cavis/libnd4j/tests_cpu/layers_tests/DeclarableOpsTests14.cpp
Alex Black 1170827c18 Merge master to upstream (#7945)
* Shugeo strided slice zeros (#14)

* Modified strided_slice op to properly work with empty-like shapes.

* Fixed test for reduce_mean with empty-like input.

* [WIP] Last merge (#15)

* correct logsoftmax looss (#2)

* Small SameDiff listener fix (#4)

* Various fixes (#6)

* #7839 Fix for asXMatrix and tests

* #7866 EmbeddingSequenceLayer dtype fix + test

* #7856 SameDiff save/load stream methods

* #7859 RegressionEvaluation rank 4 fix + tests + axis configuration

* EvaluationBinary 3d/4d

* More evaluation 3d/4d tests

* #7847 Evaluation empty checks

* Small test ifx

* #7848 Fix median edge case

* Improve DL4J samediff layer tests

* [WIP] FastText wrapper implemented (#8)

* FastText implemented

* Some fixes

* Fix shapes for wordsNearest

* Validation of input vectors

* Fixes

* Fixed test

* Thread tagged

* Some tweaks

* setContextClassLoader for DeallocatorServiceThread

* Numpy format tests (#1)

* Various fixes (#11)

* #7852 SameDiff gather fix

* #7892 SameDiff placeholder to constant conversion

* #7890 validate input rank for MLN/CG init methods

* Fix broken permute shape calculation

* Permute and gather fixes

* Tests

* #7850 LogSumExp fix + test

* Handful of test fixes

* Empty arrays with non-scalar shapes (#10)

* minor rearrangements for lambdas

* empty tensors with non-scalar shapes

* numpy empty tensors with non-scalar shapes

* few more empty tweaks

* Small fixes

* conv3d signature update

* micro fix in batchnorm mkldnn

* Import fixes

* Fix

* MKL-DNN update

* Small fill fix

* fill with empty input + test

* Fixes

* Small error improvement

* Fix

* one special test

* couple of fixes for lstm

* Rewrite TFGraphMapper.getNDArrayFromTensor to be maintainable and less error prone

* Fixes

* FP16

* Unsigned

* BFloat16

* Fill op - empty tweaks

* - couple of fixes for empty arrays construction
- stack updated

* strided slice fix

* one transform test

* provide method for reducing shapeInfo in case of input array is empty

* Fixed reduceAlongDimensions to use empty input properly.

* couple of broadcast tests

* couple of tests broadcast tests + tweak to make them pass

* add check of non-empty to methods producing sub-arrays

* Fixed reshapeC with zeros in shape.

* complete empty check in reduce_... legacy ops

* Concat and cumsum/prod

* Tweak to empty shape inference on import

* add empty check to the rest of reduce legacy ops

* one more test

* correct typo in evalReduceShapeInfoEmpty

* Added tests for reduce_* ops to tests with zero shapes.

* few more tests for empty reductions

* Fixed strided_slice op with empty case and tests.

* one more empty reduction test

* Fixed strided_slice test.

* add empty check to NDArray::reshapei

* infOrMax

* empty min/max with infinity tests

* made unstack working correctly with empty arrays

* few IndexReduce tests + tweaks for empty shapes

* add test for empty concat

* few tests fixed

* Validation fix for reductions on empty shapes

* Reverse fix

* Reduction shape calc fixes

* SameDiff.generateOutputVariable: don't use shape function to determine number of outputs

* Range fix

* - NDArray constructor updated for scalars/empty arrays
- few tests fixed

* More fixes

* Empty creator fixes

* concat fix

* concat fix

* TF import tests: allow 'both all NaN' and 'both all inf' to pass

* Slice, zero fraction, and reshape fixes

* transpose, gather

* Zero fraction

* scalar cast fix

* Empty reduction axis support

* few more tests fixed

* Fixed input checks conforming with TF for concat op and tests.

* few tests fixed

* matmul scalar shape fix

* Fixed checkout for data type and scalarity with concat to allow non-empty scalars with vector concats.

* broadcast bool fix

* few more tests

* few more tests

* correct evalReduceShapeInfoEmpty

* argmax/argmin + tests

* one more empty edge case + one more test

* argmax/argmin/realdiv_bp tweaks

* empty reshape test + fix

* Helper fixes

* Small fixes

* Gather test fix

* Gather test fix

* Small fixes

* reduce scalar zero values

* scalar mean workaround

* Remove debug code

* along dim mean workaround

* one more test

* - equalsTo() tweak for empty arrays
- one more test

* broadcast tweaks

* [WIP] Fixing outstanding issues for NLP (#9)

* Avoid using not-inited objects

* Test fixed.

* Redundant method avoided for models like FastText

* KMeans++ implementation

* KMeans++ implementation

* Disable parallel execution

* KMeans++

* Tests

* Dev branch merge (#16)

* SameDiff: convertDataType and gradient check util improvements (#12)

* GradCheck util improvements

* StopGradient constructor + test

* SameDiff: Add datatype conversion

* Javadoc and add DataType.isNumerical()

* Small fix

* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)

* TFGraphTestAllHelper: check intermediates in execution order

* Add missing debug listener

* [WIP] lstmBlock fix + other changes (#13)

- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite

* Small test fix

* CheckNumerics op wrapper

* Fix some issues on master (#17)

* Fix DataVec test issue

* Fix issue with dl4j SameDiff output layer

* Dtype fix for lambda layers

* #7912 BertIterator dtype fix (use float32 not global default)

* [WIP] Next set of CUDA stuff (#7)

New CUDA implementations and improvements

* bad file

* Dev branch master merge (#23)

* SameDiff: convertDataType and gradient check util improvements (#12)

* GradCheck util improvements

* StopGradient constructor + test

* SameDiff: Add datatype conversion

* Javadoc and add DataType.isNumerical()

* Small fix

* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)

* TFGraphTestAllHelper: check intermediates in execution order

* Add missing debug listener

* [WIP] lstmBlock fix + other changes (#13)

- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite

* Small test fix

* CheckNumerics op wrapper

* Compatibility of deserialization (#18)

Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>

* SameDiff: add activation gradient checking support for debugging (#19)

* SameDiff gradient checker: first pass on activation gradient checks

* Fixes + tests for activation gradient checking

* Javadoc

* [WIP] Some nd4j data type corrections (#20)

* Adjust data type

* Set correct Data type.

* Size of proper data type.

* fix averaged cpu load (#22)

* SameDiff ops, TF import and fixes (#24)

* CheckNumerics tests + fixes + misc fixes

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Fake quant

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Fixes

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* FakeQuantWithMinMaxArgs

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* CheckNumerics fix

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Fix libnd4j ALL_INTS and ALL_FLOATS declaration (uint and bfloat types)

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Small fix

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Javadoc

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Exception tweak

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* fix

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Fix for out of scope stack allocated var use

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Ignores

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Ignore for known failing test (already logged issue)

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Merge upstream to fork (#25)

* Add thousand-separator commas to TotalParams (#7915)

* Add thousand-separator commas to TotalParams

The number of parameters can be quite large, and it would help the reading of the summary printout to have the TotalParams column & values at the bottom have thousand-separator-commas in them.

* Add thousand-separator commas to MultiLayerNetwork

Corresponding change to MultiLayerNetwork

Signed-off-by: Jxtps Jxtps <jxtps435@gmail.com>

* Update contributing and issue/PR templates (#7934)

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Fix link to AdaDelta paper (#7942)

Fix link to AdaDelta paper hosted on matthewzeiler.com

Signed-off-by: Jxtps

* Fixes, and ignores for known/logged failing issues (#7943)

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* SameDiff + DL4J/SameDiff: Multiple fixes (#28)

* #7919 HDF5 attribute buffer length fix

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* #7909 Arbiter constructor exception ux improvements

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* #7925 RNN output layer length checks

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* #7939 Add listener for validating inputs are not incorrectly modified

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* #7939 Integrate NonInplaceValidationListener into tests

* #7844 DL4J SameDiff fixes for variable minibatch size

* DL4J SameDiff fixes - ensure gradient for input placeholder is available

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* Tweaks to ExternalErrorsFunction - use placeholders, make more robust

* Another fix

* More fixes

* More SameDiff/DL4J fixes

* Scope out scalar array creation in BaseScalarOp

* Remove debug code

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* [WIP] Final dev branch merge (#29)

* SameDiff: convertDataType and gradient check util improvements (#12)

* GradCheck util improvements

* StopGradient constructor + test

* SameDiff: Add datatype conversion

* Javadoc and add DataType.isNumerical()

* Small fix

* Fix SameDiff TF import test cases intermediate naming (workaround for bad default)

* TFGraphTestAllHelper: check intermediates in execution order

* Add missing debug listener

* [WIP] lstmBlock fix + other changes (#13)

- fixes lstmBlock issue
- changes NDArray method reshape(), permute(), transpose() by making them return instance instead of pointer
- CheckNumerics op
- fixes for ReduceBool IsInfOrNan & IsFinite

* Small test fix

* CheckNumerics op wrapper

* Compatibility of deserialization (#18)

Signed-off-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>

* SameDiff: add activation gradient checking support for debugging (#19)

* SameDiff gradient checker: first pass on activation gradient checks

* Fixes + tests for activation gradient checking

* Javadoc

* [WIP] Some nd4j data type corrections (#20)

* Adjust data type

* Set correct Data type.

* Size of proper data type.

* fix averaged cpu load (#22)

* [WIP] Multiple dataset iterators (#27)

* Splitting dataset into arbitrary number

* Fixes

* Multiple split of iterator

* Test

* Test

* Some fixes

* signature change

* one more tweak

Signed-off-by: raver119 <raver119@gmail.com>

* one more test for sequential use of DataSetIteratorSplitter

Signed-off-by: raver119 <raver119@gmail.com>

* Fixes

* Fixes

* one more test for Alexander

Signed-off-by: raver119 <raver119@gmail.com>

* Some fixes

* Some fixes

* one more test for Alexander

Signed-off-by: raver119 <raver119@gmail.com>

* minor test fix

Signed-off-by: raver119 <raver119@gmail.com>

* Some fixes

* Some fixes

* couple of assertions tweaked

Signed-off-by: raver119 <raver119@gmail.com>

* MDS splitter test :/

Signed-off-by: raver119 <raver119@gmail.com>

* Minor refactoring

* Multi dataset

* Some fixes

* More tests

* Small number of test fixes/improvements (failures on CI) (#31)

Signed-off-by: AlexDBlack <blacka101@gmail.com>

* [WIP] More CUDA stuff (#26)

* initial commit

Signed-off-by: raver119 <raver119@gmail.com>

* LRN BP CUDA

Signed-off-by: raver119 <raver119@gmail.com>

* less memory

Signed-off-by: raver119 <raver119@gmail.com>

* Fixed bug with crop_and_resize op helper.

* get rid of unnecessary index-calculation dunction

Signed-off-by: Yurii <yurii@skymind.io>

* Fixed sort with nth_element cuda-based helper.

* Refactored nth_element.

* Refactored nth_element op and tests.

* Modified usage of dim array with sortTad routine.

* Refactored main routine of helper for non_max_image_suppression op.

* non_max_image_suppression op helper with cuda kernel implementation. Initial revision.

* fix vol2col cuda kernel

* meh

Signed-off-by: raver119 <raver119@gmail.com>

* topK concept

Signed-off-by: raver119 <raver119@gmail.com>

* unsorted topK with scanWitdh of 1

Signed-off-by: raver119 <raver119@gmail.com>

* correct vol2col tests

* sorted/unsorted topK

Signed-off-by: raver119 <raver119@gmail.com>

* implementation and fixing col2im/col2vol

* Corrected usage flags with input/output with reverse op.

* dup is const now

Signed-off-by: raver119 <raver119@gmail.com>

* percentile op

Signed-off-by: raver119 <raver119@gmail.com>

* group tests for mapool2d

Signed-off-by: Yurii <yurii@skymind.io>

* special test for george

Signed-off-by: raver119 <raver119@gmail.com>

* less threads for sortTad

Signed-off-by: raver119 <raver119@gmail.com>

* provide conv2d for cuda

Signed-off-by: Yurii <yurii@skymind.io>

* remove auther in sort tad kernel code

Signed-off-by: Yurii <yurii@skymind.io>

* provide depthwise_conv2d for cuda

Signed-off-by: Yurii <yurii@skymind.io>

* - max_pooling_with_argmax
- null check for special use

Signed-off-by: raver119 <raver119@gmail.com>

* dts cuda

Signed-off-by: raver119 <raver119@gmail.com>

* provide sconv2d for cuda

Signed-off-by: Yurii <yurii@skymind.io>

* std cuda

Signed-off-by: raver119 <raver119@gmail.com>

* Refactored non_max_suppression op to conform TF implementation.

* Improved suppression helper.

* provide pooling3d for cuda

Signed-off-by: Yurii <yurii@skymind.io>

* minor lstm rearrangements

Signed-off-by: raver119 <raver119@gmail.com>

* more of minor lstm rearrangements

Signed-off-by: raver119 <raver119@gmail.com>

* (bi)dynamic_rnn

Signed-off-by: raver119 <raver119@gmail.com>

* templates init order

Signed-off-by: raver119 <raver119@gmail.com>

* Refactored non_max_suppression op.

* Added cuda kernel for non_max_suppression.

* CPU sort by key/value

Signed-off-by: raver119 <raver119@gmail.com>

* CPU sort TAD by key/value

Signed-off-by: raver119 <raver119@gmail.com>

* CPU sort TAD by key/value tests

Signed-off-by: raver119 <raver119@gmail.com>

* Eliminate compiler error with cuda implementation.

* - repaired gradCheck in cuda
- provide conv2d_bp for cuda

Signed-off-by: Yurii <yurii@skymind.io>

* missed signature

Signed-off-by: raver119 <raver119@gmail.com>

* provide depthwise_conv2d_bp for cuda

Signed-off-by: Yurii <yurii@skymind.io>

* Implementation of lup helper with cuda kernel. Initial commit.

* further work on backprops for convolutions

Signed-off-by: Yurii <yurii@skymind.io>

* CUDA linear sort by key/val

Signed-off-by: raver119 <raver119@gmail.com>

* CUDA tad sort by key/val

Signed-off-by: raver119 <raver119@gmail.com>

* start providing of backprop for pooling2d/3d

Signed-off-by: Yurii <yurii@skymind.io>

* Added atomicAdd for bool datatype.

* dynamic partition concept

Signed-off-by: raver119 <raver119@gmail.com>

* dynamic partition concept

Signed-off-by: raver119 <raver119@gmail.com>

* dynamic partition scalar CUDA

Signed-off-by: raver119 <raver119@gmail.com>

* important comment

Signed-off-by: raver119 <raver119@gmail.com>

* fix pooling2d/3d backprop helpers

Signed-off-by: Yurii <yurii@skymind.io>

* Added non-linear test with dynamic_partition.

* Improved test for dynamic_partition.

* dynamic_partition TAD concept

Signed-off-by: raver119 <raver119@gmail.com>

* - dynamic_partition TAD CUDA impl
- dynamic_partition TAD CPU fix

Signed-off-by: raver119 <raver119@gmail.com>

* - rewrite cpu code for usampling2d/3d
- write cuda code for usampling2d/3d

Signed-off-by: Yurii <yurii@skymind.io>

* dynamic_stitch CUDA vector case

Signed-off-by: raver119 <raver119@gmail.com>

* dynamic_stitch CUDA TAD case concept

Signed-off-by: raver119 <raver119@gmail.com>

* dynamic_stitch CUDA TAD case impl

Signed-off-by: raver119 <raver119@gmail.com>

* Added tests for dynamic_stitch 3D-4D cases.

* minor tests tweaks

Signed-off-by: raver119 <raver119@gmail.com>

* Fixed type check for dynamic stitch.

* min/max bp

Signed-off-by: raver119 <raver119@gmail.com>

* rewrite code for upsampling2d/3d cpu

Signed-off-by: Yurii <yurii@skymind.io>

* reduce min/max/norm_max bp

Signed-off-by: raver119 <raver119@gmail.com>

* lup implementation. Additional enhancements.

* provide code for upsamling2d/3d backprop

Signed-off-by: Yurii <yurii@skymind.io>

* weightedCrossEntropyWithLogits

Signed-off-by: raver119 <raver119@gmail.com>

* Fixed template math atomicMul for 64bit ints.

* Refactored dynamic_partition_bp op.

* inverseBroadcast fix

Signed-off-by: raver119 <raver119@gmail.com>

* DynamicPartitionBP test datatype fixed.

* - nd4j_atomicMul Windows fix
- cpu/NDArrayLambda.hpp excluded from CUDA

Signed-off-by: raver119 <raver119@gmail.com>
2019-06-27 18:37:04 +03:00

454 lines
14 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
******************************************************************************/
//
// Created by raver on 8/4/2018.
//
#include "testlayers.h"
#include <ops/declarable/CustomOperations.h>
#include <NDArray.h>
#include <ops/ops.h>
#include <GradCheck.h>
using namespace nd4j;
class DeclarableOpsTests14 : public testing::Test {
public:
DeclarableOpsTests14() {
printf("\n");
fflush(stdout);
}
};
TEST_F(DeclarableOpsTests14, Test_Validation_Edge_1) {
auto x = NDArrayFactory::create<int>('c', {2}, {2, 2});
auto exp = NDArrayFactory::create('c', {2, 2}, Environment::getInstance()->defaultFloatDataType());
exp.assign(4.0f);
nd4j::ops::fill op;
auto result = op.execute({&x}, {4.0f},{}, {});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
ASSERT_EQ(exp, *z);
delete result;
}
TEST_F(DeclarableOpsTests14, Test_Reshape_CF_1) {
auto x = NDArrayFactory::create<double>('f', {2, 3}, {1.0, 4.0, 2.0, 5.0, 3.0, 6.0});
auto e = NDArrayFactory::create<double>('f', {3, 2}, {1.0, 3.0, 5.0, 2.0, 4.0, 6.0});
x.printShapeInfo("x shape");
x.printBuffer("x buffr");
x.printIndexedBuffer("x indxd");
auto r = x.reshape('c', {3, 2});
r.printIndexedBuffer("r pre-s");
r.streamline('f');
nd4j::ops::reshape op;
auto result = op.execute({&x}, {}, {3, 2}, {});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
delete result;
}
TEST_F(DeclarableOpsTests14, Test_Inf_Comparison_1) {
auto x = NDArrayFactory::create<double>('c', {5}, {1, 2, 3, std::numeric_limits<double>::infinity(), 5});
auto y = NDArrayFactory::create<double>('c', {5}, {1, 2, 3, std::numeric_limits<double>::infinity(), 5});
ASSERT_EQ(x, y);
}
TEST_F(DeclarableOpsTests14, Test_Inf_Comparison_2) {
auto x = NDArrayFactory::create<double>('c', {5}, {1, 2, 3, std::numeric_limits<double>::infinity(), 5});
auto y = NDArrayFactory::create<double>('c', {5}, {1, 2, 3, -std::numeric_limits<double>::infinity(), 5});
ASSERT_NE(x, y);
}
TEST_F(DeclarableOpsTests14, Multiply_test) {
for(int k=2;k<10;k++){
nd4j_printf("k=%d\n", k);
NDArray x = NDArrayFactory::create<double>('c', {k, 1});
NDArray y = NDArrayFactory::create<double>('c', {k});
NDArray e = NDArrayFactory::create<double>('c', {k, k});
x.assign(1.0);
y.assign(1.0);
e.assign(1.0);
nd4j::ops::multiply op;
auto result = op.execute({&x, &y}, {}, {});
auto f = result->at(0);
NDArray r = *f;
ASSERT_EQ(e, r);
ASSERT_EQ(e, *f);
delete result;
}
}
TEST_F(DeclarableOpsTests14, Test_EvalReductionShape_1) {
auto x = NDArrayFactory::create<int>('c', {3}, {5, 3, 4});
auto y = NDArrayFactory::create<int>('c', {1}, {1});
auto e = NDArrayFactory::create<Nd4jLong>('c', {2}, {5, 4});
nd4j::ops::evaluate_reduction_shape op;
auto result = op.execute({&x, &y}, {}, {}, {false, false});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
z->printIndexedBuffer("Reduced shape");
ASSERT_EQ(e, *z);
delete result;
}
TEST_F(DeclarableOpsTests14, Test_EvalReductionShape_2) {
auto x = NDArrayFactory::create<int>('c', {3}, {5, 3, 4});
auto y = NDArrayFactory::create<int>('c', {1}, {1});
auto e = NDArrayFactory::create<Nd4jLong>('c', {3}, {5, 1, 4});
nd4j::ops::evaluate_reduction_shape op;
auto result = op.execute({&x, &y}, {}, {}, {true, false});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
ASSERT_EQ(e, *z);
delete result;
}
TEST_F(DeclarableOpsTests14, Test_Reduce_Min_Small_0) {
auto x = NDArrayFactory::create<float>('c', {3, 4}, {-999.f, 0.2236f, 0.7973f, 0.0962f, 0.7231f, 0.3381f, -0.7301f, 0.9115f, -0.5094f, 0.9749f, -2.1340f, 0.6023f});
auto z = NDArrayFactory::create<float>('c', {4});
auto e = NDArrayFactory::create<float>('c', {4}, {-999.f, 0.2236f, -2.1340f, 0.0962f});
nd4j::ops::reduce_min op;
op.execute({&x}, {&z}, {}, {0}, {});
//z.printIndexedBuffer("Z");
ASSERT_EQ(e, z);
}
TEST_F(DeclarableOpsTests14, Test_Reduce_Min_Small_1) {
auto x = NDArrayFactory::create<float>('c', {3, 4}, {-999.f, 0.2236f, 0.7973f, 0.0962f, 0.7231f, 0.3381f, -0.7301f, 0.9115f, -0.5094f, 0.9749f, -2.1340f, 0.6023f});
auto z = NDArrayFactory::create<float>('c', {3});
auto e = NDArrayFactory::create<float>('c', {3}, {-999.f, -0.7301f, -2.1340f});
nd4j::ops::reduce_min op;
op.execute({&x}, {&z}, {}, {1}, {});
//z.printIndexedBuffer("Z");
ASSERT_EQ(e, z);
}
TEST_F(DeclarableOpsTests14, Test_Diag_Zeros_1) {
auto x = NDArrayFactory::create<double>('c', {2}, {1, 2});
auto z = NDArrayFactory::create<double>('c', {2, 2}, {-119, -119, -119, -119});
auto exp = NDArrayFactory::create<double>('c', {2, 2}, {1, 0, 0, 2});
nd4j::ops::diag op;
auto status = op.execute({&x}, {&z}, {}, {}, {});
ASSERT_EQ(Status::OK(), status);
ASSERT_EQ(exp, z);
}
TEST_F(DeclarableOpsTests14, Test_scalar_broadcast_1) {
auto x = NDArrayFactory::create<float>(1.0f);
auto y = NDArrayFactory::create<float>('c', {5, 10});
auto e = NDArrayFactory::create<float>('c', {5, 10});
e.assign(1.0);
nd4j::ops::add op;
auto result = op.execute({&x, &y}, {}, {});
ASSERT_EQ(Status::OK(), result->status());
ASSERT_EQ(e, *result->at(0));
delete result;
}
TEST_F(DeclarableOpsTests14, Test_scalar_broadcast_2) {
auto x = NDArrayFactory::create<float>(1.0f);
auto y = NDArrayFactory::create<float>('c', {5, 10});
auto e = NDArrayFactory::create<float>('c', {5, 10});
y.assign(2.0f);
e.assign(-1.0f);
nd4j::ops::subtract op;
auto result = op.execute({&x, &y}, {}, {});
ASSERT_EQ(Status::OK(), result->status());
ASSERT_EQ(e, *result->at(0));
delete result;
}
TEST_F(DeclarableOpsTests14, test_empty_fill_1) {
auto x = NDArrayFactory::empty<int>();
auto y = NDArrayFactory::create<int>(1);
nd4j::ops::fill op;
auto result = op.execute({&x, &y}, {}, {});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
ASSERT_EQ(y, *z);
delete result;
}
TEST_F(DeclarableOpsTests14, test_lstmBlockCell_1) {
auto a = NDArrayFactory::create<float>('c', {1, 5}, {0.7787856f, 0.80119777f, 0.72437465f, 0.23089433f, 0.72714126f});
auto b = NDArrayFactory::create<float>('c', {1, 3});
auto c = NDArrayFactory::create<float>('c', {1, 3});
auto d = NDArrayFactory::create<float>('c', {8, 12}, {-0.15320599,-0.120416045,0.33126968,0.13921785,-0.32313538,-0.43956736,0.4756174,0.4335605,-0.5450856,-0.3943429,-0.28687626,0.068032146,-0.2793799,0.17298919,-0.36553562,-0.097853184,-0.2544747,-0.39872527,-0.14556861,-0.31479517,0.2559092,0.47166896,-0.31330687,0.47313118,0.5134543,-0.4678212,-0.12853557,0.26142156,0.43472284,-0.42842552,-0.1895876,0.538689,0.508651,-0.020272732,0.112327516,0.2704304,-0.046546757,0.32570732,-0.15148133,-0.19145513,0.18631572,-0.024152994,0.41603214,-0.3421499,0.0106860995,-0.2966229,-0.36713937,0.25841123,0.0843398,0.49082482,0.10800403,0.1874243,-0.26379472,-0.22531849,0.24924624,0.23119557,0.49940765,-0.051413506,0.20315129,-0.41888732,0.44097036,0.40453392,0.013338983,0.23434466,0.23942488,0.47894,-0.19898453,0.09253675,-0.032358468,-0.15213022,-0.3441009,-0.15600958,-0.08235118,0.12165731,-0.4481289,-0.4842423,-0.45797008,-0.4606034,0.08163166,-0.2981107,0.50207126,0.44195646,0.13850057,0.072246075,-0.34388685,0.030900061,0.35821778,0.47900867,0.5094063,0.23683065,0.18020362,-0.1369732,0.015235603,0.2786904,0.07954317,0.12543976});
auto e = NDArrayFactory::create<float>('c', {3});
auto f = NDArrayFactory::create<float>('c', {3});
auto g = NDArrayFactory::create<float>('c', {3});
auto h = NDArrayFactory::create<float>('c', {12});
auto z0 = NDArrayFactory::create<float>('c', {1, 3});
auto z1 = NDArrayFactory::create<float>('c', {1, 3});
auto z2 = NDArrayFactory::create<float>('c', {1, 3});
auto z3 = NDArrayFactory::create<float>('c', {1, 3});
auto z4 = NDArrayFactory::create<float>('c', {1, 3});
auto z5 = NDArrayFactory::create<float>('c', {1, 3});
auto z6 = NDArrayFactory::create<float>('c', {1, 3});
nd4j::ops::lstmBlockCell op;
auto result = op.execute({&a, &b, &c, &d, &e, &f, &g, &h}, {&z0, &z1, &z2, &z3, &z4, &z5, &z6}, {1.0, -1.0}, {0}, {});
ASSERT_EQ(Status::OK(), result);
}
TEST_F(DeclarableOpsTests14, test_empty_stack_1) {
auto x = NDArrayFactory::create<float>('c', {0});
auto e = NDArrayFactory::create<float>('c', {1, 0});
nd4j::ops::stack op;
auto result = op.execute({&x}, {}, {0});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
ASSERT_EQ(e, *z);
nd4j::ops::reduce_min sumOp;
auto res2 = sumOp.execute({&e}, {1.}, {1});
ASSERT_EQ(res2->status(), Status::OK());
auto out = res2->at(0);
out->printShapeInfo("ReduceSum empty shape with keep dims");
out->printIndexedBuffer("ReduceSum scalar");
ASSERT_EQ(out->e<float>(0), DataTypeUtils::infOrMax<float>());
delete res2;
delete result;
}
TEST_F(DeclarableOpsTests14, test_empty_stack_2) {
auto x = NDArrayFactory::empty<float>();
auto e = NDArrayFactory::create<float>('c', {0});
nd4j::ops::stack op;
auto result = op.execute({&x}, {}, {0});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
ASSERT_EQ(e, *z);
delete result;
}
TEST_F(DeclarableOpsTests14, test_empty_stack_3) {
auto x = NDArrayFactory::empty<float>();
auto e = NDArrayFactory::create<float>('c', {2, 0});
nd4j::ops::stack op;
auto result = op.execute({&x, &x}, {}, {0});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
ASSERT_EQ(e, *z);
delete result;
}
TEST_F(DeclarableOpsTests14, test_empty_stack_4) {
auto x = NDArrayFactory::create<float>('c', {0});
auto e = NDArrayFactory::create<float>('c', {2, 0});
nd4j::ops::stack op;
auto result = op.execute({&x, &x}, {}, {0});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
ASSERT_EQ(e, *z);
delete result;
}
TEST_F(DeclarableOpsTests14, test_empty_reduce_min_1) {
auto e = NDArrayFactory::create<float>('c', {1, 0});
nd4j::ops::reduce_min sumOp;
auto res2 = sumOp.execute({&e}, {1.}, {1});
ASSERT_EQ(res2->status(), Status::OK());
auto out = res2->at(0);
ASSERT_EQ(out->e<float>(0), DataTypeUtils::infOrMax<float>());
delete res2;
}
TEST_F(DeclarableOpsTests14, test_empty_reduce_max_1) {
auto e = NDArrayFactory::create<float>('c', {1, 0});
nd4j::ops::reduce_max sumOp;
auto res2 = sumOp.execute({&e}, {1.}, {1});
ASSERT_EQ(res2->status(), Status::OK());
auto out = res2->at(0);
ASSERT_EQ(out->e<float>(0), -DataTypeUtils::infOrMax<float>());
delete res2;
}
TEST_F(DeclarableOpsTests14, test_empty_reduce_sum_1) {
auto e = NDArrayFactory::create<float>('c', {1, 0});
nd4j::ops::reduce_sum sumOp;
auto res2 = sumOp.execute({&e}, {1.}, {1});
ASSERT_EQ(res2->status(), Status::OK());
auto out = res2->at(0);
ASSERT_EQ(out->e<float>(0), 0.f);
delete res2;
}
TEST_F(DeclarableOpsTests14, test_empty_reduce_mean_1) {
auto e = NDArrayFactory::create<float>('c', {1, 0});
nd4j::ops::reduce_mean sumOp;
auto res2 = sumOp.execute({&e}, {1.}, {1});
ASSERT_EQ(res2->status(), Status::OK());
auto out = res2->at(0);
// out->printShapeInfo("ReduceMean empty shape with keep dims");
// out->printIndexedBuffer("ReduceMean scalar");
ASSERT_TRUE(std::isnan(out->e<float>(0)));
delete res2;
}
TEST_F(DeclarableOpsTests14, Test_StridedSliceZeros_1) {
auto matrix = NDArrayFactory::create<double>('c', {1, 2, 0, 4});
auto b = NDArrayFactory::create<int>('c', {3}, {0, 0, 0});
auto e = NDArrayFactory::create<int>('c', {3}, {2,0,2});
auto s = NDArrayFactory::create<int>('c', {3}, {1,1,1});
auto exp = NDArrayFactory::create<double>('c', {1,0,0,4});
matrix.linspace(1);
nd4j::ops::strided_slice op;
auto result = op.execute({&matrix, &b, &e, &s}, {}, {0, 0, 0, 0, 0});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
ASSERT_TRUE(exp.isSameShape(z));
delete result;
}
TEST_F(DeclarableOpsTests14, Test_StridedSliceZeros_2) {
auto matrix = NDArrayFactory::create<double>('c', {1, 2, 0, 4});
auto b = NDArrayFactory::create<int>('c', {3}, {0, 0, 0});
auto e = NDArrayFactory::create<int>('c', {3}, {2,0,2});
auto s = NDArrayFactory::create<int>('c', {3}, {1,1,1});
auto exp = NDArrayFactory::create<double>('c', {0,0,4});
matrix.linspace(1);
nd4j::ops::strided_slice op;
auto result = op.execute({&matrix, &b, &e, &s}, {}, {0, 0, 0, 0, 1});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
ASSERT_TRUE(exp.isSameShape(z));
delete result;
}
TEST_F(DeclarableOpsTests14, test_empty_argmax_1) {
auto x = NDArrayFactory::create<float>('c', {1, 0});
auto y = NDArrayFactory::create<int>(0);
auto e = NDArrayFactory::create<Nd4jLong>('c', {0});
nd4j::ops::argmax op;
//nd4j::ops::reduce_max op;
auto result = op.execute({&x, &y}, {}, {});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
z->printShapeInfo("Z");
ASSERT_EQ(e, *z);
delete result;
}
TEST_F(DeclarableOpsTests14, test_empty_argmax_2) {
auto x = NDArrayFactory::create<float>('c', {1, 0});
auto y = NDArrayFactory::create<int>(1);
nd4j::ops::argmax op;
try {
auto result = op.execute({&x, &y}, {&y}, {}, {}, {});
ASSERT_TRUE(false);
} catch (std::exception &e) {
//
}
}
TEST_F(DeclarableOpsTests14, test_empty_tanh_5) {
auto x = NDArrayFactory::create<float>('c', {32, 0});
nd4j::ops::tanh op;
auto result = op.execute({&x}, {}, {});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
ASSERT_TRUE(x.isSameShape(z));
ASSERT_EQ(x, *z);
delete result;
}