caffe Sigmoid cross entropy loss 交叉熵损失函数

Sigmoid 交叉熵损失函数（Sigmoid Cross Entropy Loss）

study(3) 关于激活函数以及loss function" title="caffe study(3) 关于激活函数以及loss function" style="box-sizing: border-box; border: 0px; vertical-align: middle; outline: 0px; max-width: 100%; margin: 0px; padding: 0px; list-style: none;" />
官方： loss

,输入：形状:

















得分

















, 这个层使用 sigmoid 函数







映射到概率分布






























形状:

















标签














输出：形状：

















计算公式:










































































应用场景：
预测目标概率分布Parameters

bottom	input Blob vector (length 2) the scores , which this layer maps to probability predictions using the sigmoid function (see SigmoidLayer). the targets
top	output Blob vector (length 1) the computed cross-entropy loss:

Computes the sigmoid cross-entropy loss error gradient w.r.t. the predictions.Gradients cannot be computed with respect to the target inputs (bottom[1]), so this method ignores bottom[1] and requires !propagate_down[1], crashing if propagate_down[1] is set.Parameters

top	output Blob vector (length 1), providing the error gradient with respect to the outputs This Blob's diff will simply contain the loss_weight* , as is the coefficient of this layer's output in the overall Netloss ; hence . (*Assuming that this top Blob is not used as a bottom (input) by any other layer of the Net.)
propagate_down	see Layer::Backward. propagate_down[1] must be false as gradient computation with respect to the targets is not implemented.
bottom	input Blob vector (length 2) the predictions ; Backward computes diff the labels – ignored as we can't compute their error gradients

[cpp] view plain copy#include <algorithm>
#include <cfloat>
#include <vector>

#include "caffe/layer.hpp"
#include "caffe/util/math_functions.hpp"
#include "caffe/vision_layers.hpp"

// Computes the cross-entropy (logistic) loss ,it is often used for predicting targets interpreted
// as probabilities. Detailed reference to the official document:
// http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1SigmoidCrossEntropyLossLayer.html
namespace caffe {

template <typename Dtype>
void SigmoidCrossEntropyLossLayer<Dtype>::LayerSetUp(
const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
LossLayer<Dtype>::LayerSetUp(bottom, top);
sigmoid_bottom_vec_.clear();
sigmoid_bottom_vec_.push_back(bottom[0]);
sigmoid_top_vec_.clear();
sigmoid_top_vec_.push_back(sigmoid_output_.get());
sigmoid_layer_->SetUp(sigmoid_bottom_vec_, sigmoid_top_vec_);
}

template <typename Dtype>
void SigmoidCrossEntropyLossLayer<Dtype>::Reshape(
const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
LossLayer<Dtype>::Reshape(bottom, top);
CHECK_EQ(bottom[0]->count(), bottom[1]->count()) <<
"SIGMOID_CROSS_ENTROPY_LOSS layer inputs must have the same count.";
sigmoid_layer_->Reshape(sigmoid_bottom_vec_, sigmoid_top_vec_);
}

template <typename Dtype>
void SigmoidCrossEntropyLossLayer<Dtype>::Forward_cpu(
const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
// The forward pass computes the sigmoid outputs.
sigmoid_bottom_vec_[0] = bottom[0];
sigmoid_layer_->Forward(sigmoid_bottom_vec_, sigmoid_top_vec_);
// Compute the loss (negative log likelihood)
const int count = bottom[0]->count();
const int num = bottom[0]->num();
// Stable version of loss computation from input data
const Dtype* input_data = bottom[0]->cpu_data();
const Dtype* target = bottom[1]->cpu_data();
Dtype loss = 0;
for (int i = 0; i < count; ++i) {
loss -= input_data[i] * (target[i] - (input_data[i] >= 0)) -
log(1 + exp(input_data[i] - 2 * input_data[i] * (input_data[i] >= 0)));
}
top[0]->mutable_cpu_data()[0] = loss / num;
}

template <typename Dtype>
void SigmoidCrossEntropyLossLayer<Dtype>::Backward_cpu(
const vector<Blob<Dtype>*>& top, const vector<bool>& propagate_down,
const vector<Blob<Dtype>*>& bottom) {
if (propagate_down[1]) {
LOG(FATAL) << this->type()
<< " Layer cannot backpropagate to label inputs.";
}
if (propagate_down[0]) {
// First, compute the diff
const int count = bottom[0]->count();
const int num = bottom[0]->num();
const Dtype* sigmoid_output_data = sigmoid_output_->cpu_data();
const Dtype* target = bottom[1]->cpu_data();
Dtype* bottom_diff = bottom[0]->mutable_cpu_diff();
caffe_sub(count, sigmoid_output_data, target, bottom_diff);
// Scale down gradient
const Dtype loss_weight = top[0]->cpu_diff()[0];
caffe_scal(count, loss_weight / num, bottom_diff);
}
}

#ifdef CPU_ONLY
STUB_GPU_BACKWARD(SigmoidCrossEntropyLossLayer, Backward);
#endif

INSTANTIATE_CLASS(SigmoidCrossEntropyLossLayer);
REGISTER_LAYER_CLASS(SigmoidCrossEntropyLoss);

} // namespace caffe