cavis/libnd4j/tests_cpu/layers_tests/DeclarableOpsTests15.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

274 lines
10 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 DeclarableOpsTests15 : public testing::Test {
public:
DeclarableOpsTests15() {
printf("\n");
fflush(stdout);
}
};
TEST_F(DeclarableOpsTests15, Test_NormalizeMoments_1) {
auto d = NDArrayFactory::create<double>('c', {10, 10});
auto w = NDArrayFactory::create<double>(10);
auto x = NDArrayFactory::create<double>('c', {10});
auto y = NDArrayFactory::create<double>('c', {10});
auto z0 = NDArrayFactory::create<double>('c', {10});
auto z1 = NDArrayFactory::create<double>('c', {10});
nd4j::ops::normalize_moments op;
auto result = op.execute({&w, &x, &y}, {&z0, &z1}, {1e-4}, {}, {});
ASSERT_EQ(Status::OK(), result);
}
TEST_F(DeclarableOpsTests15, Test_Add_1) {
auto x = NDArrayFactory::create<int>('c', {5}, {1, 1, 1, 1, 1});
auto y = NDArrayFactory::create<int>('c', {5}, {1, 1, 1, 1, 1});
auto e = NDArrayFactory::create<int>('c', {5}, {2, 2, 2, 2, 2});
nd4j::ops::add op;
auto result = op.execute({&x, &y}, {&x}, {}, {}, {});
ASSERT_EQ(Status::OK(), result);
ASSERT_EQ(e, x);
}
TEST_F(DeclarableOpsTests15, Test_Half_assign_1) {
auto x = NDArrayFactory::create<float16>('c', {2, 5});
int y = 1;
x.assign(y);
ASSERT_EQ(10, x.sumNumber().e<int>(0));
}
TEST_F(DeclarableOpsTests15, test_avgpooling_edge_1) {
int inOutH = 35;
int inOutW = 35;
int inOutC = 192;
auto x = NDArrayFactory::create<double>('c', {1, inOutH, inOutW, inOutC});
x.linspace(1.0);
nd4j::ops::avgpool2d op;
auto result = op.execute({&x}, {}, {3,3, 1,1, 0,0, 1,1, 1, 0, 1});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
int totalPadHeight = (inOutH - 1) * 1 + 3 - inOutH;
int padTop = totalPadHeight / 2;
int padBottom = totalPadHeight - totalPadHeight / 2;
int k = 3;
auto m = NDArrayFactory::create<double>('c', {1, inOutH, inOutW, inOutC});
auto c = NDArrayFactory::create<double>('c', {1, inOutH, inOutW, inOutC});
for (int h = 0; h < inOutH; h++) {
for (int w = 0; w < inOutW; w++) {
int hFrom = h - padTop;
int wFrom = w - padBottom;
int hTo = hFrom + k;
int wTo = wFrom + k;
hFrom = nd4j::math::nd4j_max<int>(0, hFrom);
wFrom = nd4j::math::nd4j_max<int>(0, wFrom);
hTo = nd4j::math::nd4j_min<int>(inOutH, hTo);
wTo = nd4j::math::nd4j_min<int>(inOutW, wTo);
int idxOut[4];
int idxIn[4];
for (int ch = 0; ch < inOutC; ch++) {
idxOut[1] = h;
idxOut[2] = w;
idxOut[3] = ch;
idxIn[3] = ch;
for (int kh = hFrom; kh < hTo; kh++) {
for (int kw = wFrom; kw < wTo; kw++) {
idxIn[1] = kh;
idxIn[2] = kw;
auto inVal = x.e<double>(0, kh, kw, ch);
m.p(0, h, w, ch, inVal + m.e<double>(0, h, w, ch));
c.p(0, h, w, ch, 1 + c.e<int>(0, h, w, ch));
}
}
}
}
}
m /= c;
ASSERT_EQ(m, *z);
delete result;
}
TEST_F(DeclarableOpsTests15, Test_standarize_1) {
auto x = NDArrayFactory::create<float>('c', {5}, {1, 1, 1, 1, 1});
auto e = NDArrayFactory::create<float>('c', {5}, {0, 0, 0, 0, 0});
nd4j::ops::standardize op;
auto result = op.execute({&x}, {&x}, {}, {0}, {});
ASSERT_EQ(Status::OK(), result);
ASSERT_EQ(e, x);
}
TEST_F(DeclarableOpsTests15, Test_standarize_bp_1) {
auto x = NDArrayFactory::create<float>('c', {5}, {1., 1., 1., 1., 1.});
auto eps = NDArrayFactory::create<float>('c', {5}, {0., 0., 0., 0., 0.});
nd4j::ops::standardize_bp op;
auto result = op.execute({&x, &eps}, {}, {0}, {});
ASSERT_EQ(Status::OK(), result->status());
delete result;
}
TEST_F(DeclarableOpsTests15, test_matmul_bp_1) {
auto a = NDArrayFactory::create<double>('c', {1, 3});
auto b = NDArrayFactory::create<double>('c', {1, 4});
auto gI = NDArrayFactory::create<double>('c', {3, 4});
auto gA = NDArrayFactory::create<double>('c', {1, 3});
auto gB = NDArrayFactory::create<double>('c', {1, 4});
nd4j::ops::matmul_bp op;
auto status = op.execute({&a, &b, &gI}, {&gA, &gB}, {}, {1, 0, 0}, {});
ASSERT_EQ(Status::OK(), status);
}
TEST_F(DeclarableOpsTests15, test_non_decreasing_1) {
auto x = NDArrayFactory::create<double>(1.0);
auto z = NDArrayFactory::create<bool>(false);
auto e = NDArrayFactory::create<bool>(true);
nd4j::ops::is_non_decreasing op;
Context ctx(1);
ctx.setInputArray(0, &x);
ctx.setOutputArray(0, &z);
auto status = op.execute(&ctx);
ASSERT_EQ(Status::OK(), status);
ASSERT_EQ(e, z);
}
TEST_F(DeclarableOpsTests15, test_check_numeric_1) {
auto x = NDArrayFactory::create<float>('c', {3},{1.f, 2.f, 3.f});
auto y = NDArrayFactory::string("shouldn't ever trigger");
nd4j::ops::check_numerics op;
auto result = op.execute({&x, &y}, {}, {});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
ASSERT_EQ(x, *z);
delete result;
}
TEST_F(DeclarableOpsTests15, test_check_numeric_2) {
auto x = NDArrayFactory::create<float>('c', {3},{1.f, 2.f, std::numeric_limits<float>::infinity()});
auto y = NDArrayFactory::string("should trigger");
auto z = NDArrayFactory::create<float>('c', {3} );
nd4j::ops::check_numerics op;
try {
auto status = op.execute({&x, &y}, {&z}, {}, {}, {});
ASSERT_TRUE(false);
} catch (std::invalid_argument &e) {
//
}
}
TEST_F(DeclarableOpsTests15, test_check_numeric_3) {
auto x = NDArrayFactory::create<float>('c', {3},{1.f, 2.f, std::numeric_limits<float>::quiet_NaN()});
auto y = NDArrayFactory::string("should trigger");
auto z = NDArrayFactory::create<float>('c', {3} );
nd4j::ops::check_numerics op;
try {
auto status = op.execute({&x, &y}, {&z}, {}, {}, {});
ASSERT_TRUE(false);
} catch (std::invalid_argument &e) {
//
}
}
TEST_F(DeclarableOpsTests15, Test_layer_norm_1) {
auto x = NDArrayFactory::create<float>('c', {1, 5}, {1., 2., 3., 4., 5.});
auto g = NDArrayFactory::create<float>('c', {1, 5}, {1., 2., 3., 4., 5.});
auto b = NDArrayFactory::create<float>('c', {1, 5}, {1., 2., 3., 4., 5.});
nd4j::ops::layer_norm op;
auto result = op.execute({&x, &g, &b}, {}, {0}, {});
ASSERT_EQ(Status::OK(), result->status());
delete result;
}
TEST_F(DeclarableOpsTests15, Test_layer_norm_bp_1) {
auto x = NDArrayFactory::create<float>('c', {1, 5}, {1., 2., 3., 4., 5.});
auto g = NDArrayFactory::create<float>('c', {1, 5}, {1., 2., 3., 4., 5.});
auto b = NDArrayFactory::create<float>('c', {1, 5}, {1., 2., 3., 4., 5.});
auto eps = NDArrayFactory::create<float>('c', {1, 5}, {0., 0., 0., 0., 0.});
nd4j::ops::layer_norm_bp op;
auto result = op.execute({&x, &g, &b, &eps}, {}, {0}, {});
ASSERT_EQ(Status::OK(), result->status());
delete result;
}
TEST_F(DeclarableOpsTests15, test_lstmBlock_1) {
auto x0 = NDArrayFactory::create<Nd4jLong>(5);
auto x1 = NDArrayFactory::create<float>('c', {5, 1, 4}, {0.7787856f, 0.80119777f, 0.72437465f, 0.23089433f, 0.72714126f, 0.18039072f, 0.50563407f, 0.89252293f, 0.5461209f, 0.92336726f, 0.085571885f, 0.7937801f, 0.65908563f, 0.55552566f, 0.15962744f, 0.30874777f, 0.15476847f, 0.46954823f, 0.9938899f, 0.6112741f});
auto x2 = NDArrayFactory::create<float>('c', {1, 3}, {0.7717289f, 0.9280778f, 0.98455656f});
auto x3 = NDArrayFactory::create<float>('c', {1, 3}, {0.94414854f, 0.5956861f, 0.8668989f});
auto x4 = NDArrayFactory::create<float>('c', {7, 12}, {0.460692f, 0.042572856f, 0.08420354f, -0.09538093f, -0.11416581f, -0.53166187f, 0.40133476f, -0.24381405f, 0.30778718f, 0.52713746f, 0.16253126f, -0.034891903f, 0.011679292f, -0.19076681f, 0.14710993f, -0.3704369f, 0.51872355f, 0.13536876f, -0.5568739f, -0.08727971f, 0.07601875f, -0.074174374f, -0.5345982f, -0.3581748f, -0.28263924f, -0.25141674f, 0.43328637f, -0.50227314f, -0.26641843f, -0.38241976f, -0.19636461f, -0.04020852f, -0.27312332f, 0.5207915f, -0.37247592f, -0.4713087f, -0.25670746f, -0.14942765f, -0.015806139f, -0.22531253f, 0.5582536f, 0.3093416f, 0.3221351f, -0.0964683f, 0.14318448f, 0.42279094f, -0.46992f, -0.43399644f, -0.51704615f, -0.11854091f, 0.21697259f, -0.049382925f, 0.14059627f, 0.3912331f, -0.41345632f, 0.5067368f, -0.3420229f, 0.485789f, 0.044918716f, 0.26209074f, 0.12357575f, 0.21778125f, -0.53791714f, 0.18346387f, 0.054183125f, 0.5480431f, 0.03675288f, -0.26656917f, -0.018610716f, 0.19917983f, 0.5566165f, 0.43570566f, -0.35720813f, 0.31097364f, -0.47134516f, -0.289197f, 0.091138184f, 0.13300979f, -0.36592877f, -0.17540845f, 0.21732038f, 0.4393713f, 0.42800313f, 0.5006979f});
auto x5 = NDArrayFactory::create<float>('c', {1, 3});
auto x6 = NDArrayFactory::create<float>('c', {1, 3});
auto x7 = NDArrayFactory::create<float>('c', {1, 3});
auto x8 = NDArrayFactory::create<float>('c', {12});
nd4j::ops::lstmBlock op;
auto result = op.execute({&x0, &x1, &x2, &x3, &x4, &x5, &x6, &x7, &x8}, {2.0, 0.3}, {0, 0});
ASSERT_EQ(Status::OK(), result->status());
auto z = result->at(0);
z->printIndexedBuffer("Z");
delete result;
}