| | |
|---|
| | | #include "parser.h" |
|---|
| | | |
|---|
| | | |
|---|
| | | char *class_names[] = {"aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"}; |
|---|
| | | char *class_names[] = {"bg", "aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"}; |
|---|
| | | #define AMNT 3 |
|---|
| | | void draw_detection(image im, float *box, int side) |
|---|
| | | { |
|---|
| | | int classes = 20; |
|---|
| | | int classes = 21; |
|---|
| | | int elems = 4+classes; |
|---|
| | | int j; |
|---|
| | | int r, c; |
|---|
| | |
|---|
| | | { |
|---|
| | | 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); |
|---|
| | | } |
|---|
| | | //net.seen = 0; |
|---|
| | | printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay); |
|---|
| | | int imgs = 128; |
|---|
| | | srand(time(0)); |
|---|
| | |
|---|
| | | train = buffer; |
|---|
| | | load_thread = load_data_detection_thread(imgs, paths, plist->size, classes, im_dim, im_dim, 7, 7, jitter, background, &buffer); |
|---|
| | | |
|---|
| | | /* |
|---|
| | | image im = float_to_image(im_dim - jitter, im_dim-jitter, 3, train.X.vals[0]); |
|---|
| | | draw_detection(im, train.y.vals[0], 7); |
|---|
| | | /* |
|---|
| | | image im = float_to_image(im_dim - jitter, im_dim-jitter, 3, train.X.vals[114]); |
|---|
| | | draw_detection(im, train.y.vals[114], 7); |
|---|
| | | show_image(im, "truth"); |
|---|
| | | cvWaitKey(0); |
|---|
| | | */ |
|---|
| | | */ |
|---|
| | | |
|---|
| | | printf("Loaded: %lf seconds\n", sec(clock()-time)); |
|---|
| | | 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 num_output = 7*7*(4+classes+background); |
|---|
| | | int background = 0; |
|---|
| | | int nuisance = 1; |
|---|
| | | int num_output = 7*7*(4+classes+background+nuisance); |
|---|
| | | |
|---|
| | | 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){ |
|---|
| | | for(k = 0; k < pred.cols; k += classes+4+background+nuisance){ |
|---|
| | | float scale = 1.; |
|---|
| | | if(nuisance) scale = 1.-pred.vals[j][k]; |
|---|
| | | for(class = 0; class < classes; ++class){ |
|---|
| | | int index = (k)/(classes+4+background); |
|---|
| | | int index = (k)/(classes+4+background+nuisance); |
|---|
| | | int r = index/7; |
|---|
| | | int c = index%7; |
|---|
| | | int ci = k+classes+background; |
|---|
| | | 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 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, pred.vals[j][k+class+background], y, x, h, w); |
|---|
| | | 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); |
|---|
| | | } |
|---|
| | | } |
|---|
| | | } |
|---|
