r-cnn学习(五):SmoothL1LossLayer论文与代码的结合理解

时间:2021-06-21 22:43:52

A Loss Function for Learning Region Proposals

训练RPN时,只对两种anchor给予正标签:和gt_box有着最高的IoU && IoU超过0.7。如果对于

所有的gt_box,其IoU都小于0.3,则标记为负。损失函数定义如下:

r-cnn学习(五):SmoothL1LossLayer论文与代码的结合理解

其中i为一个mini-batch中某anchor的索引,pi表示其为目标的预测概率,pi*表示gt_box(正为1,否则为0)。

ti和ti*分别表示预测框的位置和gt_box框的位置。Lreg如下:

r-cnn学习(五):SmoothL1LossLayer论文与代码的结合理解

bound-box regression中各参数的计算方式为:

r-cnn学习(五):SmoothL1LossLayer论文与代码的结合理解   (4)

其对应的SmoothL1LossLayer代码如下,整个过程分为两部分:前向计算以及后向计算(1)式的后半部分:

// ------------------------------------------------------------------
// Fast R-CNN
// Copyright (c) 2015 Microsoft
// Licensed under The MIT License [see fast-rcnn/LICENSE for details]
// Written by Ross Girshick
// ------------------------------------------------------------------ #include "caffe/fast_rcnn_layers.hpp" namespace caffe {
//SmoothL1前向计算(3)式
template <typename Dtype>
__global__ void SmoothL1Forward(const int n, const Dtype* in, Dtype* out,
Dtype sigma2) {
// f(x) = 0.5 * (sigma * x)^2 if |x| < 1 / sigma / sigma
// |x| - 0.5 / sigma / sigma otherwise
CUDA_KERNEL_LOOP(index, n) {
Dtype val = in[index];
Dtype abs_val = abs(val);
if (abs_val < 1.0 / sigma2) {
out[index] = 0.5 * val * val * sigma2;
} else {
out[index] = abs_val - 0.5 / sigma2;
}
}
}
//
template <typename Dtype>
void SmoothL1LossLayer<Dtype>::Forward_gpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
int count = bottom[0]->count();
caffe_gpu_sub(
count,
bottom[0]->gpu_data(), //ti
bottom[1]->gpu_data(), //ti*
diff_.mutable_gpu_data()); // d := ti-ti*
if (has_weights_) { //乘上相关的权重,对应于(1)式中的pi*,有目标时为1
// apply "inside" weights
caffe_gpu_mul(
count,
bottom[2]->gpu_data(), //pi*
diff_.gpu_data(),
diff_.mutable_gpu_data()); // d := w_in * (b0 - b1)
}
//代入计算SmoothL1
SmoothL1Forward<Dtype><<<CAFFE_GET_BLOCKS(count), CAFFE_CUDA_NUM_THREADS>>>(
count, diff_.gpu_data(), errors_.mutable_gpu_data(), sigma2_);
CUDA_POST_KERNEL_CHECK; if (has_weights_) { //乘上相关的权重
// apply "outside" weights
caffe_gpu_mul(
count,
bottom[3]->gpu_data(), // 1/Nreg
errors_.gpu_data(),
errors_.mutable_gpu_data()); // d := w_out * SmoothL1(w_in * (b0 - b1))
} Dtype loss;
caffe_gpu_dot(count, ones_.gpu_data(), errors_.gpu_data(), &loss);
top[0]->mutable_cpu_data()[0] = loss / bottom[0]->num();
}
//反向计算,对smoothLoss求导
template <typename Dtype>
__global__ void SmoothL1Backward(const int n, const Dtype* in, Dtype* out,
Dtype sigma2) {
// f'(x) = sigma * sigma * x if |x| < 1 / sigma / sigma
// = sign(x) otherwise
CUDA_KERNEL_LOOP(index, n) {
Dtype val = in[index];
Dtype abs_val = abs(val);
if (abs_val < 1.0 / sigma2) {
out[index] = sigma2 * val;
} else {
out[index] = (Dtype(0) < val) - (val < Dtype(0));
}
}
}
//
template <typename Dtype>
void SmoothL1LossLayer<Dtype>::Backward_gpu(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
// after forwards, diff_ holds w_in * (b0 - b1)
int count = diff_.count();
//调用反向smoothloss,diff_.gpu_data()表示x,diff_.mutable_gpu_data()表示smoothloss的导数
SmoothL1Backward<Dtype><<<CAFFE_GET_BLOCKS(count), CAFFE_CUDA_NUM_THREADS>>>(
count, diff_.gpu_data(), diff_.mutable_gpu_data(), sigma2_); //类似于前向
CUDA_POST_KERNEL_CHECK;
for (int i = 0; i < 2; ++i) {
if (propagate_down[i]) {
const Dtype sign = (i == 0) ? 1 : -1;
const Dtype alpha = sign * top[0]->cpu_diff()[0] / bottom[i]->num();
caffe_gpu_axpby(
count, // count
alpha, // alpha
diff_.gpu_data(), // x
Dtype(0), // beta
bottom[i]->mutable_gpu_diff()); // y
if (has_weights_) {
// Scale by "inside" weight
caffe_gpu_mul(
count,
bottom[2]->gpu_data(),
bottom[i]->gpu_diff(),
bottom[i]->mutable_gpu_diff());
// Scale by "outside" weight
caffe_gpu_mul(
count,
bottom[3]->gpu_data(),
bottom[i]->gpu_diff(),
bottom[i]->mutable_gpu_diff());
}
}
}
} INSTANTIATE_LAYER_GPU_FUNCS(SmoothL1LossLayer); } // namespace caffe