标签：content center ready tom 5.0 one span ssd shared
https://www.jianshu.com/p/5195165bbd06
1.step_w、step_h其实就相当于faster中的feat_stride,也就是把这些点从feature map映射回原图,同时也可以看出min_size、max_size这些都是直接在针对原图来讲的
2.以mobileNet-ssd为例子:https://github.com/chuanqi305/MobileNet-SSD/blob/master/train.prototxt
layer { name: "conv11_mbox_priorbox" type: "PriorBox" bottom: "conv11" bottom: "data" top: "conv11_mbox_priorbox" prior_box_param { min_size: 60.0 aspect_ratio: 2.0 flip: true clip: false variance: 0.1 variance: 0.1 variance: 0.2 variance: 0.2 offset: 0.5 } }
layer { name: "conv13_mbox_priorbox" type: "PriorBox" bottom: "conv13" bottom: "data" top: "conv13_mbox_priorbox" prior_box_param { min_size: 105.0 max_size: 150.0 aspect_ratio: 2.0 aspect_ratio: 3.0 flip: true clip: false variance: 0.1 variance: 0.1 variance: 0.2 variance: 0.2 offset: 0.5 } }
只有conv11的anchor个数是3,其他5层都是6,原因是conv11只有min_size,没有max_size,并且aspect_ratio只有1个,其他5层都是两个,也就是说conv11是1+1*2=3,其他5层是1+1+2*2=6
prior_box_layer.cpp里,aspect_ratios_根据这层的param存储相应的aspect ratio.如果flip为true,param里一个aspect ratio就要存储他本身和他的倒数两个值
aspect_ratios_.clear(); aspect_ratios_.push_back(1.); flip_ = prior_box_param.flip(); for (int i = 0; i < prior_box_param.aspect_ratio_size(); ++i) { float ar = prior_box_param.aspect_ratio(i); bool already_exist = false; for (int j = 0; j < aspect_ratios_.size(); ++j) { //检查是否有重复的 if (fabs(ar - aspect_ratios_[j]) < 1e-6) { already_exist = true; break; } } if (!already_exist) { aspect_ratios_.push_back(ar); //如果flip为true,存储aspect ratio和他的倒数,否则只存储aspect ratio本身 if (flip_) { aspect_ratios_.push_back(1./ar); } } }
对于每个点,先计算以min_size为长宽的正方形这个anchor;然后如果有max_size,计算以sqrt(min_size_ * max_size_)为长宽的正方形;然后计算aspect_ratios_中所有的aspect ratios,然后以这个aspect ratios计算box_width = min_size_ * sqrt(ar)和box_height = min_size_ / sqrt(ar),prototxt中的param里,一个ratio要存储他和他的倒数,这样一个ratio就要求两个anchor
for (int h = 0; h < layer_height; ++h) { for (int w = 0; w < layer_width; ++w) { float center_x = (w + offset_) * step_w; float center_y = (h + offset_) * step_h; float box_width, box_height; for (int s = 0; s < min_sizes_.size(); ++s) { int min_size_ = min_sizes_[s]; // first prior: aspect_ratio = 1, size = min_size box_width = box_height = min_size_; // xmin top_data[idx++] = (center_x - box_width / 2.) / img_width; // ymin top_data[idx++] = (center_y - box_height / 2.) / img_height; // xmax top_data[idx++] = (center_x + box_width / 2.) / img_width; // ymax top_data[idx++] = (center_y + box_height / 2.) / img_height; if (max_sizes_.size() > 0) { CHECK_EQ(min_sizes_.size(), max_sizes_.size()); int max_size_ = max_sizes_[s]; // second prior: aspect_ratio = 1, size = sqrt(min_size * max_size) box_width = box_height = sqrt(min_size_ * max_size_); // xmin top_data[idx++] = (center_x - box_width / 2.) / img_width; // ymin top_data[idx++] = (center_y - box_height / 2.) / img_height; // xmax top_data[idx++] = (center_x + box_width / 2.) / img_width; // ymax top_data[idx++] = (center_y + box_height / 2.) / img_height; } // rest of priors for (int r = 0; r < aspect_ratios_.size(); ++r) { float ar = aspect_ratios_[r]; if (fabs(ar - 1.) < 1e-6) { continue; } box_width = min_size_ * sqrt(ar); box_height = min_size_ / sqrt(ar); // xmin top_data[idx++] = (center_x - box_width / 2.) / img_width; // ymin top_data[idx++] = (center_y - box_height / 2.) / img_height; // xmax top_data[idx++] = (center_x + box_width / 2.) / img_width; // ymax top_data[idx++] = (center_y + box_height / 2.) / img_height; } } } }
3.从reshape可以看出,输出的shape是(1,2,layer_width * layer_height * num_priors_ * 4),layer_width * layer_height * num_priors_ * 4是每个feature map上每个点乘以anchor数,再每个anchor乘以对应的4个坐标,比如整个blob中第一个4个值存储的就是feature map中第一个像素点的min size对应的正方形那个anchor的4个坐标值,第二个就是第一个像素点对应的max size对应的anchor的4个坐标值
void PriorBoxLayer<Dtype>::Reshape(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) { const int layer_width = bottom[0]->width(); const int layer_height = bottom[0]->height(); vector<int> top_shape(3, 1); // Since all images in a batch has same height and width, we only need to // generate one set of priors which can be shared across all images. top_shape[0] = 1; // 2 channels. First channel stores the mean of each prior coordinate. // Second channel stores the variance of each prior coordinate. top_shape[1] = 2; top_shape[2] = layer_width * layer_height * num_priors_ * 4; CHECK_GT(top_shape[2], 0); top[0]->Reshape(top_shape); }
注意到,输出是2channel的,第一个channel就是存储的真实的每个anchor的4个坐标,第二个channel存储的就是variance,variance_在layer_setup里面就初始化了4个值,这4个值就是来自于prototxt的param.这4个值分别对应4个坐标点,对于每个anchor,都会有对应这4个variance值,这些值存储在第二个channel,并且在第二个channel里面每4个值每4个值重复
top_data += top[0]->offset(0, 1); if (variance_.size() == 1) { caffe_set<Dtype>(dim, Dtype(variance_[0]), top_data); } else { int count = 0; for (int h = 0; h < layer_height; ++h) { for (int w = 0; w < layer_width; ++w) { for (int i = 0; i < num_priors_; ++i) { for (int j = 0; j < 4; ++j) { top_data[count] = variance_[j]; ++count; } } } } }
4.http://www.360doc.com/content/17/0810/10/10408243_678091430.shtml
这两段代码都来自于bbox_util.cpp的DecodeBBox函数.prior_box层输出的prior_variance就是一个系数,这个系数乘以bounding box regression的回归值,在faster中,是直接在anchor的坐标上加bounding box regression,ssd这里可以对回归乘以一个系数.当然DecodeBBox其实也可以使用faster那种方式,可以通过参数控制
else { // variance is encoded in bbox, we need to scale the offset accordingly. decode_bbox->set_xmin( prior_bbox.xmin() + prior_variance[0] * bbox.xmin()); decode_bbox->set_ymin( prior_bbox.ymin() + prior_variance[1] * bbox.ymin()); decode_bbox->set_xmax( prior_bbox.xmax() + prior_variance[2] * bbox.xmax()); decode_bbox->set_ymax( prior_bbox.ymax() + prior_variance[3] * bbox.ymax()); }
else { // variance is encoded in bbox, we need to scale the offset accordingly. decode_bbox->set_xmin( prior_bbox.xmin() + prior_variance[0] * bbox.xmin() * prior_width); decode_bbox->set_ymin( prior_bbox.ymin() + prior_variance[1] * bbox.ymin() * prior_height); decode_bbox->set_xmax( prior_bbox.xmax() + prior_variance[2] * bbox.xmax() * prior_width); decode_bbox->set_ymax( prior_bbox.ymax() + prior_variance[3] * bbox.ymax() * prior_height); }
标签：content center ready tom 5.0 one span ssd shared
原文地址：https://www.cnblogs.com/ymjyqsx/p/9230939.html
