/*
* 参数解释
* bottom_data:输入的特征图数据,shape是(n,c,h,w)
* bottom_rois:输入的roi数据,shape是(num_rois,5),第一维表示共有多少个rois,第二维是[batch_index,x1,y1,x2,y2],
第一个值表示rois所在的batch_id,后四个是rois所在原图的坐标值,可以根据spatial_scale对应到特征图上
* nthreads:等于roipooling后输出的size,即num_rois*channels*pooled_height*pooled_width
* pooled_height:RoIAlign后的height
* pooled_width:RoIAlign后的width\
* channels:输入特征图的channels,输入输出前后不变
* height:输入特征图的height
* width:输入特征图的width
* spatial_scale:原图与特征图比例,等于特征图/原图,如1/16
* sampling_ratio:bin中高和宽方向的采样率,论文中默认是2,即每个bin采样2*2=4个点
* top_data:roipooling后的输入,shape是(num_rois,channels,pooled_height,pooled_width)
*/
template <typename T>
__global__ void RoIAlignForward(
const int nthreads,
const T* bottom_data,
const T spatial_scale,
const int channels,
const int height,
const int width,
const int pooled_height,
const int pooled_width,
const int sampling_ratio,
const T* bottom_rois,
T* top_data) {
CUDA_1D_KERNEL_LOOP(index, nthreads) {
// (n, c, ph, pw) is an element in the pooled output
int pw = index % pooled_width;
int ph = (index / pooled_width) % pooled_height;
int c = (index / pooled_width / pooled_height) % channels;
int n = index / pooled_width / pooled_height / channels;
//index对应的索引,即(n,c,ph,pw)分别代表(num_rois,channels,pooled_height,pooled_width)的索引
const T* offset_bottom_rois = bottom_rois + n * 5;
int roi_batch_ind = offset_bottom_rois[0];//0维表示batch_id
// Do not using rounding; this implementation detail is critical
T roi_start_w = offset_bottom_rois[1] * spatial_scale;//将原图的坐标映射到特征图上的坐标
T roi_start_h = offset_bottom_rois[2] * spatial_scale;
T roi_end_w = offset_bottom_rois[3] * spatial_scale;
T roi_end_h = offset_bottom_rois[4] * spatial_scale;
// T roi_start_w = round(offset_bottom_rois[1] * spatial_scale);不使用round,就没有引入量化损失
// T roi_start_h = round(offset_bottom_rois[2] * spatial_scale);
// T roi_end_w = round(offset_bottom_rois[3] * spatial_scale);
// T roi_end_h = round(offset_bottom_rois[4] * spatial_scale);
// Force malformed ROIs to be 1x1
T roi_width = max(roi_end_w - roi_start_w, (T)1.);//特征图上的roi的宽
T roi_height = max(roi_end_h - roi_start_h, (T)1.);//特征图上的roi的高
T bin_size_h = static_cast<T>(roi_height) / static_cast<T>(pooled_height);//将rois划分成pooled_height*pooled_width个bin
T bin_size_w = static_cast<T>(roi_width) / static_cast<T>(pooled_width);//计算得到每个bin的h和w
const T* offset_bottom_data =
bottom_data + (roi_batch_ind * channels + c) * height * width;
// We use roi_bin_grid to sample the grid and mimic integral
// 采样率,论文中默认是2,如果没有设置则等于ceil(roi_height / pooled_height),大概约等于每个bin里有几个格子就采样几个点
int roi_bin_grid_h = (sampling_ratio > 0)
? sampling_ratio
: ceil(roi_height / pooled_height); // e.g., = 2
int roi_bin_grid_w =
(sampling_ratio > 0) ? sampling_ratio : ceil(roi_width / pooled_width);
// We do average (integral) pooling inside a bin
const T count = roi_bin_grid_h * roi_bin_grid_w; // e.g. = 4
T output_val = 0.;
for (int iy = 0; iy < roi_bin_grid_h; iy++) // e.g., iy = 0, 1
{
// 在height方向采样
const T y = roi_start_h + ph * bin_size_h +
static_cast<T>(iy + .5f) * bin_size_h /
static_cast<T>(roi_bin_grid_h); // e.g., 0.5, 1.5
// 在width方向采样
for (int ix = 0; ix < roi_bin_grid_w; ix++) {
const T x = roi_start_w + pw * bin_size_w +
static_cast<T>(ix + .5f) * bin_size_w /
static_cast<T>(roi_bin_grid_w);
// 被采样到的点由于坐标是浮点数,其对应位置的值需要双线性插值获取(最近的4个点得到)
T val = bilinear_interpolate(
offset_bottom_data, height, width, y, x, index);
output_val += val;
}
}
output_val /= count;
top_data[index] = output_val;
}
}
} // namespace
RoiAlign源码解析
最新推荐文章于 2023-07-14 15:09:26 发布