1.80182});
|
|
|
|
auto z = NDArrayFactory::create<double>('c', {3});
|
|
|
|
|
|
|
|
auto dim = NDArrayFactory::create<int>('c', {1}, {1});
|
2019-08-02 19:01:03 +02:00
|
|
|
dim.syncToHost();
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::LaunchContext* context = sd::LaunchContext::defaultContext();
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
Nd4jPointer* extraPointers = nullptr;
|
|
|
|
#ifdef __CUDABLAS__
|
|
|
|
extraPointers = new Nd4jPointer[7] {nullptr, context->getCudaStream(), context->getScalarPointer(), nullptr, context->getCudaSpecialStream(), context->getReductionPointer(), context->getAllocationPointer()};
|
|
|
|
#endif
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
auto packX = sd::ConstantTadHelper::getInstance()->tadForDimensions(x.getShapeInfo(), {1});
|
|
|
|
auto packY = sd::ConstantTadHelper::getInstance()->tadForDimensions(y.getShapeInfo(), {1});
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
NDArray::prepareSpecialUse({&z}, {&x, &y, &dim});
|
2020-01-04 11:27:50 +01:00
|
|
|
OpaqueDataBuffer xBuf(x.dataBuffer());
|
|
|
|
OpaqueDataBuffer yBuf(y.dataBuffer());
|
|
|
|
OpaqueDataBuffer zBuf(z.dataBuffer());
|
|
|
|
OpaqueDataBuffer dimBuf(dim.dataBuffer());
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
execReduce3Tad(extraPointers, reduce3::CosineDistance,
|
2020-01-04 11:27:50 +01:00
|
|
|
&xBuf, x.shapeInfo(), x.specialShapeInfo(),
|
2019-08-02 19:01:03 +02:00
|
|
|
nullptr,
|
2020-01-04 11:27:50 +01:00
|
|
|
&yBuf, y.shapeInfo(), y.specialShapeInfo(),
|
|
|
|
&zBuf, z.shapeInfo(), z.specialShapeInfo(),
|
|
|
|
&dimBuf, dim.shapeInfo(), dim.specialShapeInfo(),
|
2019-08-02 19:01:03 +02:00
|
|
|
packX.platformShapeInfo(), packX.platformOffsets(), packY.platformShapeInfo(), packY.platformOffsets());
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_EQ(e, z);
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray::registerSpecialUse({&z}, {&x, &y, &dim});
|
|
|
|
delete []extraPointers;
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, Reduce3_4) {
|
|
|
|
auto x = NDArrayFactory::create<double>('c', {3, 5}, {-0.84443557262, -0.06822254508, 0.74266910552, 0.61765557527, -0.77555125951,
|
|
|
|
-0.99536740779, -0.0257304441183, -0.6512106060, -0.345789492130, -1.25485503673,
|
|
|
|
0.62955373525, -0.31357592344, 1.03362500667, -0.59279078245, 1.1914824247});
|
|
|
|
|
|
|
|
auto y = NDArrayFactory::create<double>('c', {1, 5}, {-0.99536740779, -0.0257304441183, -0.6512106060, -0.345789492130, -1.25485503673});
|
|
|
|
auto e = NDArrayFactory::create<double>('c', {1, 3}, {0.577452, 0.0, 1.80182});
|
|
|
|
auto z = NDArrayFactory::create<double>('c', {1, 3});
|
|
|
|
|
|
|
|
auto dim = NDArrayFactory::create<int>('c', {1}, {1});
|
2019-08-02 19:01:03 +02:00
|
|
|
dim.syncToHost();
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::LaunchContext* context = sd::LaunchContext::defaultContext();
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
Nd4jPointer* extraPointers = nullptr;
|
|
|
|
#ifdef __CUDABLAS__
|
|
|
|
extraPointers = new Nd4jPointer[7] {nullptr, context->getCudaStream(), context->getScalarPointer(), nullptr, context->getCudaSpecialStream(), context->getReductionPointer(), context->getAllocationPointer()};
|
|
|
|
#endif
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
auto packX = sd::ConstantTadHelper::getInstance()->tadForDimensions(x.getShapeInfo(), {1});
|
|
|
|
auto packY = sd::ConstantTadHelper::getInstance()->tadForDimensions(y.getShapeInfo(), {1});
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
NDArray::prepareSpecialUse({&z}, {&x, &y, &dim});
|
2020-01-04 11:27:50 +01:00
|
|
|
OpaqueDataBuffer xBuf(x.dataBuffer());
|
|
|
|
OpaqueDataBuffer yBuf(y.dataBuffer());
|
|
|
|
OpaqueDataBuffer zBuf(z.dataBuffer());
|
|
|
|
OpaqueDataBuffer dimBuf(dim.dataBuffer());
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
execReduce3Tad(extraPointers, reduce3::CosineDistance,
|
2020-01-04 11:27:50 +01:00
|
|
|
&xBuf, x.shapeInfo(), x.specialShapeInfo(),
|
2019-06-06 14:21:15 +02:00
|
|
|
nullptr,
|
2020-01-04 11:27:50 +01:00
|
|
|
&yBuf, y.shapeInfo(), y.specialShapeInfo(),
|
|
|
|
&zBuf, z.shapeInfo(), z.specialShapeInfo(),
|
|
|
|
&dimBuf, dim.shapeInfo(), dim.specialShapeInfo(),
|
2019-08-02 19:01:03 +02:00
|
|
|
packX.platformShapeInfo(), packX.platformOffsets(), packY.platformShapeInfo(), packY.platformOffsets());
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
// z.printIndexedBuffer("z");
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray::registerSpecialUse({&z}, {&x, &y, &dim});
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_EQ(e, z);
|
2019-08-02 19:01:03 +02:00
|
|
|
delete []extraPointers;
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, Reduce3_5) {
|
|
|
|
auto x = NDArrayFactory::create<double>('c', {3, 5}, {-0.84443557262, -0.06822254508, 0.74266910552, 0.61765557527, -0.77555125951,
|
|
|
|
-0.99536740779, -0.0257304441183, -0.6512106060, -0.345789492130, -1.25485503673,
|
|
|
|
0.62955373525, -0.31357592344, 1.03362500667, -0.59279078245, 1.1914824247});
|
|
|
|
|
|
|
|
auto y = NDArrayFactory::create<double>('c', {1, 5}, {-0.99536740779, -0.0257304441183, -0.6512106060, -0.345789492130, -1.25485503673});
|
|
|
|
auto e = NDArrayFactory::create<double>('c', {1, 3}, {0.577452, 0.0, 1.80182});
|
|
|
|
auto z = NDArrayFactory::create<double>('c', {1, 3});
|
|
|
|
|
|
|
|
auto dim = NDArrayFactory::create<int>('c', {1}, {1});
|
2019-08-02 19:01:03 +02:00
|
|
|
dim.syncToHost();
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::LaunchContext* context = sd::LaunchContext::defaultContext();
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
Nd4jPointer* extraPointers = nullptr;
|
|
|
|
#ifdef __CUDABLAS__
|
|
|
|
extraPointers = new Nd4jPointer[7] {nullptr, context->getCudaStream(), context->getScalarPointer(), nullptr, context->getCudaSpecialStream(), context->getReductionPointer(), context->getAllocationPointer()};
|
|
|
|
#endif
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
auto packX = sd::ConstantTadHelper::getInstance()->tadForDimensions(x.getShapeInfo(), {1});
|
|
|
|
auto packY = sd::ConstantTadHelper::getInstance()->tadForDimensions(y.getShapeInfo(), {1});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray::prepareSpecialUse({&z}, {&x, &y, &dim});
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2020-01-04 11:27:50 +01:00
|
|
|
OpaqueDataBuffer xBuf(x.dataBuffer());
|
|
|
|
OpaqueDataBuffer yBuf(y.dataBuffer());
|
|
|
|
OpaqueDataBuffer zBuf(z.dataBuffer());
|
|
|
|
OpaqueDataBuffer dimBuf(dim.dataBuffer());
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
execReduce3Tad(extraPointers, reduce3::CosineDistance,
|
2020-01-04 11:27:50 +01:00
|
|
|
&xBuf, x.shapeInfo(), x.specialShapeInfo(),
|
2019-06-06 14:21:15 +02:00
|
|
|
nullptr,
|
2020-01-04 11:27:50 +01:00
|
|
|
&yBuf, y.shapeInfo(), y.specialShapeInfo(), &zBuf, z.shapeInfo(), z.specialShapeInfo(),
|
|
|
|
&dimBuf, dim.shapeInfo(), dim.specialShapeInfo(),
|
2019-08-02 19:01:03 +02:00
|
|
|
packX.platformShapeInfo(), packX.platformOffsets(), packY.platformShapeInfo(), packY.platformOffsets());
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray::registerSpecialUse({&z}, {&x, &y, &dim});
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_EQ(e, z);
|
2019-08-02 19:01:03 +02:00
|
|
|
delete []extraPointers;
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, test_Reduce3_All_1) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {1000, 100});
|
|
|
|
auto y = NDArrayFactory::create<float>('c', {1, 100});
|
|
|
|
auto z = NDArrayFactory::create<float>('c', {1000, 1});
|
|
|
|
auto dim = NDArrayFactory::create<int>('c', {1}, {-1});
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
auto tadPackX = sd::ConstantTadHelper::getInstance()->tadForDimensions(x.shapeInfo(), -1);
|
|
|
|
auto tadPackY = sd::ConstantTadHelper::getInstance()->tadForDimensions(y.shapeInfo(), -1);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
sd::LaunchContext* context = sd::LaunchContext::defaultContext();
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
Nd4jPointer* extraPointers = nullptr;
|
|
|
|
#ifdef __CUDABLAS__
|
|
|
|
extraPointers = new Nd4jPointer[7] {nullptr, context->getCudaStream(), context->getScalarPointer(), nullptr, context->getCudaSpecialStream(), context->getReductionPointer(), context->getAllocationPointer()};
|
|
|
|
#endif
|
|
|
|
|
|
|
|
NDArray::prepareSpecialUse({&z}, {&x, &y});
|
|
|
|
|
2020-01-04 11:27:50 +01:00
|
|
|
OpaqueDataBuffer xBuf(x.dataBuffer());
|
|
|
|
OpaqueDataBuffer yBuf(y.dataBuffer());
|
|
|
|
OpaqueDataBuffer zBuf(z.dataBuffer());
|
|
|
|
OpaqueDataBuffer dimBuf(dim.dataBuffer());
|
|
|
|
|
|
|
|
execReduce3All(extraPointers, reduce3::EuclideanDistance, &xBuf, x.shapeInfo(), x.specialShapeInfo(),
|
|
|
|
nullptr, &yBuf, y.shapeInfo(), y.specialShapeInfo(),
|
|
|
|
&zBuf, z.shapeInfo(), z.specialShapeInfo(),
|
|
|
|
&dimBuf, dim.shapeInfo(), dim.specialShapeInfo(),
|
2019-06-06 14:21:15 +02:00
|
|
|
tadPackX.platformShapeInfo(), tadPackX.platformOffsets(),
|
|
|
|
tadPackY.platformShapeInfo(), tadPackY.platformOffsets());
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
NDArray::registerSpecialUse({&z}, {&x, &y});
|
|
|
|
|
|
|
|
delete []extraPointers;
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, test_inverse_broadcast_1) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {4}, {2.0f, 2.0f, 2.0f, 2.0f});
|
|
|
|
auto y = NDArrayFactory::create<float>('c', {3, 4});
|
|
|
|
auto e = NDArrayFactory::create<float>('c', {3, 4});
|
|
|
|
e.assign(2.0f);
|
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
auto tadPackY = sd::ConstantTadHelper::getInstance()->tadForDimensions(y.shapeInfo(), 1);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
y.tickWriteDevice();
|
|
|
|
|
|
|
|
NativeOpExecutioner::execInverseBroadcast(LaunchContext::defaultContext(), broadcast::Add,
|
|
|
|
x.buffer(), x.shapeInfo(), x.specialBuffer(), x.specialShapeInfo(),
|
|
|
|
y.buffer(), y.shapeInfo(), y.specialBuffer(), y.specialShapeInfo(),
|
|
|
|
y.buffer(), y.shapeInfo(), y.specialBuffer(), y.specialShapeInfo(),
|
|
|
|
nullptr, 0,
|
|
|
|
tadPackY.platformShapeInfo(), tadPackY.platformOffsets(),
|
|
|
|
tadPackY.platformShapeInfo(), tadPackY.platformOffsets());
|
|
|
|
|
|
|
|
ASSERT_EQ(e, y);
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, test_inverse_broadcast_2) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {4}, {2.0f, 2.0f, 2.0f, 2.0f});
|
|
|
|
auto y = NDArrayFactory::create<float>('c', {3, 4});
|
|
|
|
auto z = NDArrayFactory::create<bool>('c', {3, 4});
|
|
|
|
auto e = NDArrayFactory::create<bool>('c', {3, 4});
|
|
|
|
e.assign(false);
|
|
|
|
|
2020-03-03 05:32:37 +01:00
|
|
|
auto row = y(1, {0});
|
2019-12-20 20:35:39 +01:00
|
|
|
row.assign(2.0f);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2020-03-03 05:32:37 +01:00
|
|
|
auto erow = e(1, {0});
|
2019-12-20 20:35:39 +01:00
|
|
|
erow.assign(true);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2020-03-02 10:49:41 +01:00
|
|
|
auto tadPackY = sd::ConstantTadHelper::getInstance()->tadForDimensions(y.shapeInfo(), 1);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
z.tickWriteDevice();
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
NativeOpExecutioner::execInverseBroadcastBool(LaunchContext::defaultContext(), broadcast::BoolOps::EqualTo,
|
|
|
|
x.buffer(), x.shapeInfo(), x.specialBuffer(), x.specialShapeInfo(),
|
|
|
|
y.buffer(), y.shapeInfo(), y.specialBuffer(), y.specialShapeInfo(),
|
|
|
|
z.buffer(), z.shapeInfo(), z.specialBuffer(), z.specialShapeInfo(),
|
2019-11-21 13:43:03 +01:00
|
|
|
nullptr,
|
2019-06-06 14:21:15 +02:00
|
|
|
nullptr, 0,
|
|
|
|
tadPackY.platformShapeInfo(), tadPackY.platformOffsets(),
|
|
|
|
tadPackY.platformShapeInfo(), tadPackY.platformOffsets());
|
|
|
|
|
|
|
|
ASSERT_EQ(e, z);
|
2019-06-15 13:34:34 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, test_legacy_reduce_empty_1) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {2, 0, 3});
|
|
|
|
auto z = NDArrayFactory::create<float>('c', {2, 3});
|
|
|
|
auto e = NDArrayFactory::create<float>('c', {2, 3});
|
|
|
|
|
|
|
|
int dim = 1;
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
NativeOpExecutioner::execReduceSame(LaunchContext::defaultContext(), reduce::SameOps::Sum,
|
|
|
|
x.buffer(), x.shapeInfo(), x.specialBuffer(), x.specialShapeInfo(),
|
|
|
|
nullptr,
|
|
|
|
z.buffer(), z.shapeInfo(), z.specialBuffer(), z.specialShapeInfo(),
|
|
|
|
&dim, 1, x.getPlatformShapeInfo(), nullptr);
|
2019-06-15 13:34:34 +02:00
|
|
|
|
|
|
|
ASSERT_EQ(e, z);
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, test_legacy_reduce_empty_2) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {2, 0, 3});
|
|
|
|
auto z = NDArrayFactory::create<float>('c', {2, 3});
|
|
|
|
auto e = NDArrayFactory::create<float>('c', {2, 3});
|
|
|
|
e.assign(std::numeric_limits<float>::infinity());
|
|
|
|
|
|
|
|
int dim = 1;
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
NativeOpExecutioner::execReduceSame(LaunchContext::defaultContext(), reduce::SameOps::Min, x.buffer(), x.shapeInfo(), x.specialBuffer(), x.specialShapeInfo(), nullptr, z.buffer(), z.shapeInfo(), z.specialBuffer(), z.specialShapeInfo(), &dim, 1, x.getPlatformShapeInfo(), nullptr);
|
2019-06-15 13:34:34 +02:00
|
|
|
|
|
|
|
ASSERT_EQ(e, z);
|
|
|
|
}
|
|
|
|
|
|
|
|
TEST_F(LegacyOpsTests, test_legacy_reduce_empty_3) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {2, 0, 3});
|
|
|
|
auto z = NDArrayFactory::create<float>('c', {2, 3});
|
|
|
|
auto e = NDArrayFactory::create<float>('c', {2, 3});
|
|
|
|
e.assign(-std::numeric_limits<float>::infinity());
|
|
|
|
|
|
|
|
int dim = 1;
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
NativeOpExecutioner::execReduceSame(LaunchContext::defaultContext(), reduce::SameOps::Max, x.buffer(), x.shapeInfo(), x.specialBuffer(), x.specialShapeInfo(), nullptr, z.buffer(), z.shapeInfo(), z.specialBuffer(), z.specialShapeInfo(), &dim, 1, x.getPlatformShapeInfo(), nullptr);
|
2019-06-15 13:34:34 +02:00
|
|
|
|
|
|
|
ASSERT_EQ(e, z);
|
|
|
|
}
|
|
|
|
|
2019-11-13 15:15:18 +01:00
|
|
|
TEST_F(LegacyOpsTests, test_legacy_reduce_empty_4) {
|
|
|
|
if (!Environment::getInstance()->isCPU())
|
|
|
|
return;
|
|
|
|
int a = 0;
|
|
|
|
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {1, 0, 2});
|
|
|
|
auto d = NDArrayFactory::create<int>('c', {1}, {a});
|
|
|
|
auto z = NDArrayFactory::create<float>('c', {0, 2});
|
|
|
|
auto e = NDArrayFactory::create<float>('c', {0, 2});
|
|
|
|
|
2020-01-04 11:27:50 +01:00
|
|
|
InteropDataBuffer xdb(x.dataBuffer());
|
|
|
|
InteropDataBuffer ddb(d.dataBuffer());
|
|
|
|
InteropDataBuffer zdb(z.dataBuffer());
|
2019-11-13 15:15:18 +01:00
|
|
|
|
|
|
|
|
|
|
|
::execReduceSame2(nullptr, reduce::SameOps::Sum,
|
2020-01-04 11:27:50 +01:00
|
|
|
&xdb, x.shapeInfo(), x.specialShapeInfo(),
|
2019-11-13 15:15:18 +01:00
|
|
|
nullptr,
|
2020-01-04 11:27:50 +01:00
|
|
|
&zdb, z.shapeInfo(), z.specialShapeInfo(),
|
|
|
|
&ddb, d.shapeInfo(), d.specialShapeInfo());
|
2019-11-13 15:15:18 +01:00
|
|
|
|
|
|
|
}
|
|
|
|
|
2019-06-15 13:34:34 +02:00
|
|
|
TEST_F(LegacyOpsTests, test_legacy_transform_float_1) {
|
|
|
|
auto x = NDArrayFactory::create<float>('c', {1, 0, 4});
|
|
|
|
|
|
|
|
NativeOpExecutioner::execTransformFloat(LaunchContext::defaultContext(), transform::FloatOps::RSqrt, x.buffer(), x.shapeInfo(), x.specialBuffer(), x.specialShapeInfo(), x.buffer(), x.shapeInfo(), x.specialBuffer(), x.specialShapeInfo(), nullptr, nullptr, nullptr);
|
2019-07-22 13:34:08 +02:00
|
|
|
}
|