Yurii Shyrma 5d9b2a16e5 Shyrma temp (#131)
* - specifying template instantiation for certain types in float16 and bloat16

Signed-off-by: Yurii <iuriish@yahoo.com>

* - polishing bfloat16 and float16 member functions template specialization

Signed-off-by: Yurii <iuriish@yahoo.com>

* - rewrite and overload array +-*/ scalar and scalar +-*/ arr in NDAray class

Signed-off-by: Yurii <iuriish@yahoo.com>

* - make corrections which have to do with and rvalue lvalue conversions

Signed-off-by: Yurii <iuriish@yahoo.com>

* - provide move semantic in NDArray operators array +-/* array

Signed-off-by: Yurii <iuriish@yahoo.com>

* float16/bfloat16 tweaks

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

* one more tweak

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

* - make float16 and bfloat16 to compile successfully on cuda

Signed-off-by: Yurii <iuriish@yahoo.com>

* - do not use resources of view-like arrays when move semantics is applied

Signed-off-by: Yurii <iuriish@yahoo.com>

* - get rid of pointers in signatures NDArray methods 1

Signed-off-by: Yurii <iuriish@yahoo.com>

* - correction of signature of NDArray::dup method

Signed-off-by: Yurii <iuriish@yahoo.com>

* - correction of signature of NDArray::reduceAlongDimension method

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::applyIndexReduce and applyTrueBroadcast methods

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::applyReduce3 and varianceAlongDimension methods

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::tensorsAlongDimension and diagonal methods

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::allTensorsAlongDimension

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::reduceAlongDimension 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::applyTransform 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::applyPairwiseTransform 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::applyBroadcast 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::applyTrueBroadcast 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::applyScalar and applyScalarArr

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::lambda methods

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::reduce3 methods 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of following NDArray methods: add/sub/mul/div row/column and fillAsTriangular

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::tileToShape methods

Signed-off-by: Yurii <iuriish@yahoo.com>

* - signature correction of NDArray::isShapeSameStrict method

Signed-off-by: Yurii <iuriish@yahoo.com>

* minor corrections in tests

Signed-off-by: Yurii <iuriish@yahoo.com>

* - replace reduce op in batchnorm mkldnn

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add explicit templates instantiations for operator+(NDArray&&. const scalar)

Signed-off-by: Yurii <iuriish@yahoo.com>

* - corrections of casts in float16/bfloat16

Signed-off-by: Yurii <iuriish@yahoo.com>

* - provide move semantics in following NDArray methods: transform, applyTrueBroadcast, transpose, reshape, permute

Signed-off-by: Yurii <iuriish@yahoo.com>

* - get rid of input array A duplicate in svd cuda op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - avoid available bug in svd cuda API

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add temporary global memory buffer in svd cuda when calcUV = false and  m != n

Signed-off-by: Yurii <iuriish@yahoo.com>

* - remove test with blfoat16 type for betainC

Signed-off-by: Yurii <iuriish@yahoo.com>

* - resolve conflicts after master has been merged in

Signed-off-by: Yurii <iuriish@yahoo.com>

* - changed type of affected input array in fused_batch_norm

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add several explicit type castings

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add ND4J_EXPORT to operators

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add explicit template types in instantiations of template arithm operators of NDArray class

Signed-off-by: Yurii <iuriish@yahoo.com>

* - one more test fix

Signed-off-by: Yurii <iuriish@yahoo.com>

Co-authored-by: raver119 <raver119@gmail.com>
2019-12-20 22:35:39 +03:00

118 lines
4.4 KiB
C++

/*******************************************************************************
* Copyright (c) 2015-2018 Skymind, Inc.
*
* This program and the accompanying materials are made available under the
* terms of the Apache License, Version 2.0 which is available at
* https://www.apache.org/licenses/LICENSE-2.0.
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
* WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
* License for the specific language governing permissions and limitations
* under the License.
*
* SPDX-License-Identifier: Apache-2.0
******************************************************************************/
//
// @author Yurii Shyrma (iuriish@yahoo.com)
//
#ifndef LIBND4J_LSTMLAYER_H
#define LIBND4J_LSTMLAYER_H
#include <ops/declarable/helpers/helpers.h>
#include <ops/declarable/helpers/activations.h>
namespace nd4j {
namespace ops {
namespace helpers {
//////////////////////////////////////////////////////////////////////////
void ND4J_EXPORT lstmLayerCell(const NDArray* x, const NDArray* Wx, const NDArray* Wr,
const NDArray* b, const NDArray* hI, const NDArray* cI, const NDArray* Wp,
const std::vector<float>& params,
NDArray* h, NDArray* c);
//////////////////////////////////////////////////////////////////////////
void ND4J_EXPORT lstmLayerTimeLoop(const NDArray* x, const NDArray* Wx, const NDArray* Wr,
const NDArray* b, const NDArray* seqLen, const NDArray* hI, const NDArray* cI, const NDArray* Wp,
const std::vector<float>& params,
const bool forward,
NDArray* h, NDArray* hL, NDArray* cL);
//////////////////////////////////////////////////////////////////////////
static FORCEINLINE void applyActivation(NDArray& x, const int opId, const float alpha, const float beta, NDArray& z) {
switch (opId) {
case 0:
(const_cast<NDArray&>(x)).applyTransform(transform::Tanh, z);
break;
case 1:
(const_cast<NDArray&>(x)).applyScalar<float>(scalar::RELU, 0, z);
break;
case 2:
(const_cast<NDArray&>(x)).applyTransform(transform::Sigmoid, z);
break;
case 3: {
ExtraArguments args({ static_cast<double>(alpha), static_cast<double>(beta)});
(const_cast<NDArray&>(x)).applyTransform(transform::Affine, z, &args);
break;
}
case 4:
(const_cast<NDArray&>(x)).applyScalar<float>(scalar::LeakyRELU, alpha, z);
break;
case 5:
helpers::thresholdRelu(x.getContext(), x, alpha, z);
break;
case 6: {
ExtraArguments args({ static_cast<double>(alpha), static_cast<double>(beta)});
(const_cast<NDArray&>(x)).applyTransform(transform::ScaledTanh, z, &args);
break;
}
case 7:
(const_cast<NDArray&>(x)).applyTransform(transform::HardSigmoid, z);
break;
case 8:
(const_cast<NDArray&>(x)).applyScalar<float>(scalar::ELU, alpha, z);
break;
case 9:
(const_cast<NDArray&>(x)).applyTransform(transform::SoftSign, z);
break;
case 10:
(const_cast<NDArray&>(x)).applyTransform(transform::SoftPlus, z);
break;
default:
throw std::invalid_argument("LSTM_LAYER operation: wrong id number of activation !");
}
}
//////////////////////////////////////////////////////////////////////////
static FORCEINLINE NDArray tensorAlongTimeBatchDims(const NDArray& arr, const int dataFormat, const int t1, const int t2, const int b1, const int b2) {
if(dataFormat == 0 || dataFormat == 3)
return arr({t1,t2, b1,b2, 0,0}); // TNS: [sL, bS, nIn]
if(dataFormat == 1)
return arr({b1,b2, t1,t2, 0,0}); // NTS: [bS, sL ,nIn]
return arr({b1,b2, 0,0, t1,t2}); // NST: [bS, nIn, sL]
}
//////////////////////////////////////////////////////////////////////////
static FORCEINLINE int getBatchTimeTotalIndex(const int dataFormat, const int sL, const int bS, const int t, const int b) {
if(dataFormat == 0 || dataFormat == 3)
return t * bS + b; // TNS: shape [sL, bS, nIn]
return b * sL + t; // NTS, NST: shape [bS, sL, nIn], [bS, nIn, sL]
}
}
}
}
#endif //LIBND4J_LSTMLAYER_H