整体源码如下,该源码是利用yolo训练检测网络时,对输入数据作前处理的源代码,该代码段中包含了从外部传入的超参数(jitter),也有内部写死的超参数(scale)。下面将对该代码做详细的解析。
data load_data_detection(int n, char **paths, int m, int w, int h, int boxes, int classes, float jitter, float hue, float saturation, float exposure)
{
char **random_paths = get_random_paths(paths, n, m);
int i;
data d = {0};
d.shallow = 0;
d.X.rows = n;
d.X.vals = calloc(d.X.rows, sizeof(float*));
d.X.cols = h*w*3;
d.y = make_matrix(n, 5*boxes);
for(i = 0; i < n; ++i){
image orig = load_image_color(random_paths[i], 0, 0);
image sized = make_image(w, h, orig.c);
fill_image(sized, .5);
float dw = jitter * orig.w;
float dh = jitter * orig.h;
float new_ar = (orig.w + rand_uniform(-dw, dw)) / (orig.h + rand_uniform(-dh, dh));
//float scale = rand_uniform(.25, 2);
float scale = 1;
float nw, nh;
if(new_ar < 1){
nh = scale * h;
nw = nh * new_ar;
} else {
nw = scale * w;
nh = nw / new_ar;
}
float dx = rand_uniform(0, w - nw);
float dy = rand_uniform(0, h - nh);
place_image(orig, nw, n