Commit d3ee28fc by xuchen

bug fix

parent 6cc50435
......@@ -147,4 +147,4 @@ private:
}
#endif
#endif
\ No newline at end of file
......@@ -1107,18 +1107,18 @@ void Test(const char * test, const char * result, FNNModel &model)
/* the gold standard */
XTensor gold;
/* make the input tensor for position i */
for (int i = 0; i < model.n - 1; i++)
MakeWordBatch(inputs[i], ngrams, ngramNum, i, model.vSize, model.devID, model.mem);
/* make the gold tensor */
MakeWordBatch(gold, ngrams, ngramNum, model.n - 1, model.vSize, model.devID, model.mem);
if (!autoDiff) {
/* prepare an empty network for building the fnn */
FNNNet net;
/* make the input tensor for position i */
for (int i = 0; i < model.n - 1; i++)
MakeWordBatch(inputs[i], ngrams, ngramNum, i, model.vSize, model.devID, model.mem);
/* make the gold tensor */
MakeWordBatch(gold, ngrams, ngramNum, model.n - 1, model.vSize, model.devID, model.mem);
/* forward computation */
Forward(inputs, output, model, net);
}
......
......@@ -122,9 +122,9 @@ _SIMPLE_UNARY_FUNCTION(_Tan, tan)
_SIMPLE_UNARY_FUNCTION_ME(_TanMe, _Tan)
SIMPLE_UNARY_FUNCTION(Tan, _Tan, MATH_TAN)
_SIMPLE_UNARY_FUNCTION(_Round, round)
/*_SIMPLE_UNARY_FUNCTION(_Round, round)
_SIMPLE_UNARY_FUNCTION_ME(_RoundMe, _Round)
SIMPLE_UNARY_FUNCTION(Round, _Round, MATH_ROUND)
SIMPLE_UNARY_FUNCTION(Round, _Round, MATH_ROUND)*/
#endif
}
\ No newline at end of file
......@@ -57,6 +57,6 @@ SIMPLE_UNARY_FUNCTION_GPU(Log, log)
SIMPLE_UNARY_FUNCTION_GPU(Sin, sin)
SIMPLE_UNARY_FUNCTION_GPU(Cos, cos)
SIMPLE_UNARY_FUNCTION_GPU(Tan, tan)
SIMPLE_UNARY_FUNCTION_GPU(Round, round)
//SIMPLE_UNARY_FUNCTION_GPU(Round, round)
}
\ No newline at end of file
......@@ -84,13 +84,13 @@ void KernelTan(__half * a, __half * b, int size);
void _CudaTan(const XTensor * a, XTensor * b);
/* set each entry to its round value (CUDA Kernel) */
__global__
void KernelRound(DTYPE * a, DTYPE * b, int size);
//__global__
//void KernelRound(DTYPE * a, DTYPE * b, int size);
/* set each entry to its round value (CUDA Kernel) with float16 data type*/
__global__
void KernelRound(__half * a, __half * b, int size);
//__global__
//void KernelRound(__half * a, __half * b, int size);
/* set each entry to its round value */
void _CudaRound(const XTensor * a, XTensor * b);
//void _CudaRound(const XTensor * a, XTensor * b);
#endif // USE_CUDA
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论