blob: 41734f3254aac01afac681a71e8634a4e51afc39 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
|
#ifndef TENSORFLOW_KERNELS_ARGMAX_OP_H_
#define TENSORFLOW_KERNELS_ARGMAX_OP_H_
// Generator definition for ArgMaxOp, must be compilable by nvcc.
#include "tensorflow/core/platform/port.h"
#include "tensorflow/core/framework/tensor_types.h"
#include "third_party/eigen3/unsupported/Eigen/CXX11/Tensor"
namespace tensorflow {
namespace functor {
template <typename Device, typename T>
struct ArgMax {
#define DECLARE_COMPUTE_SPEC(Dims) \
EIGEN_ALWAYS_INLINE static void Reduce##Dims( \
const Device& d, typename TTypes<T, Dims>::ConstTensor input, \
const int32 dimension, \
typename TTypes<int64, Dims - 1>::Tensor output) { \
output.device(d) = input.argmax(dimension).template cast<int64>(); \
}
DECLARE_COMPUTE_SPEC(1);
DECLARE_COMPUTE_SPEC(2);
DECLARE_COMPUTE_SPEC(3);
DECLARE_COMPUTE_SPEC(4);
DECLARE_COMPUTE_SPEC(5);
#undef DECLARE_COMPUTE_SPEC
};
template <typename Device, typename T>
struct ArgMin {
#define DECLARE_COMPUTE_SPEC(Dims) \
EIGEN_ALWAYS_INLINE static void Reduce##Dims( \
const Device& d, typename TTypes<T, Dims>::ConstTensor input, \
const int32 dimension, \
typename TTypes<int64, Dims - 1>::Tensor output) { \
output.device(d) = input.argmin(dimension).template cast<int64>(); \
}
DECLARE_COMPUTE_SPEC(1);
DECLARE_COMPUTE_SPEC(2);
DECLARE_COMPUTE_SPEC(3);
DECLARE_COMPUTE_SPEC(4);
DECLARE_COMPUTE_SPEC(5);
#undef DECLARE_COMPUTE_SPEC
};
} // namespace functor
} // namespace tensorflow
#endif // TENSORFLOW_KERNELS_ARGMAX_OP_H_
|
