Skip to content

T
Tensor.LowPrecision
Commit 01747e0d by linye
Options

update test of multiply, softmax, unsqueeze, crossentropy

parent 4c0fafc0
正在显示 包含 801 行增加 和 3 行删除
source/tensor/test/TMultiply.cpp
......@@ -20,6 +20,7 @@
*/
#include "TMultiply.h"
#include "../core/getandset/ConvertDataType.h"
namespace nts { // namespace nts(NiuTrans.Tensor)
......@@ -148,6 +149,118 @@ bool TestMultiply1()
#endif // USE_CUDA
}
/*
case 2: float16 element-wise product of two tensors
c(i) = a(i)*b(i) + \alpha * c(i)
In this case, (2, 2) (2, 2) -> (2, 2), leadingDim=0, alpha=0.
*/
bool TestMultiply2()
{
/* a source tensor of size (2, 2) */
int sOrder1 = 2;
int * sDimSize1 = new int[sOrder1];
sDimSize1[0] = 2;
sDimSize1[1] = 2;
int sUnitNum1 = 1;
for (int i = 0; i < sOrder1; i++)
sUnitNum1 *= sDimSize1[i];
/* a source tensor of size (2, 2) */
int sOrder2 = 2;
int * sDimSize2 = new int[sOrder2];
sDimSize2[0] = 2;
sDimSize2[1] = 2;
int sUnitNum2 = 1;
for (int i = 0; i < sOrder2; i++)
sUnitNum2 *= sDimSize2[i];
/* a target tensor of size (2, 2) */
int tOrder = 2;
int * tDimSize = new int[tOrder];
tDimSize[0] = 2;
tDimSize[1] = 2;
int tUnitNum = 1;
for (int i = 0; i < tOrder; i++)
tUnitNum *= tDimSize[i];
DTYPE sData1[2][2] = { {0.0F, 1.0F},
{2.0F, 3.0F} };
DTYPE sData2[2][2] = { {0.0F, 1.0F},
{2.0F, 3.0F} };
DTYPE answer[2][2] = { {0.0F, 1.0F},
{4.0F, 9.0F} };
/* CPU test */
bool cpuTest = true;
#ifdef USE_CUDA
/* GPU test */
bool gpuTest = true;
/* create tensor */
XTensor * sGPU1 = NewTensor(sOrder1, sDimSize1, X_FLOAT, 1.0F, 0);
XTensor * sGPU2 = NewTensor(sOrder2, sDimSize2, X_FLOAT, 1.0F, 0);
XTensor * tGPU = NewTensor(tOrder, tDimSize, X_FLOAT, 1.0F, 0);
XTensor * tMeGPU = NewTensor(tOrder, tDimSize, X_FLOAT, 1.0F, 0);
XTensor tUserGPU;
/* create float16 tensor */
XTensor sHalfGPU1;
XTensor sHalfGPU2;
XTensor tHalfGPU;
XTensor tMeHalfGPU;
XTensor tUserHalfGPU;
/* Initialize variables */
sGPU1->SetData(sData1, sUnitNum1);
tMeGPU->SetData(sData1, sUnitNum1);
sGPU2->SetData(sData2, sUnitNum2);
tGPU->SetZeroAll();
/* convert data type from float to float16 */
sHalfGPU1 = ConvertDataType(*sGPU1, X_FLOAT16);
sHalfGPU2 = ConvertDataType(*sGPU2, X_FLOAT16);
tHalfGPU = ConvertDataType(*tGPU, X_FLOAT16);
tMeHalfGPU = ConvertDataType(*tMeGPU, X_FLOAT16);
/* call multiply function */
_Multiply(&sHalfGPU1, &sHalfGPU2, &tHalfGPU, 0, 0);
_MultiplyMe(&tMeHalfGPU, &sHalfGPU2, 0, 0);
tUserHalfGPU = Multiply(sHalfGPU1, sHalfGPU2, 0);
/* convert data type from float16 to float */
_ConvertDataType(&tHalfGPU, tGPU);
_ConvertDataType(&tMeHalfGPU, tMeGPU);
tUserGPU = ConvertDataType(tUserHalfGPU, X_FLOAT);
/* check results */
gpuTest = tGPU->CheckData(answer, tUnitNum) &&
tMeGPU->CheckData(answer, tUnitNum) &&
tUserGPU.CheckData(answer, tUnitNum);
/* destroy variables */
delete sGPU1;
delete sGPU2;
delete tGPU;
delete tMeGPU;
delete[] sDimSize1;
delete[] sDimSize2;
delete[] tDimSize;
return cpuTest && gpuTest;
#else
/* destroy variables */
delete[] sDimSize1;
delete[] sDimSize2;
delete[] tDimSize;
return cpuTest;
#endif // USE_CUDA
}
/* other cases */
/*
TODO!!
......@@ -169,6 +282,16 @@ bool TestMultiply()
else
XPRINT(0, stdout, ">> case 1 passed!\n");
/* case 2 test */
caseFlag = TestMultiply2();
if (!caseFlag) {
returnFlag = false;
XPRINT(0, stdout, ">> case 2 failed!\n");
}
else
XPRINT(0, stdout, ">> case 2 passed!\n");
/* other cases test */
/*
TODO!!
......
source/tensor/test/TSoftmax.cpp
......@@ -22,6 +22,7 @@
#include "../XTensor.h"
#include "../XUtility.h"
#include "TSoftmax.h"
#include "../core/getandset/ConvertDataType.h"
namespace nts { // namespace nts(NiuTrans.Tensor)
......@@ -207,6 +208,167 @@ bool TestSoftmax2()
#endif // USE_CUDA
}
/*
case 3: float16 test Softmax function.
softmax function: y = e^x / \sum_{i} e^{x_i}
*/
bool TestSoftmax3()
{
/* a tensor of size (2, 3) */
int order = 2;
int * dimSize = new int[order];
dimSize[0] = 2;
dimSize[1] = 3;
int unitNum = 1;
for (int i = 0; i < order; i++)
unitNum *= dimSize[i];
DTYPE xData[2][3] = { {0.0F, 1.0F, 2.0F},
{0.5F, 0.7F, 1.4F} };
DTYPE answer[2][3] = { {0.0900F, 0.2447F, 0.6652F},
{0.2136F, 0.2609F, 0.5254F} };
/* CPU test */
bool cpuTest = true;
#ifdef USE_CUDA
/* GPU test */
bool gpuTest = true;
/* create tensors */
XTensor * xGPU = NewTensor(order, dimSize, X_FLOAT, 1.0F, 0);
XTensor * yGPU = NewTensor(order, dimSize, X_FLOAT, 1.0F, 0);
XTensor yUserGPU;
/* create float16 tensors */
XTensor xHalfGPU;
XTensor yHalfGPU;
XTensor yUserHalfGPU;
/* initialize variables */
xGPU->SetData(xData, unitNum);
yGPU->SetZeroAll();
/* convert data type from float to float16 */
xHalfGPU = ConvertDataType(*xGPU, X_FLOAT16);
yHalfGPU = ConvertDataType(*yGPU, X_FLOAT16);
/* call softmax function */
_Softmax(&xHalfGPU, &yHalfGPU, 1);
yUserHalfGPU = Softmax(xHalfGPU, 1);
/* convert data type from float16 to float */
_ConvertDataType(&yHalfGPU, yGPU);
yUserGPU = ConvertDataType(yUserHalfGPU, X_FLOAT);
/* check result */
gpuTest = yGPU->CheckData(answer, unitNum, 1e-3F) &&
yUserGPU.CheckData(answer, unitNum, 1e-3F);
/* destroy variables */
delete xGPU;
delete yGPU;
delete[] dimSize;
return cpuTest && gpuTest;
#else
/* destroy variables */
delete[] dimSize;
return cpuTest;
#endif // USE_CUDA
}
/*
case 4: float16 test SoftmaxBackward function.
SoftmaxBackward function: dE/dx_j = -gold_j + y_j
In this case, LossName=CROSSENTROPY.
*/
bool TestSoftmax4()
{
/* a input tensor of size (2, 3) */
int order = 2;
int * dimSize = new int[order];
dimSize[0] = 1;
dimSize[1] = 3;
int unitNum = 1;
for (int i = 0; i < order; i++)
unitNum *= dimSize[i];
DTYPE xData[1][3] = { {0.0F, 1.0F, 2.0F} };
DTYPE gData[1][3] = { {0.0F, 0.0F, 1.0F} };
DTYPE yAnswer[1][3] = { {0.0900F, 0.2447F, 0.6652F} };
DTYPE dedxAnswer[1][3] = {0.0900F, 0.2447F, -0.3347F};
/* CPU test */
bool cpuTest = true;
#ifdef USE_CUDA
/* GPU test */
bool gpuTest = true;
/* create tensors */
XTensor * xGPU = NewTensor(order, dimSize, X_FLOAT, 1.0F, 0);
XTensor * yGPU = NewTensor(order, dimSize, X_FLOAT, 1.0F, 0);
XTensor * gGPU = NewTensor(order, dimSize, X_FLOAT, 1.0F, 0);
XTensor * dedyGPU = NewTensor(order, dimSize, X_FLOAT, 1.0F, 0);
XTensor * dedxGPU = NewTensor(order, dimSize, X_FLOAT, 1.0F, 0);
/* create float16 tensors */
XTensor xHalfGPU;
XTensor yHalfGPU;
XTensor gHalfGPU;
XTensor dedyHalfGPU;
XTensor dedxHalfGPU;
/* initialize variables */
xGPU->SetData(xData, unitNum);
gGPU->SetData(gData, unitNum);
yGPU->SetZeroAll();
dedxGPU->SetZeroAll();
dedyGPU->SetZeroAll();
/* convert data type from float to float16 */
xHalfGPU = ConvertDataType(*xGPU, X_FLOAT16);
yHalfGPU = ConvertDataType(*yGPU, X_FLOAT16);
gHalfGPU = ConvertDataType(*gGPU, X_FLOAT16);
dedxHalfGPU = ConvertDataType(*dedxGPU, X_FLOAT16);
dedyHalfGPU = ConvertDataType(*dedyGPU, X_FLOAT16);
/* call softmax function */
_Softmax(&xHalfGPU, &yHalfGPU, 1);
/* call SoftmaxBackward function */
_SoftmaxBackward(&gHalfGPU, &yHalfGPU, &xHalfGPU, &dedyHalfGPU, &dedxHalfGPU, NULL, 1, CROSSENTROPY);
/* convert data type from float to float16 */
_ConvertDataType(&yHalfGPU, yGPU);
_ConvertDataType(&dedxHalfGPU, dedxGPU);
/* check result */
gpuTest = yGPU->CheckData(yAnswer, unitNum, 1e-3F) &&
dedxGPU->CheckData(dedxAnswer, unitNum, 1e-3F);
/* destroy variables */
delete xGPU;
delete yGPU;
delete gGPU;
delete dedxGPU;
delete dedyGPU;
delete[] dimSize;
return cpuTest && gpuTest;
#else
/* destroy variables */
delete[] dimSize;
return cpuTest;
#endif // USE_CUDA
}
/* other cases */
/*
TODO!!
......@@ -238,6 +400,26 @@ bool TestSoftmax()
else
XPRINT(0, stdout, ">> case 2 passed!\n");
/* case 3 test */
caseFlag = TestSoftmax3();
if (!caseFlag) {
returnFlag = false;
XPRINT(0, stdout, ">> case 3 failed!\n");
}
else
XPRINT(0, stdout, ">> case 3 passed!\n");
/* case 4 test */
caseFlag = TestSoftmax4();
if (!caseFlag) {
returnFlag = false;
XPRINT(0, stdout, ">> case 4 failed!\n");
}
else
XPRINT(0, stdout, ">> case 4 passed!\n");
/* other cases test */
/*
TODO!!
......
source/tensor/test/TUnsqueeze.cpp
......@@ -21,6 +21,7 @@
#include "../XList.h"
#include "TUnsqueeze.h"
#include "../core/getandset/ConvertDataType.h"
namespace nts { // namespace nts(NiuTrans.Tensor)
......@@ -153,6 +154,128 @@ bool TestUnsqueeze1()
#endif // USE_CUDA
}
/*
case 2: float16 insert a dimension by copying the blocks for x times (where x is the size of the inerted dimension)
In this case,
(2, 3) -> (2, 2, 3), dim=1, dSize=2
(2, 3) -> (2, 3, 2), dim=2, dSize=2
*/
bool TestUnsqueeze2()
{
/* a source tensor of size (2, 3) */
int sOrder = 2;
int * sDimSize = new int[sOrder];
sDimSize[0] = 2;
sDimSize[1] = 3;
int sUnitNum = 1;
for (int i = 0; i < sOrder; i++)
sUnitNum *= sDimSize[i];
/* a target tensor of size (2, 2, 3) */
int tOrder1 = 3;
int * tDimSize1 = new int[tOrder1];
tDimSize1[0] = 2;
tDimSize1[1] = 2;
tDimSize1[2] = 3;
int tUnitNum1 = 1;
for (int i = 0; i < tOrder1; i++)
tUnitNum1 *= tDimSize1[i];
/* a target tensor of size (2, 3, 2) */
int tOrder2 = 3;
int * tDimSize2 = new int[tOrder2];
tDimSize2[0] = 2;
tDimSize2[1] = 3;
tDimSize2[2] = 2;
int tUnitNum2 = 1;
for (int i = 0; i < tOrder2; i++)
tUnitNum2 *= tDimSize2[i];
DTYPE sData[2][3] = { {0.0F, 1.0F, 2.0F},
{3.0F, 4.0F, 5.0F} };
DTYPE answer1[2][2][3] = { { {0.0F, 1.0F, 2.0F},
{0.0F, 1.0F, 2.0F} },
{ {3.0F, 4.0F, 5.0F},
{3.0F, 4.0F, 5.0F} } };
DTYPE answer2[2][3][2] = { { {0.0F, 0.0F},
{1.0F, 1.0F},
{2.0F, 2.0F} },
{ {3.0F, 3.0F},
{4.0F, 4.0F},
{5.0F, 5.0F} } };
/* CPU test */
bool cpuTest = true;
#ifdef USE_CUDA
/* GPU test */
bool gpuTest = true;
/* create tensor */
XTensor * sGPU = NewTensor(sOrder, sDimSize, X_FLOAT, 1.0F, 0);
XTensor * tGPU1 = NewTensor(tOrder1, tDimSize1, X_FLOAT, 1.0F, 0);
XTensor * tGPU2 = NewTensor(tOrder2, tDimSize2, X_FLOAT, 1.0F, 0);
XTensor tUserGPU1;
XTensor tUserGPU2;
/* create float16 tensor */
XTensor sHalfGPU;
XTensor tHalfGPU1;
XTensor tHalfGPU2;
XTensor tUserHalfGPU1;
XTensor tUserHalfGPU2;
/* Initialize variables */
sGPU->SetData(sData, sUnitNum);
tGPU1->SetZeroAll();
tGPU2->SetZeroAll();
/* convert data type from float to float16 */
sHalfGPU = ConvertDataType(*sGPU, X_FLOAT16);
tHalfGPU1 = ConvertDataType(*tGPU1, X_FLOAT16);
tHalfGPU2 = ConvertDataType(*tGPU2, X_FLOAT16);
/* call unsqueeze function */
_Unsqueeze(&sHalfGPU, &tHalfGPU1, 1, 2);
_Unsqueeze(&sHalfGPU, &tHalfGPU2, 2, 2);
tUserHalfGPU1 = Unsqueeze(sHalfGPU, 1, 2);
tUserHalfGPU2 = Unsqueeze(sHalfGPU, 2, 2);
/* convert data type from float16 to float */
_ConvertDataType(&tHalfGPU1, tGPU1);
_ConvertDataType(&tHalfGPU2, tGPU2);
tUserGPU1 = ConvertDataType(tUserHalfGPU1, X_FLOAT);
tUserGPU2 = ConvertDataType(tUserHalfGPU2, X_FLOAT);
/* check results */
gpuTest = tGPU1->CheckData(answer1, tUnitNum1) &&
tUserGPU1.CheckData(answer1, tUnitNum1) &&
tGPU2->CheckData(answer2, tUnitNum2) &&
tUserGPU2.CheckData(answer2, tUnitNum2);
/* destroy variables */
delete sGPU;
delete tGPU1;
delete tGPU2;
delete[] sDimSize;
delete[] tDimSize1;
delete[] tDimSize2;
return cpuTest && gpuTest;
#else
/* destroy variables */
delete[] sDimSize;
delete[] tDimSize1;
delete[] tDimSize2;
return cpuTest;
#endif // USE_CUDA
}
/* other cases */
/*
TODO!!
......@@ -174,6 +297,16 @@ bool TestUnsqueeze()
else
XPRINT(0, stdout, ">> case 1 passed!\n");
/* case 2 test */
caseFlag = TestUnsqueeze2();
if (!caseFlag) {
returnFlag = false;
XPRINT(0, stdout, ">> case 2 failed!\n");
}
else
XPRINT(0, stdout, ">> case 2 passed!\n");
/* other cases test */
/*
TODO!!
......
source/tensor/test/Test.cpp
......@@ -76,10 +76,10 @@ bool Test()
//wrong = !TestTan() || wrong;
//wrong = !TestTranspose() || wrong;
//wrong = !TestTopK() || wrong;
//wrong = !TestUnsqueeze() || wrong;
wrong = !TestUnsqueeze() || wrong;
//wrong = !TestXMem() || wrong;
//
//wrong = !TestCrossEntropy() || wrong;
wrong = !TestCrossEntropy() || wrong;
//wrong = !TestDropout() || wrong;
//wrong = !TestHardTanH() || wrong;
//wrong = !TestIdentity() || wrong;
......@@ -87,7 +87,7 @@ bool Test()
//wrong = !TestLoss() || wrong;
//wrong = !TestRectify() || wrong;
//wrong = !TestSigmoid() || wrong;
//wrong = !TestSoftmax() || wrong;
wrong = !TestSoftmax() || wrong;
/* other test */
/*
......
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论