-
Notifications
You must be signed in to change notification settings - Fork 18.7k
/
tanh_layer.hpp
73 lines (63 loc) · 2.45 KB
/
tanh_layer.hpp
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
#ifndef CAFFE_TANH_LAYER_HPP_
#define CAFFE_TANH_LAYER_HPP_
#include <vector>
#include "caffe/blob.hpp"
#include "caffe/layer.hpp"
#include "caffe/proto/caffe.pb.h"
#include "caffe/layers/neuron_layer.hpp"
namespace caffe {
/**
* @brief TanH hyperbolic tangent non-linearity @f$
* y = \frac{\exp(2x) - 1}{\exp(2x) + 1}
* @f$, popular in auto-encoders.
*
* Note that the gradient vanishes as the values move away from 0.
* The ReLULayer is often a better choice for this reason.
*/
template <typename Dtype>
class TanHLayer : public NeuronLayer<Dtype> {
public:
explicit TanHLayer(const LayerParameter& param)
: NeuronLayer<Dtype>(param) {}
virtual inline const char* type() const { return "TanH"; }
protected:
/**
* @param bottom input Blob vector (length 1)
* -# @f$ (N \times C \times H \times W) @f$
* the inputs @f$ x @f$
* @param top output Blob vector (length 1)
* -# @f$ (N \times C \times H \times W) @f$
* the computed outputs @f$
* y = \frac{\exp(2x) - 1}{\exp(2x) + 1}
* @f$
*/
virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top);
virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top);
/**
* @brief Computes the error gradient w.r.t. the sigmoid inputs.
*
* @param top output Blob vector (length 1), providing the error gradient with
* respect to the outputs
* -# @f$ (N \times C \times H \times W) @f$
* containing error gradients @f$ \frac{\partial E}{\partial y} @f$
* with respect to computed outputs @f$ y @f$
* @param propagate_down see Layer::Backward.
* @param bottom input Blob vector (length 1)
* -# @f$ (N \times C \times H \times W) @f$
* the inputs @f$ x @f$; Backward fills their diff with
* gradients @f$
* \frac{\partial E}{\partial x}
* = \frac{\partial E}{\partial y}
* \left(1 - \left[\frac{\exp(2x) - 1}{exp(2x) + 1} \right]^2 \right)
* = \frac{\partial E}{\partial y} (1 - y^2)
* @f$ if propagate_down[0]
*/
virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
};
} // namespace caffe
#endif // CAFFE_TANH_LAYER_HPP_