| | |
| | | int count = 0; |
| | | box *boxes = read_boxes(labelpath, &count); |
| | | randomize_boxes(boxes, count); |
| | | float l,r,t,b; |
| | | float x,y,w,h; |
| | | int id; |
| | | int i; |
| | | if(background){ |
| | |
| | | } |
| | | } |
| | | for(i = 0; i < count; ++i){ |
| | | l = boxes[i].left; |
| | | r = boxes[i].right; |
| | | t = boxes[i].top; |
| | | b = boxes[i].bottom; |
| | | x = boxes[i].x; |
| | | y = boxes[i].y; |
| | | w = boxes[i].w; |
| | | h = boxes[i].h; |
| | | id = boxes[i].id; |
| | | |
| | | if(flip){ |
| | | float left = l; |
| | | float right = r; |
| | | r = 1-left; |
| | | l = 1-right; |
| | | x = 1-x; |
| | | } |
| | | |
| | | l = l*sx-dx; |
| | | r = r*sx-dx; |
| | | t = t*sy-dy; |
| | | b = b*sy-dy; |
| | | |
| | | float x = (l+r)/2.; |
| | | float y = (t+b)/2.; |
| | | x = x*sx-dx; |
| | | y = y*sy-dy; |
| | | w = w*sx; |
| | | h = h*sy; |
| | | |
| | | if (x < 0 || x >= 1 || y < 0 || y >= 1) continue; |
| | | |
| | | int i = (int)(x*num_boxes); |
| | | int j = (int)(y*num_boxes); |
| | | |
| | | l = constrain(0, 1, l); |
| | | r = constrain(0, 1, r); |
| | | t = constrain(0, 1, t); |
| | | b = constrain(0, 1, b); |
| | | x = x*num_boxes - i; |
| | | y = y*num_boxes - j; |
| | | |
| | | w = constrain(0, 1, w); |
| | | h = constrain(0, 1, h); |
| | | |
| | | int index = (i+j*num_boxes)*(4+classes+background); |
| | | if(truth[index+classes+background+2]) continue; |
| | | if(background) truth[index++] = 0; |
| | | truth[index+id] = 1; |
| | | index += classes; |
| | | truth[index++] = l; |
| | | truth[index++] = r; |
| | | truth[index++] = t; |
| | | truth[index++] = b; |
| | | truth[index++] = y; |
| | | truth[index++] = x; |
| | | truth[index++] = w; |
| | | truth[index++] = h; |
| | | } |
| | | free(boxes); |
| | | } |
| | |
| | | int classes = 20; |
| | | int background = 0; |
| | | int nuisance = 1; |
| | | int num_output = 7*7*(4+classes+background+nuisance); |
| | | int num_boxes = 7; |
| | | int per_box = 4+classes+background+nuisance; |
| | | int num_output = num_boxes*num_boxes*per_box; |
| | | |
| | | int m = plist->size; |
| | | int i = 0; |
| | |
| | | matrix pred = network_predict_data(net, val); |
| | | int j, k, class; |
| | | for(j = 0; j < pred.rows; ++j){ |
| | | for(k = 0; k < pred.cols; k += classes+4+background+nuisance){ |
| | | for(k = 0; k < pred.cols; k += per_box){ |
| | | float scale = 1.; |
| | | int index = k/per_box; |
| | | int row = index / num_boxes; |
| | | int col = index % num_boxes; |
| | | if (nuisance) scale = 1.-pred.vals[j][k]; |
| | | for (class = 0; class < classes; ++class){ |
| | | int ci = k+classes+background+nuisance; |
| | | float left = pred.vals[j][ci + 0]; |
| | | float right = pred.vals[j][ci + 1]; |
| | | float top = pred.vals[j][ci + 2]; |
| | | float bot = pred.vals[j][ci + 3]; |
| | | printf("%d %d %f %f %f %f %f\n", (i-1)*m/splits + j, class, scale*pred.vals[j][k+class+background+nuisance], left, right, top, bot); |
| | | float y = (pred.vals[j][ci + 0] + row)/num_boxes; |
| | | float x = (pred.vals[j][ci + 1] + col)/num_boxes; |
| | | float h = pred.vals[j][ci + 2]; |
| | | float w = pred.vals[j][ci + 3]; |
| | | printf("%d %d %f %f %f %f %f\n", (i-1)*m/splits + j, class, scale*pred.vals[j][k+class+background+nuisance], y, x, h, w); |
| | | } |
| | | } |
| | | } |