这篇博客主要写multibox_loss_layer,multibox_loss_layer也是SSD比较关键内容,主要包括内建了两个layer进行loss回归,还包括比如FindMatches,MineHardExamples,EncodeLocPrediction && EncodeConfPrediction等都是比较重要的函数(其中有一部分在bbox_util中,后面会介绍)
代码:
#include <algorithm>
#include <map>
#include <utility>
#include <vector>
#include "caffe/layers/multibox_loss_layer.hpp"
#include "caffe/util/math_functions.hpp"
namespace caffe {
// layer setup,在这个函数里面还分别新建了两个layer用于loc回归和conf loss的计算
template <typename Dtype>
void MultiBoxLossLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
LossLayer<Dtype>::LayerSetUp(bottom, top);
if (this->layer_param_.propagate_down_size() == 0) {
this->layer_param_.add_propagate_down(true); // 定位
this->layer_param_.add_propagate_down(true); // 分类得分
this->layer_param_.add_propagate_down(false); // prior
this->layer_param_.add_propagate_down(false); // ground truth
}
const MultiBoxLossParameter& multibox_loss_param =
this->layer_param_.multibox_loss_param();
multibox_loss_param_ = this->layer_param_.multibox_loss_param(); // 这句话多余吧?
num_ = bottom[0]->num(); // batch size
num_priors_ = bottom[2]->height() / 4; // 先验的个数,每个先验包含左上角和右下角的点坐标
// Get other parameters.
CHECK(multibox_loss_param.has_num_classes()) << "Must provide num_classes.";
num_classes_ = multibox_loss_param.num_classes(); // 类别个数
CHECK_GE(num_classes_, 1) << "num_classes should not be less than 1.";
share_location_ = multibox_loss_param.share_location(); // 共享类别位置预测 default = true
loc_classes_ = share_location_ ? 1 : num_classes_; // 如果shared表示所有的类别同用一个location prediction,否则每一类各自预测。还不是很懂这样做的原因
background_label_id_ = multibox_loss_param.background_label_id(); // background的id
use_difficult_gt_ = multibox_loss_param.use_difficult_gt(); // 是否使用difficutlt的ground truth,这个具体是什么还有待考虑
mining_type_ = multibox_loss_param.mining_type(); // 这里跟老版SSD代码有些许不同
if (multibox_loss_param.has_do_neg_mining()) {
LOG(WARNING) << "do_neg_mining is deprecated, use mining_type instead.";
do_neg_mining_ = multibox_loss_param.do_neg_mining(); // 难例挖掘 true
CHECK_EQ(do_neg_mining_,
mining_type_ != MultiBoxLossParameter_MiningType_NONE); // MultiBoxLossParameter_MiningType_NONE变量?还不清楚具体的用法
}
do_neg_mining_ = mining_type_ != MultiBoxLossParameter_MiningType_NONE;
if (!this->layer_param_.loss_param().has_normalization() && // loss normalization,出自LossParameter,默认VALID
this->layer_param_.loss_param().has_normalize()) {
normalization_ = this->layer_param_.loss_param().normalize() ?
LossParameter_NormalizationMode_VALID :
LossParameter_NormalizationMode_BATCH_SIZE;
} else {
normalization_ = this->layer_param_.loss_param().normalization();
}
if (do_neg_mining_) {
CHECK(share_location_)
<< "Currently only support negative mining if share_location is true.";
}
vector<int> loss_shape(1, 1);
// Set up localization loss layer. // 定位loss
loc_weight_ = multibox_loss_param.loc_weight(); // loc weight 1.0
loc_loss_type_ = multibox_loss_param.loc_loss_type(); // loss 类型 SMOOTH_L1
// fake shape.
vector<int> loc_shape(1, 1); // 1维
loc_shape.push_back(4); // 1,4
loc_pred_.Reshape(loc_shape); // 1*2 [1,4]
loc_gt_.Reshape(loc_shape); // [1,4]
loc_bottom_vec_.push_back(&loc_pred_); // 存放前面的指针
loc_bottom_vec_.push_back(&loc_gt_); // 存放gt的指针
loc_loss_.Reshape(loss_shape); // location的loss [1,4]
loc_top_vec_.push_back(&loc_loss_); // 存放top的指针
if (loc_loss_type_ == MultiBoxLossParameter_LocLossType_L2) { // 新建一个层,实现对locationloss的计算
LayerParameter layer_param;
layer_param.set_name(this->layer_param_.name() + "_l2_loc");
layer_param.set_type("EuclideanLoss");
layer_param.add_loss_weight(loc_weight_);
loc_loss_layer_ = LayerRegistry<Dtype>::CreateLayer(layer_param);
loc_loss_layer_->SetUp(loc_bottom_vec_, loc_top_vec_);
} else if (loc_loss_type_ == MultiBoxLossParameter_LocLossType_SMOOTH_L1) { // SMOOTH_L1,SSD是选这个
LayerParameter layer_param;
layer_param.set_name(this->layer_param_.name() + "_smooth_L1_loc"); // mbox_loss_smooth_L1_loc
layer_param.set_type("SmoothL1Loss");
layer_param.add_loss_weight(loc_weight_); // 1.0
loc_loss_layer_ = LayerRegistry<Dtype>::CreateLayer(layer_param); // 创建layer
loc_loss_layer_->SetUp(loc_bottom_vec_, loc_top_vec_); //送入推断和gt,输出loc_loss,有一点不太清楚loc_bottom_vec_是两个地址,后面怎么弄?
} else {
LOG(FATAL) << "Unknown localization loss type.";
}
// Set up confidence loss layer.
// 新建一个层,实现的是对confidence loss的计算
conf_loss_type_ = multibox_loss_param.conf_loss_type(); // SOFTMAX
conf_bottom_vec_.push_back(&conf_pred_); // conf_pred_ 是blob
conf_bottom_vec_.push_back(&conf_gt_); // conf_gt_ 是blob
conf_loss_.Reshape(loss_shape); // [1,4]
conf_top_vec_.push_back(&conf_loss_); // 也是一维向量
if (conf_loss_type_ == MultiBoxLossParameter_ConfLossType_SOFTMAX) {
CHECK_GE(background_label_id_, 0)
<< "background_label_id should be within [0, num_classes) for Softmax.";
CHECK_LT(background_label_id_, num_classes_)
<< "background_label_id should be within [0, num_classes) for Softmax.";
LayerParameter layer_param;
layer_param.set_name(this->layer_param_.name() + "_softmax_conf"); // mbox_loss_softmax_conf
layer_param.set_type("SoftmaxWithLoss");
layer_param.add_loss_weight(Dtype(1.)); // 1.0
layer_param.mutable_loss_param()->set_normalization(
LossParameter_NormalizationMode_NONE);
SoftmaxParameter* softmax_param = layer_param.mutable_softmax_param();
softmax_param->set_axis(1);
// Fake reshape.
vector<int> conf_shape(1, 1);
conf_gt_.Reshape(conf_shape); // [1]
conf_shape.push_back(num_classes_); // 这两个参数没有用到
conf_pred_.Reshape(conf_shape);
conf_loss_layer_ = LayerRegistry<Dtype>::CreateLayer(layer_param);
conf_loss_layer_->SetUp(conf_bottom_vec_, conf_top_vec_);
} else if (conf_loss_type_ == MultiBoxLossParameter_ConfLossType_LOGISTIC) {
LayerParameter layer_param;
layer_param.set_name(this->layer_param_.name() + "_logistic_conf");
layer_param.set_type("SigmoidCrossEntropyLoss");
layer_param.add_loss_weight(Dtype(1.));
// Fake reshape.
vector<int> conf_shape(1, 1);
conf_shape.push_back(num_classes_);
conf_gt_.Reshape(conf_shape);
conf_pred_.Reshape(conf_shape);
conf_loss_layer_ = LayerRegistry<Dtype>::CreateLayer(layer_param);
conf_loss_layer_->SetUp(conf_bottom_vec_, conf_top_vec_);
} else {
LOG(FATAL) << "Unknown confidence loss type.";
}
} // layer setup 结束
template <typename Dtype>
void MultiBoxLossLayer<Dtype>::Reshape(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
LossLayer<Dtype>::Reshape(bottom, top);
num_ = bottom[0]->num(); // batch num
num_priors_ = bottom[2]->height() / 4; // 这里的blob维度还需要再仔细分析下
num_gt_ = bottom[3]->height();
CHECK_EQ(bottom[0]->num(), bottom[1]->num());
CHECK_EQ(num_priors_ * loc_classes_ * 4, bottom[0]->channels()) // loc_classes_共享是1,不共享就是classes数
<< "Number of priors must match number of location predictions.";
CHECK_EQ(num_priors_ * num_classes_, bottom[1]->channels())
<< "Number of priors must match number of confidence predictions.";
}
// 预测loction bottom[0] dimension is [N*C*1*1],confidence bottom[1] dimension is [N*C*1*1]
// priors bottom[2] dimension is [N*1*2*W], gound truth bottom[3] dimension is [N*1*H*8]
template <typename Dtype>
void MultiBoxLossLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom,
const vector<Blob<Dtype>*>& top) {
const Dtype* loc_data = bottom[0]->cpu_data();
const Dtype* conf_data = bottom[1]->cpu_data();
const Dtype* prior_data = bottom[2]->cpu_data();
const Dtype* gt_data = bottom[3]->cpu_data();
// Retrieve all ground truth.
/*
message NormalizedBBox {
optional float xmin = 1;
optional float ymin = 2;
optional float xmax = 3;
optional float ymax = 4;
optional int32 label = 5;
optional bool difficult = 6;
optional float score = 7;
optional float size = 8;
}
*/
// Retrieve all ground truth.
map<int, vector<NormalizedBBox> > all_gt_bboxes; //转化ground truth bounding box,存放在all_gt_bboxes
GetGroundTruth(gt_data, num_gt_, background_label_id_, use_difficult_gt_, // background_label_id_=0,use_difficult_gt_=true
&all_gt_bboxes);
// Retrieve all prior bboxes. It is same within a batch since we assume all
// images in a batch are of same dimension.
// 把prior box 存入prior_bboxes,把variances存入prior_variances
vector<NormalizedBBox> prior_bboxes;
vector<vector<float> > prior_variances;
GetPriorBBoxes(prior_data, num_priors_, &prior_bboxes, &prior_variances);
// Retrieve all predictions.
vector<LabelBBox> all_loc_preds; // map<int, vector<NormalizedBBox> > LabelBBox;
GetLocPredictions(loc_data, num_, num_priors_, loc_classes_, share_location_,
&all_loc_preds); // 这里是把所有预测的box写入了all_loc_preds,这些box就是bottom[0],loc_data
// Find matches between source bboxes and ground truth bboxes.
vector<map<int, vector<float> > > all_match_overlaps;
FindMatches(all_loc_preds, all_gt_bboxes, prior_bboxes, prior_variances,
multibox_loss_param_, &all_match_overlaps, &all_match_indices_);
num_matches_ = 0;
int num_negs = 0;
// Sample hard negative (and positive) examples based on mining type.
MineHardExamples(*bottom[1], all_loc_preds, all_gt_bboxes, prior_bboxes,
prior_variances, all_match_overlaps, multibox_loss_param_,
&num_matches_, &num_negs, &all_match_indices_,
&all_neg_indices_);
if (num_matches_ >= 1) {
// Form data to pass on to loc_loss_layer_.
vector<int> loc_shape(2);
loc_shape[0] = 1;
loc_shape[1] = num_matches_ * 4;
loc_pred_.Reshape(loc_shape); // 地址已经存放进了loc_bottom_vec_
loc_gt_.Reshape(loc_shape);
Dtype* loc_pred_data = loc_pred_.mutable_cpu_data();
Dtype* loc_gt_data = loc_gt_.mutable_cpu_data();
EncodeLocPrediction(all_loc_preds, all_gt_bboxes, all_match_indices_,
prior_bboxes, prior_variances, multibox_loss_param_,
loc_pred_data, loc_gt_data);
loc_loss_layer_->Reshape(loc_bottom_vec_, loc_top_vec_);
loc_loss_layer_->Forward(loc_bottom_vec_, loc_top_vec_); // 前向计算
} else {
loc_loss_.mutable_cpu_data()[0] = 0;
} // 这里完成loc的loss前向计算
// Form data to pass on to conf_loss_layer_.
if (do_neg_mining_) { // 计算positive和negative样本
num_conf_ = num_matches_ + num_negs;
} else {
num_conf_ = num_ * num_priors_;
}
if (num_conf_ >= 1) {
// Reshape the confidence data.
vector<int> conf_shape;
if (conf_loss_type_ == MultiBoxLossParameter_ConfLossType_SOFTMAX) { // 选softmax
conf_shape.push_back(num_conf_);
conf_gt_.Reshape(conf_shape);
conf_shape.push_back(num_classes_);
conf_pred_.Reshape(conf_shape);
} else if (conf_loss_type_ == MultiBoxLossParameter_ConfLossType_LOGISTIC) {
conf_shape.push_back(1);
conf_shape.push_back(num_conf_);
conf_shape.push_back(num_classes_);
conf_gt_.Reshape(conf_shape);
conf_pred_.Reshape(conf_shape);
} else {
LOG(FATAL) << "Unknown confidence loss type.";
}
if (!do_neg_mining_) {
// Consider all scores.
// Share data and diff with bottom[1].
CHECK_EQ(conf_pred_.count(), bottom[1]->count());
conf_pred_.ShareData(*(bottom[1]));
}
Dtype* conf_pred_data = conf_pred_.mutable_cpu_data();
Dtype* conf_gt_data = conf_gt_.mutable_cpu_data();
caffe_set(conf_gt_.count(), Dtype(background_label_id_), conf_gt_data);
EncodeConfPrediction(conf_data, num_, num_priors_, multibox_loss_param_,
all_match_indices_, all_neg_indices_, all_gt_bboxes,
conf_pred_data, conf_gt_data);
conf_loss_layer_->Reshape(conf_bottom_vec_, conf_top_vec_);
conf_loss_layer_->Forward(conf_bottom_vec_, conf_top_vec_);
} else {
conf_loss_.mutable_cpu_data()[0] = 0;
} // 这里结束conf的loss计算
top[0]->mutable_cpu_data()[0] = 0;
if (this->layer_param_.propagate_down(0)) { // true 正则化一下 loc_loss
Dtype normalizer = LossLayer<Dtype>::GetNormalizer(
normalization_, num_, num_priors_, num_matches_);
top[0]->mutable_cpu_data()[0] +=
loc_weight_ * loc_loss_.cpu_data()[0] / normalizer;
}
if (this->layer_param_.propagate_down(1)) { // true conf_loss
Dtype normalizer = LossLayer<Dtype>::GetNormalizer(
normalization_, num_, num_priors_, num_matches_);
top[0]->mutable_cpu_data()[0] += conf_loss_.cpu_data()[0] / normalizer;
}
} // 结束Forward计算
template <typename Dtype>
void MultiBoxLossLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
const vector<bool>& propagate_down,
const vector<Blob<Dtype>*>& bottom) {
if (propagate_down[2]) {
LOG(FATAL) << this->type()
<< " Layer cannot backpropagate to prior inputs.";
}
if (propagate_down[3]) {
LOG(FATAL) << this->type()
<< " Layer cannot backpropagate to label inputs.";
}
// Back propagate on location prediction.
if (propagate_down[0]) { // 先回传 loc_loss
Dtype* loc_bottom_diff = bottom[0]->mutable_cpu_diff();
caffe_set(bottom[0]->count(), Dtype(0), loc_bottom_diff);
if (num_matches_ >= 1) {
vector<bool> loc_propagate_down;
// Only back propagate on prediction, not ground truth.
loc_propagate_down.push_back(true);
loc_propagate_down.push_back(false);
loc_loss_layer_->Backward(loc_top_vec_, loc_propagate_down,
loc_bottom_vec_);
// Scale gradient.
Dtype normalizer = LossLayer<Dtype>::GetNormalizer(
normalization_, num_, num_priors_, num_matches_);
Dtype loss_weight = top[0]->cpu_diff()[0] / normalizer;
caffe_scal(loc_pred_.count(), loss_weight, loc_pred_.mutable_cpu_diff());
// Copy gradient back to bottom[0].
const Dtype* loc_pred_diff = loc_pred_.cpu_diff();
int count = 0;
for (int i = 0; i < num_; ++i) {
for (map<int, vector<int> >::iterator it =
all_match_indices_[i].begin();
it != all_match_indices_[i].end(); ++it) {
const int label = share_location_ ? 0 : it->first;
const vector<int>& match_index = it->second;
for (int j = 0; j < match_index.size(); ++j) {
if (match_index[j] <= -1) {
continue;
}
// Copy the diff to the right place.
int start_idx = loc_classes_ * 4 * j + label * 4;
caffe_copy<Dtype>(4, loc_pred_diff + count * 4,
loc_bottom_diff + start_idx);
++count;
}
}
loc_bottom_diff += bottom[0]->offset(1);
}
}
}
// Back propagate on confidence prediction.
if (propagate_down[1]) {
Dtype* conf_bottom_diff = bottom[1]->mutable_cpu_diff();
caffe_set(bottom[1]->count(), Dtype(0), conf_bottom_diff);
if (num_conf_ >= 1) {
vector<bool> conf_propagate_down;
// Only back propagate on prediction, not ground truth.
conf_propagate_down.push_back(true);
conf_propagate_down.push_back(false);
conf_loss_layer_->Backward(conf_top_vec_, conf_propagate_down,
conf_bottom_vec_);
// Scale gradient.
Dtype normalizer = LossLayer<Dtype>::GetNormalizer(
normalization_, num_, num_priors_, num_matches_);
Dtype loss_weight = top[0]->cpu_diff()[0] / normalizer;
caffe_scal(conf_pred_.count(), loss_weight,
conf_pred_.mutable_cpu_diff());
// Copy gradient back to bottom[1].
const Dtype* conf_pred_diff = conf_pred_.cpu_diff();
if (do_neg_mining_) {
int count = 0;
for (int i = 0; i < num_; ++i) {
// Copy matched (positive) bboxes scores' diff.
const map<int, vector<int> >& match_indices = all_match_indices_[i];
for (map<int, vector<int> >::const_iterator it =
match_indices.begin(); it != match_indices.end(); ++it) {
const vector<int>& match_index = it->second;
CHECK_EQ(match_index.size(), num_priors_);
for (int j = 0; j < num_priors_; ++j) {
if (match_index[j] <= -1) {
continue;
}
// Copy the diff to the right place.
caffe_copy<Dtype>(num_classes_,
conf_pred_diff + count * num_classes_,
conf_bottom_diff + j * num_classes_);
++count;
}
}
// Copy negative bboxes scores' diff.
for (int n = 0; n < all_neg_indices_[i].size(); ++n) {
int j = all_neg_indices_[i][n];
CHECK_LT(j, num_priors_);
caffe_copy<Dtype>(num_classes_,
conf_pred_diff + count * num_classes_,
conf_bottom_diff + j * num_classes_);
++count;
}
conf_bottom_diff += bottom[1]->offset(1);
}
} else {
// The diff is already computed and stored.
bottom[1]->ShareDiff(conf_pred_);
}
}
}
// After backward, remove match statistics.
all_match_indices_.clear();
all_neg_indices_.clear();
}
INSTANTIATE_CLASS(MultiBoxLossLayer);
REGISTER_LAYER_CLASS(MultiBoxLoss);
} // namespace caffe