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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
|
/* Copyright 2015 The TensorFlow Authors. All Rights Reserved.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://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.
==============================================================================*/
#ifndef TENSORFLOW_KERNELS_TRAINING_OPS_H_
#define TENSORFLOW_KERNELS_TRAINING_OPS_H_
#include "third_party/eigen3/unsupported/Eigen/CXX11/Tensor"
#include "tensorflow/core/framework/tensor_types.h"
namespace tensorflow {
namespace functor {
// Each training algorithm has a ApplyXYZ functor struct declared in
// this header file. They are specialized for different devices
// (CPUDevice in training_ops.cc or GPUDevice in training_ops_gpu.cc).
template <typename Device, typename T>
struct ApplyGradientDescent {
void operator()(const Device& d, typename TTypes<T>::Flat var,
typename TTypes<T>::ConstScalar alpha,
typename TTypes<T>::ConstFlat delta);
};
template <typename Device, typename T>
struct ApplyAdadelta {
void operator()(const Device& d, typename TTypes<T>::Flat var,
typename TTypes<T>::Flat accum,
typename TTypes<T>::Flat accum_update,
typename TTypes<T>::ConstScalar lr,
typename TTypes<T>::ConstScalar rho,
typename TTypes<T>::ConstScalar epsilon,
typename TTypes<T>::ConstFlat grad);
};
template <typename Device, typename T>
struct FobosElasticNet {
void operator()(const Device& d, typename TTypes<T>::Flat var,
typename TTypes<T>::ConstScalar lr,
typename TTypes<T>::ConstScalar l1,
typename TTypes<T>::ConstScalar l2,
typename TTypes<T>::ConstFlat grad);
};
template <typename Device, typename T>
struct ApplyProximalGradientDescent {
void operator()(const Device& d, typename TTypes<T>::Flat var,
typename TTypes<T>::ConstScalar lr,
typename TTypes<T>::ConstScalar l1,
typename TTypes<T>::ConstScalar l2,
typename TTypes<T>::ConstFlat grad);
};
template <typename Device, typename T>
struct ApplyAdagrad {
void operator()(const Device& d, typename TTypes<T>::Flat var,
typename TTypes<T>::Flat accum,
typename TTypes<T>::ConstScalar lr,
typename TTypes<T>::ConstFlat grad);
};
template <typename Device, typename T>
struct ApplyProximalAdagrad {
void operator()(const Device& d, typename TTypes<T>::Flat var,
typename TTypes<T>::Flat accum,
typename TTypes<T>::ConstScalar lr,
typename TTypes<T>::ConstScalar l1,
typename TTypes<T>::ConstScalar l2,
typename TTypes<T>::ConstFlat grad);
};
template <typename Device, typename T>
struct ApplyFtrl {
void operator()(const Device& d, typename TTypes<T>::Flat var,
typename TTypes<T>::Flat accum,
typename TTypes<T>::Flat linear,
typename TTypes<T>::ConstFlat grad,
typename TTypes<T>::ConstScalar lr,
typename TTypes<T>::ConstScalar l1,
typename TTypes<T>::ConstScalar l2,
typename TTypes<T>::ConstScalar lr_power);
};
template <typename Device, typename T>
struct ApplyMomentum {
void operator()(const Device& d, typename TTypes<T>::Flat var,
typename TTypes<T>::Flat accum,
typename TTypes<T>::ConstScalar lr,
typename TTypes<T>::ConstFlat grad,
typename TTypes<T>::ConstScalar momentum);
};
template <typename Device, typename T>
struct ApplyAdam {
void operator()(const Device& d, typename TTypes<T>::Flat var,
typename TTypes<T>::Flat m, typename TTypes<T>::Flat v,
typename TTypes<T>::ConstScalar beta1_power,
typename TTypes<T>::ConstScalar beta2_power,
typename TTypes<T>::ConstScalar lr,
typename TTypes<T>::ConstScalar beta1,
typename TTypes<T>::ConstScalar beta2,
typename TTypes<T>::ConstScalar epsilon,
typename TTypes<T>::ConstFlat grad);
};
template <typename Device, typename T>
struct ApplyRMSProp {
void operator()(const Device& d, typename TTypes<T>::Flat var,
typename TTypes<T>::Flat ms, typename TTypes<T>::Flat mom,
typename TTypes<T>::ConstScalar lr,
typename TTypes<T>::ConstScalar rho,
typename TTypes<T>::ConstScalar momentum,
typename TTypes<T>::ConstScalar epsilon,
typename TTypes<T>::ConstFlat grad);
};
} // end namespace functor
} // end namespace tensorflow
#endif // TENSORFLOW_KERNELS_TRAINING_OPS_H_
|
