p60975123
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!15694 slice like ops and transpose support higher dimensions 

From: @zhaozhenlong
Reviewed-by: @zhanghaibo5,@zhang_xue_tong
Signed-off-by: @zhang_xue_tong
This commit is contained in:
mindspore-ci-bot 2021-04-27 11:25:15 +08:00 committed by Gitee
parent 972577b31b 3fa19d4764
commit 5b97697b3f
9 changed files with 530 additions and 159 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

113
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/base/slice_base.c
View File

@ -15,11 +15,11 @@
*/
#include "nnacl/base/slice_base.h"
#include <string.h>
void PadSliceParameterTo4D(SliceParameter *param) {
int32_t begin[DIMENSION_4D];
int32_t end[DIMENSION_4D];
int32_t slice_size[DIMENSION_4D];
int32_t data_shape[DIMENSION_4D];
void PadSliceParameterTo8D(SliceParameter *param) {
int32_t begin[DIMENSION_8D];
int32_t end[DIMENSION_8D];
int32_t slice_size[DIMENSION_8D];
int32_t data_shape[DIMENSION_8D];
for (int32_t i = 0; i < param->param_length_; ++i) {
begin[i] = param->begin_[i];
end[i] = param->end_[i];
@ -27,7 +27,7 @@ void PadSliceParameterTo4D(SliceParameter *param) {
data_shape[i] = param->shape_[i];
}
int32_t real_index = param->param_length_ - 1;
for (int32_t i = DIMENSION_4D - 1; i >= 0; --i) {
for (int32_t i = DIMENSION_8D - 1; i >= 0; --i) {
if (real_index >= 0) {
param->begin_[i] = begin[real_index];
param->end_[i] = end[real_index];
@ -40,39 +40,55 @@ void PadSliceParameterTo4D(SliceParameter *param) {
param->shape_[i] = 1;
}
}
param->param_length_ = DIMENSION_4D;
param->param_length_ = DIMENSION_8D;
}
void DoSlice(const void *input, void *output, SliceParameter *param, int thread_id, int data_size) {
int8_t *int8_in = (int8_t *)input;
int8_t *int8_out = (int8_t *)output;
int32_t out_dim1 = param->size_[1];
int32_t out_dim2 = param->size_[2];
int32_t out_dim3 = param->size_[3];
size_t out_stride2 = out_dim3;
size_t out_stride1 = out_stride2 * out_dim2;
size_t out_stride0 = out_stride1 * out_dim1;
size_t count_per_thread = UP_DIV(out_dim1, param->op_parameter_.thread_num_);
size_t thread_stride = thread_id * count_per_thread;
size_t copy_size = param->size_[3] * data_size;
size_t in_stride2 = param->shape_[3];
size_t in_stride1 = param->shape_[2] * in_stride2;
size_t in_stride0 = param->shape_[1] * in_stride1;
for (int i = 0; i < param->size_[0]; ++i) {
size_t out_offset0 = i * out_stride0;
size_t in_offset0 = (i + param->begin_[0]) * in_stride0 + param->begin_[3];
for (size_t j = 0; j < count_per_thread; ++j) {
size_t k = j + thread_stride;
if (k >= out_dim1) {
break;
size_t out_stride[8];
out_stride[7] = 1;
for (int i = 6; i >= 0; --i) {
out_stride[i] = out_stride[i + 1] * param->size_[i + 1];
}
size_t count_per_thread = UP_DIV(param->size_[5], param->op_parameter_.thread_num_);
size_t thread_begin = thread_id * count_per_thread;
size_t thread_end = MSMIN(param->size_[5], thread_begin + count_per_thread);
size_t copy_size = param->size_[7] * data_size;
size_t in_stride[8];
in_stride[7] = 1;
for (int i = 6; i >= 0; --i) {
in_stride[i] = param->shape_[i + 1] * in_stride[i + 1];
}
for (int ii = 0; ii < param->size_[0]; ++ii) {
size_t out_offset0 = ii * out_stride[0];
size_t in_offset0 = (ii + param->begin_[0]) * in_stride[0] + param->begin_[7];
for (int jj = 0; jj < param->size_[1]; ++jj) {
size_t out_offset1 = jj * out_stride[1] + out_offset0;
size_t in_offset1 = (jj + param->begin_[1]) * in_stride[1] + in_offset0;
for (int kk = 0; kk < param->size_[2]; ++kk) {
size_t out_offset2 = kk * out_stride[2] + out_offset1;
size_t in_offset2 = (kk + param->begin_[2]) * in_stride[2] + in_offset1;
for (int ll = 0; ll < param->size_[3]; ++ll) {
size_t out_offset3 = ll * out_stride[3] + out_offset2;
size_t in_offset3 = (ll + param->begin_[3]) * in_stride[3] + in_offset2;
for (int i = 0; i < param->size_[4]; ++i) {
size_t out_offset4 = i * out_stride[4] + out_offset3;
size_t in_offset4 = (i + param->begin_[4]) * in_stride[4] + in_offset3;
for (size_t j = thread_begin; j < thread_end; ++j) {
size_t out_offset5 = j * out_stride[5] + out_offset4;
size_t in_offset5 = (j + param->begin_[5]) * in_stride[5] + in_offset4;
for (int k = 0; k < param->size_[6]; ++k) {
size_t out_offset6 = k * out_stride[6] + out_offset5;
size_t in_offset6 = (k + param->begin_[6]) * in_stride[6] + in_offset5;
memcpy(int8_out + out_offset6 * data_size, int8_in + in_offset6 * data_size, copy_size);
}
}
}
}
size_t out_offset1 = k * out_stride1 + out_offset0;
size_t in_offset1 = (k + param->begin_[1]) * in_stride1 + in_offset0;
for (int l = 0; l < out_dim2; ++l) {
size_t out_offset = out_offset1 + l * out_stride2;
size_t in_offset = in_offset1 + (l + param->begin_[2]) * in_stride2;
memcpy(int8_out + out_offset * data_size, int8_in + in_offset * data_size, copy_size);
}
}
}
@ -82,19 +98,34 @@ void DoSliceNoParallel(const void *input, void *output, SliceParameter *param, i
int8_t *int8_in = (int8_t *)input;
int8_t *int8_out = (int8_t *)output;
size_t copy_size = param->size_[3] * data_size;
size_t in_stride2 = param->shape_[3];
size_t in_stride1 = param->shape_[2] * in_stride2;
size_t in_stride0 = param->shape_[1] * in_stride1;
size_t copy_size = param->size_[7] * data_size;
size_t in_stride[8];
in_stride[7] = 1;
for (int i = 6; i >= 0; --i) {
in_stride[i] = param->shape_[i + 1] * in_stride[i + 1];
}
size_t out_offset = 0;
for (int32_t dim0 = param->begin_[0]; dim0 < param->end_[0]; ++dim0) {
size_t in_offset0 = dim0 * in_stride0 + param->begin_[3];
size_t in_offset0 = dim0 * in_stride[0] + param->begin_[7];
for (size_t dim1 = param->begin_[1]; dim1 < param->end_[1]; ++dim1) {
size_t in_offset1 = dim1 * in_stride1 + in_offset0;
size_t in_offset1 = dim1 * in_stride[1] + in_offset0;
for (int32_t dim2 = param->begin_[2]; dim2 < param->end_[2]; ++dim2) {
size_t in_offset = in_offset1 + dim2 * in_stride2;
memcpy(int8_out + out_offset * data_size, int8_in + in_offset * data_size, copy_size);
out_offset += param->size_[3];
size_t in_offset2 = in_offset1 + dim2 * in_stride[2];
for (int32_t dim3 = param->begin_[3]; dim3 < param->end_[3]; ++dim3) {
size_t in_offset3 = in_offset2 + dim3 * in_stride[3];
for (int32_t dim4 = param->begin_[4]; dim4 < param->end_[4]; ++dim4) {
size_t in_offset4 = in_offset3 + dim4 * in_stride[4];
for (int32_t dim5 = param->begin_[5]; dim5 < param->end_[5]; ++dim5) {
size_t in_offset5 = in_offset4 + dim5 * in_stride[5];
for (int32_t dim6 = param->begin_[6]; dim6 < param->end_[6]; ++dim6) {
size_t in_offset6 = in_offset5 + dim6 * in_stride[6];
memcpy(int8_out + out_offset * data_size, int8_in + in_offset6 * data_size, copy_size);
out_offset += param->size_[7];
}
}
}
}
}
}
}

2
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/base/slice_base.h
View File

@ -23,7 +23,7 @@
#ifdef __cplusplus
extern "C" {
#endif
void PadSliceParameterTo4D(SliceParameter *param);
void PadSliceParameterTo8D(SliceParameter *param);
void DoSlice(const void *input, void *output, SliceParameter *param, int thread_id, int data_size);
void DoSliceNoParallel(const void *input, void *output, SliceParameter *param, int data_size);

125
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/int8/slice_int8.c
View File

@ -16,104 +16,77 @@
#include "nnacl/int8/slice_int8.h"
int SliceInt8NoParallel(const int8_t *input, int8_t *output, SliceParameter *param) {
double input_scale = param->quant_arg_.in_args_.scale_;
int input_zp = param->quant_arg_.in_args_.zp_;
double output_scale = param->quant_arg_.out_args_.scale_;
int output_zp = param->quant_arg_.out_args_.zp_;
int act_min = param->quant_arg_.output_activation_min_;
int act_max = param->quant_arg_.output_activation_max_;
int equal_quant = 0;
double multiplier = input_scale / output_scale;
if (input_scale == output_scale && input_zp == output_zp) {
equal_quant = 1;
}
int32_t end_n = param->begin_[0] + param->size_[0];
int32_t end_h = param->begin_[1] + param->size_[1];
int32_t end_w = param->begin_[2] + param->size_[2];
int unit_count = param->size_[3];
int unit_size = unit_count * sizeof(int8_t);
int in_stride2 = param->shape_[3];
int in_stride1 = param->shape_[2] * in_stride2;
int in_stride0 = param->shape_[1] * in_stride1;
int out_offset = 0;
int n, h, w, c;
for (n = param->begin_[0]; n < end_n; ++n) {
size_t in_offset0 = n * in_stride0;
for (h = param->begin_[1]; h < end_h; ++h) {
size_t in_offset1 = h * in_stride1 + in_offset0;
for (w = param->begin_[2]; w < end_w; ++w) {
size_t in_offset = in_offset1 + w * in_stride2;
if (equal_quant == 1) {
memcpy(output + out_offset, input + in_offset, unit_size);
} else {
for (c = 0; c < unit_count; ++c) {
int32_t output_val = round(multiplier * (input[in_offset + c] - input_zp)) + output_zp;
output[c + out_offset] = (int8_t)MSMAX(act_min, MSMIN(output_val, act_max));
}
}
out_offset += unit_count;
}
}
}
return 0;
}
int SliceInt8(const int8_t *input, int8_t *output, SliceParameter *param, int thread_id) {
double input_scale = param->quant_arg_.in_args_.scale_;
int input_zp = param->quant_arg_.in_args_.zp_;
double output_scale = param->quant_arg_.out_args_.scale_;
int output_zp = param->quant_arg_.out_args_.zp_;
const int base_offset = 20;
int act_min = param->quant_arg_.output_activation_min_;
int act_max = param->quant_arg_.output_activation_max_;
int32_t out_dim1 = param->size_[1];
int32_t out_dim2 = param->size_[2];
int32_t out_dim3 = param->size_[3];
int out_stride2 = out_dim3;
int out_stride1 = out_stride2 * out_dim2;
int out_stride0 = out_stride1 * out_dim1;
int count_per_thread = UP_DIV(out_dim1, param->op_parameter_.thread_num_);
int thread_stride = thread_id * count_per_thread;
int unit_size = param->size_[3] * sizeof(int8_t);
int in_stride2 = param->shape_[3];
int in_stride1 = param->shape_[2] * in_stride2;
int in_stride0 = param->shape_[1] * in_stride1;
int n, h, w, c;
size_t out_stride[8];
out_stride[7] = 1;
for (int i = 6; i >= 0; --i) {
out_stride[i] = out_stride[i + 1] * param->size_[i + 1];
}
int count_per_thread = UP_DIV(param->size_[5], param->op_parameter_.thread_num_);
size_t thread_begin = thread_id * count_per_thread;
size_t thread_end = MSMIN(param->size_[5], thread_begin + count_per_thread);
int unit_size = param->size_[7] * sizeof(int8_t);
size_t in_stride[8];
in_stride[7] = 1;
for (int i = 6; i >= 0; --i) {
in_stride[i] = param->shape_[i + 1] * in_stride[i + 1];
}
int i, j, k, l, n, h, w, c;
int equal_quant = 0;
double multiplier = input_scale / output_scale;
if (input_scale == output_scale && input_zp == output_zp) {
equal_quant = 1;
}
for (n = 0; n < param->size_[0]; ++n) {
size_t out_offset0 = n * out_stride0;
size_t in_offset0 = (n + param->begin_[0]) * in_stride0 + param->begin_[3];
for (h = 0; h < count_per_thread; ++h) {
size_t k = h + thread_stride;
if (k >= out_dim1) {
break;
}
size_t out_offset1 = k * out_stride1 + out_offset0;
size_t in_offset1 = (k + param->begin_[1]) * in_stride1 + in_offset0;
for (w = 0; w < out_dim2; ++w) {
size_t out_offset = out_offset1 + w * out_stride2;
size_t in_offset = in_offset1 + (w + param->begin_[2]) * in_stride2;
for (i = 0; i < param->size_[0]; ++i) {
size_t out_offset0 = i * out_stride[0];
size_t in_offset0 = (i + param->begin_[0]) * in_stride[0] + param->begin_[7];
for (j = 0; j < param->size_[1]; ++j) {
size_t out_offset1 = j * out_stride[1] + out_offset0;
size_t in_offset1 = (j + param->begin_[1]) * in_stride[1] + in_offset0;
for (k = 0; k < param->size_[2]; ++k) {
size_t out_offset2 = k * out_stride[2] + out_offset1;
size_t in_offset2 = (k + param->begin_[2]) * in_stride[2] + in_offset1;
for (l = 0; l < param->size_[3]; ++l) {
size_t out_offset3 = l * out_stride[3] + out_offset2;
size_t in_offset3 = (l + param->begin_[3]) * in_stride[3] + in_offset2;
for (n = 0; n < param->size_[4]; ++n) {
size_t out_offset4 = n * out_stride[4] + out_offset3;
size_t in_offset4 = (n + param->begin_[4]) * in_stride[4] + in_offset3;
for (h = thread_begin; h < thread_end; ++h) {
size_t out_offset5 = h * out_stride[5] + out_offset4;
size_t in_offset5 = (h + param->begin_[5]) * in_stride[5] + in_offset4;
for (w = 0; w < param->size_[6]; ++w) {
size_t out_offset = w * out_stride[6] + out_offset5;
size_t in_offset = (w + param->begin_[6]) * in_stride[6] + in_offset5;
if (equal_quant == 1) {
memcpy(output + out_offset, input + in_offset, unit_size);
} else {
for (c = 0; c < out_dim3; ++c) {
int32_t output_val = round(multiplier * (input[in_offset + c] - input_zp)) + output_zp;
for (c = 0; c < param->size_[7]; ++c) {
int32_t output_val = MultiplyByQuantizedMultiplier(
input[in_offset + c] - input_zp, param->quant_arg_.multiplier_.multiplier_,
param->quant_arg_.multiplier_.left_shift_ + base_offset,
param->quant_arg_.multiplier_.right_shift_ - base_offset) +
output_zp;
output_val = MSMAX(INT8_MIN, MSMIN(output_val, INT8_MAX));
output[c + out_offset] = (int8_t)MSMAX(act_min, MSMIN(output_val, act_max));
}
}
}
}
}
}
}
}
}
return 0;
}

2
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/int8/slice_int8.h
View File

@ -25,7 +25,7 @@
#ifdef __cplusplus
extern "C" {
#endif
int SliceInt8NoParallel(const int8_t *input, int8_t *output, SliceParameter *param);
int SliceInt8NoParallel(const int8_t *input, int8_t *output, SliceParameter *param, const QuantMulArg *multiplier);
int SliceInt8(const int8_t *input, int8_t *output, SliceParameter *param, int thread_id);
#ifdef __cplusplus
}

1
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/op_base.h
View File

@ -49,6 +49,7 @@
#define DIMENSION_4D 4
#define DIMENSION_6D 6
#define DIMENSION_7D 7
#define DIMENSION_8D 8
#define kInputIndex 0
#define kWeightIndex 1
#define kBiasIndex 2

11
mindspore/ccsrc/backend/kernel_compiler/cpu/nnacl/slice_parameter.h
View File

@ -24,6 +24,7 @@ typedef struct SliceQuantArg {
QuantArg out_args_;
int output_activation_min_;
int output_activation_max_;
QuantMulArg multiplier_;
} SliceQuantArg;
typedef struct SliceParameter {
@ -31,11 +32,11 @@ typedef struct SliceParameter {
OpParameter op_parameter_;
// shape correlative
int32_t shape_[COMM_SHAPE_SIZE];
int32_t begin_[COMM_SHAPE_SIZE];
int32_t end_[COMM_SHAPE_SIZE];
int32_t size_[COMM_SHAPE_SIZE];
int32_t axis_[COMM_SHAPE_SIZE];
int32_t shape_[DIMENSION_8D];
int32_t begin_[DIMENSION_8D];
int32_t end_[DIMENSION_8D];
int32_t size_[DIMENSION_8D];
int32_t axis_[DIMENSION_8D];
// other parameter
SliceQuantArg quant_arg_;

13
mindspore/lite/src/runtime/kernel/arm/base/slice_base.cc
View File

@ -40,14 +40,14 @@ int SliceCPUKernel::ReSize() {
MS_ASSERT(in_tensor->shape().size() == begin_tensor->ElementsNum());
MS_ASSERT(in_tensor->shape().size() == size_tensor->ElementsNum());
MS_ASSERT(in_tensor->shape().size() <= DIMENSION_4D);
MS_ASSERT(in_tensor->shape().size() <= DIMENSION_8D);
auto begin = reinterpret_cast<int32_t *>(begin_tensor->data_c());
auto size = reinterpret_cast<int32_t *>(size_tensor->data_c());
param_->param_length_ = in_tensor->shape().size();
if (param_->param_length_ > DIMENSION_4D) {
MS_LOG(ERROR) << "input dimension num should <= " << DIMENSION_4D;
if (param_->param_length_ > DIMENSION_8D) {
MS_LOG(ERROR) << "input dimension num should <= " << DIMENSION_8D;
return RET_ERROR;
}
for (int i = 0; i < param_->param_length_; ++i) {
@ -56,8 +56,8 @@ int SliceCPUKernel::ReSize() {
param_->size_[i] = size[i] < 0 ? param_->shape_[i] - param_->begin_[i] : size[i];
param_->end_[i] = param_->begin_[i] + param_->size_[i];
}
if (param_->param_length_ < DIMENSION_4D) {
PadSliceParameterTo4D(param_);
if (param_->param_length_ < DIMENSION_8D) {
PadSliceParameterTo8D(param_);
}
return RET_OK;
}
@ -76,7 +76,8 @@ int SliceCPUKernel::SliceParallelRun(int thread_id) {
}
int SliceCPUKernel::Run() {
if (param_->size_[1] < op_parameter_->thread_num_) {
// param_ shape info has already been extended to 8d
if (param_->size_[5] < op_parameter_->thread_num_) {
DoSliceNoParallel(in_tensors_.at(0)->data_c(), out_tensors_.at(0)->data_c(), param_,
lite::DataTypeSize(in_tensors_.at(0)->data_type()));
return RET_OK;

21
mindspore/lite/src/runtime/kernel/arm/int8/slice_int8.cc
View File

@ -42,6 +42,11 @@ int SliceInt8CPUKernel::Init() {
param_->quant_arg_.out_args_.scale_ = out_quant_args.front().scale;
param_->quant_arg_.out_args_.zp_ = out_quant_args.front().zeroPoint;
QuantizeRoundParameterWithDoublePrecision(param_->quant_arg_.in_args_.scale_ / param_->quant_arg_.out_args_.scale_,
&param_->quant_arg_.multiplier_.multiplier_,
&param_->quant_arg_.multiplier_.left_shift_,
&param_->quant_arg_.multiplier_.right_shift_);
param_->quant_arg_.output_activation_max_ = std::numeric_limits<int8_t>::max();
param_->quant_arg_.output_activation_min_ = std::numeric_limits<int8_t>::min();
if (!InferShapeDone()) {
@ -51,9 +56,9 @@ int SliceInt8CPUKernel::Init() {
}
int SliceInt8CPUKernel::DoSlice(int task_id) {
const int8_t *input_data = reinterpret_cast<const int8_t *>(in_tensors_.at(0)->MutableData());
const int8_t *input_data = reinterpret_cast<const int8_t *>(in_tensors_.at(0)->data_c());
MS_ASSERT(input_data);
int8_t *output_data = reinterpret_cast<int8_t *>(out_tensors_.at(0)->MutableData());
int8_t *output_data = reinterpret_cast<int8_t *>(out_tensors_.at(0)->data_c());
MS_ASSERT(output_data);
auto ret = SliceInt8(input_data, output_data, param_, task_id);
@ -73,17 +78,9 @@ int SliceInt8Run(void *cdata, int task_id) {
}
int SliceInt8CPUKernel::Run() {
const int8_t *input_data = reinterpret_cast<const int8_t *>(in_tensors_.at(0)->MutableData());
MS_ASSERT(input_data);
int8_t *output_data = reinterpret_cast<int8_t *>(out_tensors_.at(0)->MutableData());
MS_ASSERT(output_data);
mindspore::lite::STATUS ret = RET_ERROR;
if (param_->size_[1] < param_->op_parameter_.thread_num_) {
ret = SliceInt8NoParallel(input_data, output_data, param_);
} else {
ret = ParallelLaunch(static_cast<const lite::InnerContext *>(this->context_)->thread_pool_, SliceInt8Run, this,
// param_ shape info has already been extended to 8d
auto ret = ParallelLaunch(static_cast<const lite::InnerContext *>(this->context_)->thread_pool_, SliceInt8Run, this,
op_parameter_->thread_num_);
}
if (ret != RET_OK) {
MS_LOG(ERROR) << "SliceInt8Run error, error_code[" << ret << "]";

389
mindspore/lite/test/ut/src/runtime/kernel/arm/int8/slice_int8_tests.cc
View File

@ -30,29 +30,29 @@ class TestSliceInt8 : public mindspore::CommonTest {
TEST_F(TestSliceInt8, SliceInt8) {
lite::Tensor in_tensor(kNumberTypeInt8, {1, 3, 2, 3});
lite::Tensor out_tensor(kNumberTypeInt8, {1, 1, 2, 3});
lite::Tensor out_tensor(kNumberTypeInt8, {1, 2, 2, 3});
int8_t input_data[] = {105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68};
int8_t output_data[12];
in_tensor.set_data(input_data);
out_tensor.set_data(output_data);
lite::Tensor begin_tensor(kNumberTypeInt32, {4});
int begin_data[4] = {0, 1, 0, 0};
begin_tensor.set_data(begin_data);
lite::Tensor size_tensor(kNumberTypeInt32, {4});
int size_data[4] = {1, 2, 2, 3};
size_tensor.set_data(size_data);
const lite::QuantArg quant_in0 = {0.00784314f, 0}; // -1.0--1.0 -> 0--255
const lite::QuantArg quant_out = {0.00784314f, 0};
in_tensor.AddQuantParam(quant_in0);
out_tensor.AddQuantParam(quant_out);
std::vector<lite::Tensor *> inputs = {&in_tensor};
std::vector<lite::Tensor *> inputs = {&in_tensor, &begin_tensor, &size_tensor};
std::vector<lite::Tensor *> outputs = {&out_tensor};
SliceParameter parameter;
parameter.begin_[0] = 1;
parameter.begin_[1] = 0;
parameter.begin_[2] = 0;
parameter.size_[0] = -1;
parameter.size_[1] = -1;
parameter.size_[2] = -1;
parameter.param_length_ = 3;
SliceParameter *parameter = new (std::nothrow) SliceParameter;
parameter->op_parameter_.infer_flag_ = true;
kernel::KernelKey desc = {kernel::KERNEL_ARCH::kCPU, kNumberTypeInt8, schema::PrimitiveType_SliceFusion};
@ -61,7 +61,58 @@ TEST_F(TestSliceInt8, SliceInt8) {
auto ctx = std::make_shared<lite::InnerContext>();
ASSERT_EQ(lite::RET_OK, ctx->Init());
auto kernel = creator(inputs, outputs, reinterpret_cast<OpParameter *>(&parameter), ctx.get(), desc);
auto kernel = creator(inputs, outputs, reinterpret_cast<OpParameter *>(parameter), ctx.get(), desc);
ASSERT_NE(kernel, nullptr);
auto ret = kernel->Run();
EXPECT_EQ(0, ret);
int8_t expect0[12] = {16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68};
for (int i = 0; i < 12; ++i) {
EXPECT_EQ(output_data[i], expect0[i]);
}
in_tensor.set_data(nullptr);
begin_tensor.set_data(nullptr);
size_tensor.set_data(nullptr);
out_tensor.set_data(nullptr);
delete kernel;
}
TEST_F(TestSliceInt8, Slice5D) {
lite::Tensor in_tensor(kNumberTypeInt8, {2, 1, 3, 2, 3});
lite::Tensor out_tensor(kNumberTypeInt8, {1, 1, 2, 2, 3});
int8_t input_data[] = {105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68,
105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68};
int8_t output_data[12];
in_tensor.set_data(input_data);
out_tensor.set_data(output_data);
lite::Tensor begin_tensor(kNumberTypeInt32, {5});
int begin_data[5] = {0, 0, 1, 0, 0};
begin_tensor.set_data(begin_data);
lite::Tensor size_tensor(kNumberTypeInt32, {5});
int size_data[5] = {1, 1, 2, 2, 3};
size_tensor.set_data(size_data);
const lite::QuantArg quant_in0 = {0.00784314f, 0}; // -1.0--1.0 -> 0--255
const lite::QuantArg quant_out = {0.00784314f, 0};
in_tensor.AddQuantParam(quant_in0);
out_tensor.AddQuantParam(quant_out);
std::vector<lite::Tensor *> inputs = {&in_tensor, &begin_tensor, &size_tensor};
std::vector<lite::Tensor *> outputs = {&out_tensor};
SliceParameter *parameter = new (std::nothrow) SliceParameter;
parameter->op_parameter_.infer_flag_ = true;
kernel::KernelKey desc = {kernel::KERNEL_ARCH::kCPU, kNumberTypeInt8, schema::PrimitiveType_SliceFusion};
auto creator = lite::KernelRegistry::GetInstance()->GetCreator(desc);
ASSERT_NE(creator, nullptr);
auto ctx = std::make_shared<lite::InnerContext>();
ASSERT_EQ(lite::RET_OK, ctx->Init());
auto kernel = creator(inputs, outputs, reinterpret_cast<OpParameter *>(parameter), ctx.get(), desc);
ASSERT_NE(kernel, nullptr);
auto ret = kernel->Run();
EXPECT_EQ(0, ret);
@ -73,5 +124,321 @@ TEST_F(TestSliceInt8, SliceInt8) {
in_tensor.set_data(nullptr);
out_tensor.set_data(nullptr);
begin_tensor.set_data(nullptr);
size_tensor.set_data(nullptr);
delete kernel;
}
TEST_F(TestSliceInt8, Slice6D) {
lite::Tensor in_tensor(kNumberTypeInt8, {2, 1, 1, 3, 2, 3});
lite::Tensor out_tensor(kNumberTypeInt8, {1, 1, 1, 2, 2, 3});
int8_t input_data[] = {105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68,
105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68};
int8_t output_data[12];
in_tensor.set_data(input_data);
out_tensor.set_data(output_data);
lite::Tensor begin_tensor(kNumberTypeInt32, {6});
int begin_data[6] = {0, 0, 0, 1, 0, 0};
begin_tensor.set_data(begin_data);
lite::Tensor size_tensor(kNumberTypeInt32, {6});
int size_data[6] = {1, 1, 1, 2, 2, 3};
size_tensor.set_data(size_data);
const lite::QuantArg quant_in0 = {0.00784314f, 0}; // -1.0--1.0 -> 0--255
const lite::QuantArg quant_out = {0.00784314f, 0};
in_tensor.AddQuantParam(quant_in0);
out_tensor.AddQuantParam(quant_out);
std::vector<lite::Tensor *> inputs = {&in_tensor, &begin_tensor, &size_tensor};
std::vector<lite::Tensor *> outputs = {&out_tensor};
SliceParameter *parameter = new (std::nothrow) SliceParameter;
parameter->op_parameter_.infer_flag_ = true;
kernel::KernelKey desc = {kernel::KERNEL_ARCH::kCPU, kNumberTypeInt8, schema::PrimitiveType_SliceFusion};
auto creator = lite::KernelRegistry::GetInstance()->GetCreator(desc);
ASSERT_NE(creator, nullptr);
auto ctx = std::make_shared<lite::InnerContext>();
ASSERT_EQ(lite::RET_OK, ctx->Init());
auto kernel = creator(inputs, outputs, reinterpret_cast<OpParameter *>(parameter), ctx.get(), desc);
ASSERT_NE(kernel, nullptr);
auto ret = kernel->Run();
EXPECT_EQ(0, ret);
int8_t expect0[12] = {16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68};
for (int i = 0; i < 12; ++i) {
EXPECT_EQ(output_data[i], expect0[i]);
}
in_tensor.set_data(nullptr);
out_tensor.set_data(nullptr);
begin_tensor.set_data(nullptr);
size_tensor.set_data(nullptr);
delete kernel;
}
TEST_F(TestSliceInt8, Slice7D) {
lite::Tensor in_tensor(kNumberTypeInt8, {2, 1, 1, 1, 3, 2, 3});
lite::Tensor out_tensor(kNumberTypeInt8, {1, 1, 1, 1, 2, 2, 3});
int8_t input_data[] = {105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68,
105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68};
int8_t output_data[12];
in_tensor.set_data(input_data);
out_tensor.set_data(output_data);
lite::Tensor begin_tensor(kNumberTypeInt32, {7});
int begin_data[7] = {0, 0, 0, 0, 1, 0, 0};
begin_tensor.set_data(begin_data);
lite::Tensor size_tensor(kNumberTypeInt32, {7});
int size_data[7] = {1, 1, 1, 1, 2, 2, 3};
size_tensor.set_data(size_data);
const lite::QuantArg quant_in0 = {0.00784314f, 0}; // -1.0--1.0 -> 0--255
const lite::QuantArg quant_out = {0.00784314f, 0};
in_tensor.AddQuantParam(quant_in0);
out_tensor.AddQuantParam(quant_out);
std::vector<lite::Tensor *> inputs = {&in_tensor, &begin_tensor, &size_tensor};
std::vector<lite::Tensor *> outputs = {&out_tensor};
SliceParameter *parameter = new (std::nothrow) SliceParameter;
parameter->op_parameter_.infer_flag_ = true;
kernel::KernelKey desc = {kernel::KERNEL_ARCH::kCPU, kNumberTypeInt8, schema::PrimitiveType_SliceFusion};
auto creator = lite::KernelRegistry::GetInstance()->GetCreator(desc);
ASSERT_NE(creator, nullptr);
auto ctx = std::make_shared<lite::InnerContext>();
ASSERT_EQ(lite::RET_OK, ctx->Init());
auto kernel = creator(inputs, outputs, reinterpret_cast<OpParameter *>(parameter), ctx.get(), desc);
ASSERT_NE(kernel, nullptr);
auto ret = kernel->Run();
EXPECT_EQ(0, ret);
int8_t expect0[12] = {16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68};
for (int i = 0; i < 12; ++i) {
EXPECT_EQ(output_data[i], expect0[i]);
}
in_tensor.set_data(nullptr);
out_tensor.set_data(nullptr);
begin_tensor.set_data(nullptr);
size_tensor.set_data(nullptr);
delete kernel;
}
TEST_F(TestSliceInt8, Slice8D) {
lite::Tensor in_tensor(kNumberTypeInt8, {2, 1, 1, 1, 1, 3, 2, 3});
lite::Tensor out_tensor(kNumberTypeInt8, {1, 1, 1, 1, 1, 1, 2, 3});
lite::Tensor begin_tensor(kNumberTypeInt32, {8});
int begin_data[8] = {1, 0, 0, 0, 0, 1, 0, 0};
begin_tensor.set_data(begin_data);
lite::Tensor size_tensor(kNumberTypeInt32, {8});
int size_data[8] = {1, 1, 1, 1, 1, 2, 2, 3};
size_tensor.set_data(size_data);
int8_t input_data[] = {105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68,
105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68};
int8_t output_data[12];
in_tensor.set_data(input_data);
out_tensor.set_data(output_data);
const lite::QuantArg quant_in0 = {0.00784314f, 0}; // -1.0--1.0 -> 0--255
const lite::QuantArg quant_out = {0.00784314f, 0};
in_tensor.AddQuantParam(quant_in0);
out_tensor.AddQuantParam(quant_out);
std::vector<lite::Tensor *> inputs = {&in_tensor, &begin_tensor, &size_tensor};
std::vector<lite::Tensor *> outputs = {&out_tensor};
SliceParameter *parameter = new (std::nothrow) SliceParameter;
parameter->op_parameter_.infer_flag_ = true;
kernel::KernelKey desc = {kernel::KERNEL_ARCH::kCPU, kNumberTypeInt8, schema::PrimitiveType_SliceFusion};
auto creator = lite::KernelRegistry::GetInstance()->GetCreator(desc);
ASSERT_NE(creator, nullptr);
auto ctx = std::make_shared<lite::InnerContext>();
ASSERT_EQ(lite::RET_OK, ctx->Init());
auto kernel = creator(inputs, outputs, reinterpret_cast<OpParameter *>(parameter), ctx.get(), desc);
ASSERT_NE(kernel, nullptr);
auto ret = kernel->Run();
EXPECT_EQ(0, ret);
int8_t expect0[12] = {16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68};
for (int i = 0; i < 12; ++i) {
EXPECT_EQ(output_data[i], expect0[i]);
}
in_tensor.set_data(nullptr);
out_tensor.set_data(nullptr);
begin_tensor.set_data(nullptr);
size_tensor.set_data(nullptr);
delete kernel;
}
TEST_F(TestSliceInt8, SliceDiffQuantArgs) {
lite::Tensor in_tensor(kNumberTypeInt8, {2, 1, 1, 1, 1, 3, 2, 3});
lite::Tensor out_tensor(kNumberTypeInt8, {1, 1, 1, 1, 1, 1, 2, 3});
lite::Tensor begin_tensor(kNumberTypeInt32, {8});
int begin_data[8] = {1, 0, 0, 0, 0, 1, 0, 0};
begin_tensor.set_data(begin_data);
lite::Tensor size_tensor(kNumberTypeInt32, {8});
int size_data[8] = {1, 1, 1, 1, 1, 2, 2, 3};
size_tensor.set_data(size_data);
int8_t input_data[] = {105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68,
105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68};
int8_t output_data[12];
in_tensor.set_data(input_data);
out_tensor.set_data(output_data);
const lite::QuantArg quant_in0 = {0.00784314f, 0}; // -1.0--1.0 -> 0--255
const lite::QuantArg quant_out = {0.01568628f, 0};
in_tensor.AddQuantParam(quant_in0);
out_tensor.AddQuantParam(quant_out);
std::vector<lite::Tensor *> inputs = {&in_tensor, &begin_tensor, &size_tensor};
std::vector<lite::Tensor *> outputs = {&out_tensor};
SliceParameter *parameter = new (std::nothrow) SliceParameter;
parameter->op_parameter_.infer_flag_ = true;
kernel::KernelKey desc = {kernel::KERNEL_ARCH::kCPU, kNumberTypeInt8, schema::PrimitiveType_SliceFusion};
auto creator = lite::KernelRegistry::GetInstance()->GetCreator(desc);
ASSERT_NE(creator, nullptr);
auto ctx = std::make_shared<lite::InnerContext>();
ASSERT_EQ(lite::RET_OK, ctx->Init());
auto kernel = creator(inputs, outputs, reinterpret_cast<OpParameter *>(parameter), ctx.get(), desc);
ASSERT_NE(kernel, nullptr);
auto ret = kernel->Run();
EXPECT_EQ(0, ret);
int8_t expect0[12] = {8, 23, 34, -25, -58, 53, -49, 60, 52, 41, -57, 34};
for (int i = 0; i < 12; ++i) {
EXPECT_EQ(output_data[i], expect0[i]);
}
in_tensor.set_data(nullptr);
out_tensor.set_data(nullptr);
begin_tensor.set_data(nullptr);
size_tensor.set_data(nullptr);
delete kernel;
}
TEST_F(TestSliceInt8, SliceSingleThread) {
lite::Tensor in_tensor(kNumberTypeInt8, {2, 1, 1, 1, 1, 3, 2, 3});
lite::Tensor out_tensor(kNumberTypeInt8, {1, 1, 1, 1, 1, 1, 2, 3});
lite::Tensor begin_tensor(kNumberTypeInt32, {8});
int begin_data[8] = {1, 0, 0, 0, 0, 1, 0, 0};
begin_tensor.set_data(begin_data);
lite::Tensor size_tensor(kNumberTypeInt32, {8});
int size_data[8] = {1, 1, 1, 1, 1, 2, 2, 3};
size_tensor.set_data(size_data);
int8_t input_data[] = {105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68,
105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68};
int8_t output_data[12];
in_tensor.set_data(input_data);
out_tensor.set_data(output_data);
const lite::QuantArg quant_in0 = {0.00784314f, 0}; // -1.0--1.0 -> 0--255
const lite::QuantArg quant_out = {0.00784314f, 0};
in_tensor.AddQuantParam(quant_in0);
out_tensor.AddQuantParam(quant_out);
std::vector<lite::Tensor *> inputs = {&in_tensor, &begin_tensor, &size_tensor};
std::vector<lite::Tensor *> outputs = {&out_tensor};
SliceParameter *parameter = new (std::nothrow) SliceParameter;
parameter->op_parameter_.infer_flag_ = true;
kernel::KernelKey desc = {kernel::KERNEL_ARCH::kCPU, kNumberTypeInt8, schema::PrimitiveType_SliceFusion};
auto creator = lite::KernelRegistry::GetInstance()->GetCreator(desc);
ASSERT_NE(creator, nullptr);
auto ctx = std::make_shared<lite::InnerContext>();
ctx->thread_num_ = 1;
ASSERT_EQ(lite::RET_OK, ctx->Init());
auto kernel = creator(inputs, outputs, reinterpret_cast<OpParameter *>(parameter), ctx.get(), desc);
ASSERT_NE(kernel, nullptr);
auto ret = kernel->Run();
EXPECT_EQ(0, ret);
int8_t expect0[12] = {16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68};
for (int i = 0; i < 12; ++i) {
EXPECT_EQ(output_data[i], expect0[i]);
}
in_tensor.set_data(nullptr);
out_tensor.set_data(nullptr);
begin_tensor.set_data(nullptr);
size_tensor.set_data(nullptr);
delete kernel;
}
TEST_F(TestSliceInt8, Slice4Thread) {
lite::Tensor in_tensor(kNumberTypeInt8, {2, 1, 1, 1, 1, 3, 2, 3});
lite::Tensor out_tensor(kNumberTypeInt8, {1, 1, 1, 1, 1, 1, 2, 3});
lite::Tensor begin_tensor(kNumberTypeInt32, {8});
int begin_data[8] = {1, 0, 0, 0, 0, 1, 0, 0};
begin_tensor.set_data(begin_data);
lite::Tensor size_tensor(kNumberTypeInt32, {8});
int size_data[8] = {1, 1, 1, 1, 1, 2, 2, 3};
size_tensor.set_data(size_data);
int8_t input_data[] = {105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68,
105, 35, -27, 0, -63, 99, 16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68};
int8_t output_data[12];
in_tensor.set_data(input_data);
out_tensor.set_data(output_data);
const lite::QuantArg quant_in0 = {0.00784314f, 0}; // -1.0--1.0 -> 0--255
const lite::QuantArg quant_out = {0.00784314f, 0};
in_tensor.AddQuantParam(quant_in0);
out_tensor.AddQuantParam(quant_out);
std::vector<lite::Tensor *> inputs = {&in_tensor, &begin_tensor, &size_tensor};
std::vector<lite::Tensor *> outputs = {&out_tensor};
SliceParameter *parameter = new (std::nothrow) SliceParameter;
parameter->op_parameter_.infer_flag_ = true;
kernel::KernelKey desc = {kernel::KERNEL_ARCH::kCPU, kNumberTypeInt8, schema::PrimitiveType_SliceFusion};
auto creator = lite::KernelRegistry::GetInstance()->GetCreator(desc);
ASSERT_NE(creator, nullptr);
auto ctx = std::make_shared<lite::InnerContext>();
ctx->thread_num_ = 4;
ASSERT_EQ(lite::RET_OK, ctx->Init());
auto kernel = creator(inputs, outputs, reinterpret_cast<OpParameter *>(parameter), ctx.get(), desc);
ASSERT_NE(kernel, nullptr);
auto ret = kernel->Run();
EXPECT_EQ(0, ret);
int8_t expect0[12] = {16, 45, 67, -49, -115, 106, -98, 119, 103, 81, -114, 68};
for (int i = 0; i < 12; ++i) {
EXPECT_EQ(output_data[i], expect0[i]);
}
in_tensor.set_data(nullptr);
out_tensor.set_data(nullptr);
begin_tensor.set_data(nullptr);
size_tensor.set_data(nullptr);
delete kernel;
}
} // namespace mindspore