tanh_layer.hpp
#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_
tanh_layer.cpp
// TanH neuron activation function layer.
// Adapted from ReLU layer code written by Yangqing Jia
#include <vector>
#include "caffe/layers/tanh_layer.hpp"
namespace caffe {
template <typename Dtype>
void TanHLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
const Dtype* bottom_data = bottom[0]->cpu_data();
Dtype* top_data = top[0]->mutable_cpu_data();
const int count = bottom[0]->count();
for (int i = 0; i < count; ++i) {
top_data[i] = tanh(bottom_data[i]);
}
}
template <typename Dtype>
void TanHLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down,
const vector<Blob<Dtype>*>& bottom) {
if (propagate_down[0]) {
const Dtype* top_data = top[0]->cpu_data();
const Dtype* top_diff = top[0]->cpu_diff();
Dtype* bottom_diff = bottom[0]->mutable_cpu_diff();
const int count = bottom[0]->count();
Dtype tanhx;
for (int i = 0; i < count; ++i) {
tanhx = top_data[i];
bottom_diff[i] = top_diff[i] * (1 - tanhx * tanhx);
}
}
}
#ifdef CPU_ONLY
STUB_GPU(TanHLayer);
#endif
INSTANTIATE_CLASS(TanHLayer);
} // namespace caffe