| | |
| | | float blue = get_color(2,class,classes); |
| | | |
| | | j += classes; |
| | | int d = im.w/side; |
| | | int y = r*d+box[j]*d; |
| | | int x = c*d+box[j+1]*d; |
| | | int h = box[j+2]*im.h; |
| | | int w = box[j+3]*im.w; |
| | | draw_box(im, x-w/2, y-h/2, x+w/2, y+h/2,red,green,blue); |
| | | int left = box[j] *im.w; |
| | | int right = box[j+1]*im.w; |
| | | int top = box[j+2]*im.h; |
| | | int bot = box[j+3]*im.h; |
| | | draw_box(im, left, top, right, bot, red, green, blue); |
| | | } |
| | | } |
| | | } |
| | |
| | | { |
| | | char *base = basecfg(cfgfile); |
| | | printf("%s\n", base); |
| | | float avg_loss = 1; |
| | | float avg_loss = -1; |
| | | network net = parse_network_cfg(cfgfile); |
| | | if(weightfile){ |
| | | load_weights(&net, weightfile); |
| | |
| | | time=clock(); |
| | | float loss = train_network(net, train); |
| | | net.seen += imgs; |
| | | if (avg_loss < 0) avg_loss = loss; |
| | | avg_loss = avg_loss*.9 + loss*.1; |
| | | printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), i*imgs); |
| | | if(i%100==0){ |
| | |
| | | char **paths = (char **)list_to_array(plist); |
| | | int im_size = 448; |
| | | int classes = 20; |
| | | int background = 1; |
| | | int nuisance = 0; |
| | | int num_output = 7*7*(4+classes+background+nuisance); |
| | | int background = 0; |
| | | int nuisance = 1; |
| | | 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.; |
| | | if(nuisance) scale = pred.vals[j][k]; |
| | | for(class = 0; class < classes; ++class){ |
| | | int index = (k)/(classes+4+background+nuisance); |
| | | int r = index/7; |
| | | int c = index%7; |
| | | 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 y = (r + pred.vals[j][ci + 0])/7.; |
| | | float x = (c + pred.vals[j][ci + 1])/7.; |
| | | 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); |