void *detect_in_thread(void *ptr)
{
float nms = .4;
layer l = net.layers[net.n-1];
float *X = det_s.data;
float *prediction = network_predict(net, X);
memcpy(predictions[demo_index], prediction, l.outputs*sizeof(float));
mean_arrays(predictions, FRAMES, l.outputs, avg);
l.output = avg;
free_image(det_s);
if(l.type == DETECTION){
get_detection_boxes(l, 1, 1, demo_thresh, probs, boxes, 0);
} else if (l.type == REGION){
get_region_boxes(l, 1, 1, demo_thresh, probs, boxes, 0, 0, demo_hier_thresh);
} else {
error("Last layer must produce detections\n");
}
if (nms > 0) do_nms(boxes, probs, l.w*l.h*l.n, l.classes, nms);
printf("\033[2J");
printf("\033[1;1H");
printf("\nFPS:%.1f\n",fps);
printf("Objects:\n\n");
images[demo_index] = det;
det = images[(demo_index + FRAMES/2 + 1)%FRAMES];
demo_index = (demo_index + 1)%FRAMES;
draw_detections(det, l.w*l.h*l.n, demo_thresh, boxes, probs, demo_names, demo_alphabet, demo_classes);
return 0;
}
void *detect_in_thread(void *ptr)
{
running = 1;
float nms = .4;
layer l = net.layers[net.n-1];
float *X = buff_letter[(buff_index+2)%3].data;
float *prediction = network_predict(net, X);
memcpy(predictions[demo_index], prediction, l.outputs*sizeof(float));
mean_arrays(predictions, demo_frame, l.outputs, avg);
l.output = last_avg2;
if(demo_delay == 0) l.output = avg;
if(l.type == DETECTION){
get_detection_boxes(l, 1, 1, demo_thresh, probs, boxes, 0);
} else if (l.type == REGION){
get_region_boxes(l, buff[0].w, buff[0].h, net.w, net.h, demo_thresh, probs, boxes, 0, 0, demo_hier, 1);
} else {
error("Last layer must produce detections\n");
}
if (nms > 0) do_nms_obj(boxes, probs, l.w*l.h*l.n, l.classes, nms);
printf("\033[2J");
printf("\033[1;1H");
printf("\nFPS:%.1f\n",fps);
printf("Objects:\n\n");
image display = buff[(buff_index+2) % 3];
draw_detections(display, demo_detections, demo_thresh, boxes, probs, demo_names, demo_alphabet, demo_classes);
demo_index = (demo_index + 1)%demo_frame;
running = 0;
return 0;
}
void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, float hier_thresh)
{
int show_flag = 1;
list *options = read_data_cfg(datacfg);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
image **alphabet = load_alphabet();
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
srand(2222222);
clock_t time;
char buff[256];
char *input = buff;
int j;
float nms=.4;
while(1){
if(filename){
strncpy(input, filename, 256);
} else {
printf("Enter Image Path: ");
fflush(stdout);
input = fgets(input, 256, stdin);
if(!input) return;
strtok(input, "\n");
}
image im = load_image_color(input,0,0);
image sized = resize_image(im, net.w, net.h);
layer l = net.layers[net.n-1];
box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(l.classes + 1, sizeof(float *));
float *X = sized.data;
time=clock();
network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
get_region_boxes(l, 1, 1, thresh, probs, boxes, 0, 0, hier_thresh);
if (l.softmax_tree && nms) do_nms_obj(boxes, probs, l.w*l.h*l.n, l.classes, nms);
else if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, l.classes, nms);
draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, names, alphabet, l.classes, show_flag);
save_image(im, "predictions");
show_image(im, "predictions");
free_image(im);
free_image(sized);
free(boxes);
free_ptrs((void **)probs, l.w*l.h*l.n);
#ifdef OPENCV
cvWaitKey(0);
cvDestroyAllWindows();
#endif
if (filename) break;
}
}
void custom_get_region_detections(layer l, int w, int h, int net_w, int net_h, float thresh, int *map, float hier, int relative, detection *dets, int letter)
{
box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
int i, j;
for (j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(l.classes, sizeof(float));
get_region_boxes(l, 1, 1, thresh, probs, boxes, 0, map);
for (j = 0; j < l.w*l.h*l.n; ++j) {
dets[j].classes = l.classes;
dets[j].bbox = boxes[j];
dets[j].objectness = 1;
for (i = 0; i < l.classes; ++i) {
dets[j].prob[i] = probs[j][i];
}
}
free(boxes);
free_ptrs((void **)probs, l.w*l.h*l.n);
//correct_region_boxes(dets, l.w*l.h*l.n, w, h, net_w, net_h, relative);
correct_yolo_boxes(dets, l.w*l.h*l.n, w, h, net_w, net_h, relative, letter);
}
void validate_detector_recall(char *cfgfile, char *weightfile)
{
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
srand(time(0));
list *plist = get_paths("data/voc.2007.test");
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n-1];
int classes = l.classes;
int j, k;
box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
int m = plist->size;
int i=0;
float thresh = .001;
float iou_thresh = .5;
float nms = .4;
int total = 0;
int correct = 0;
int proposals = 0;
float avg_iou = 0;
for(i = 0; i < m; ++i){
char *path = paths[i];
image orig = load_image_color(path, 0, 0);
image sized = resize_image(orig, net.w, net.h);
char *id = basecfg(path);
network_predict(net, sized.data);
get_region_boxes(l, 1, 1, thresh, probs, boxes, 1, 0, .5);
if (nms) do_nms(boxes, probs, l.w*l.h*l.n, 1, nms);
char labelpath[4096];
find_replace(path, "images", "labels", labelpath);
find_replace(labelpath, "JPEGImages", "labels", labelpath);
find_replace(labelpath, ".jpg", ".txt", labelpath);
find_replace(labelpath, ".JPEG", ".txt", labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
for(k = 0; k < l.w*l.h*l.n; ++k){
if(probs[k][0] > thresh){
++proposals;
}
}
for (j = 0; j < num_labels; ++j) {
++total;
box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
float best_iou = 0;
for(k = 0; k < l.w*l.h*l.n; ++k){
float iou = box_iou(boxes[k], t);
if(probs[k][0] > thresh && iou > best_iou){
best_iou = iou;
}
}
avg_iou += best_iou;
if(best_iou > iou_thresh){
++correct;
}
}
fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\n", i, correct, total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct/total);
free(id);
free_image(orig);
free_image(sized);
}
}
void validate_detector(char *datacfg, char *cfgfile, char *weightfile, char *outfile)
{
int j;
list *options = read_data_cfg(datacfg);
char *valid_images = option_find_str(options, "valid", "data/train.list");
char *name_list = option_find_str(options, "names", "data/names.list");
char *prefix = option_find_str(options, "results", "results");
char **names = get_labels(name_list);
char *mapf = option_find_str(options, "map", 0);
int *map = 0;
if (mapf) map = read_map(mapf);
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
srand(time(0));
list *plist = get_paths(valid_images);
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n-1];
int classes = l.classes;
char buff[1024];
char *type = option_find_str(options, "eval", "voc");
FILE *fp = 0;
FILE **fps = 0;
int coco = 0;
int imagenet = 0;
if(0==strcmp(type, "coco")){
if(!outfile) outfile = "coco_results";
snprintf(buff, 1024, "%s/%s.json", prefix, outfile);
fp = fopen(buff, "w");
fprintf(fp, "[\n");
coco = 1;
} else if(0==strcmp(type, "imagenet")){
if(!outfile) outfile = "imagenet-detection";
snprintf(buff, 1024, "%s/%s.txt", prefix, outfile);
fp = fopen(buff, "w");
imagenet = 1;
classes = 200;
} else {
if(!outfile) outfile = "comp4_det_test_";
fps = calloc(classes, sizeof(FILE *));
for(j = 0; j < classes; ++j){
snprintf(buff, 1024, "%s/%s%s.txt", prefix, outfile, names[j]);
fps[j] = fopen(buff, "w");
}
}
box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
int m = plist->size;
int i=0;
int t;
float thresh = .005;
float nms = .45;
int nthreads = 4;
image *val = calloc(nthreads, sizeof(image));
image *val_resized = calloc(nthreads, sizeof(image));
image *buf = calloc(nthreads, sizeof(image));
image *buf_resized = calloc(nthreads, sizeof(image));
pthread_t *thr = calloc(nthreads, sizeof(pthread_t));
load_args args = {0};
args.w = net.w;
args.h = net.h;
args.type = IMAGE_DATA;
for(t = 0; t < nthreads; ++t){
args.path = paths[i+t];
args.im = &buf[t];
args.resized = &buf_resized[t];
thr[t] = load_data_in_thread(args);
}
time_t start = time(0);
for(i = nthreads; i < m+nthreads; i += nthreads){
fprintf(stderr, "%d\n", i);
for(t = 0; t < nthreads && i+t-nthreads < m; ++t){
pthread_join(thr[t], 0);
val[t] = buf[t];
val_resized[t] = buf_resized[t];
}
for(t = 0; t < nthreads && i+t < m; ++t){
args.path = paths[i+t];
args.im = &buf[t];
args.resized = &buf_resized[t];
thr[t] = load_data_in_thread(args);
}
for(t = 0; t < nthreads && i+t-nthreads < m; ++t){
char *path = paths[i+t-nthreads];
char *id = basecfg(path);
float *X = val_resized[t].data;
network_predict(net, X);
int w = val[t].w;
int h = val[t].h;
get_region_boxes(l, w, h, thresh, probs, boxes, 0, map, .5);
if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, classes, nms);
if (coco){
print_cocos(fp, path, boxes, probs, l.w*l.h*l.n, classes, w, h);
} else if (imagenet){
print_imagenet_detections(fp, i+t-nthreads+1, boxes, probs, l.w*l.h*l.n, classes, w, h);
} else {
print_detector_detections(fps, id, boxes, probs, l.w*l.h*l.n, classes, w, h);
}
free(id);
free_image(val[t]);
free_image(val_resized[t]);
}
}
for(j = 0; j < classes; ++j){
if(fps) fclose(fps[j]);
}
if(coco){
fseek(fp, -2, SEEK_CUR);
fprintf(fp, "\n]\n");
fclose(fp);
}
fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
}
std::vector< detected_object > ofxDarknet::yolo( ofPixels & pix, float threshold /*= 0.24f */, float maxOverlap /*= 0.5f */ )
{
int originalWidth = pix.getWidth();
int originalHeight = pix.getHeight();
ofPixels pix2( pix );
if (pix2.getImageType() != OF_IMAGE_COLOR) {
pix2.setImageType(OF_IMAGE_COLOR);
}
if( pix2.getWidth() != net.w && pix2.getHeight() != net.h ) {
pix2.resize( net.w, net.h );
}
image im = convert( pix2 );
layer l = net.layers[ net.n - 1 ];
box *boxes = ( box* ) calloc( l.w*l.h*l.n, sizeof( box ) );
float **probs = ( float** ) calloc( l.w*l.h*l.n, sizeof( float * ) );
for( int j = 0; j < l.w*l.h*l.n; ++j ) probs[ j ] = ( float* ) calloc( l.classes, sizeof( float * ) );
network_predict( net, im.data1 );
get_region_boxes( l, 1, 1, threshold, probs, boxes, 0, 0 );
do_nms_sort( boxes, probs, l.w*l.h*l.n, l.classes, 0.4 );
free_image( im );
std::vector< detected_object > detections;
int num = l.w*l.h*l.n;
int feature_layer = net.n - 2;
layer l1 = net.layers[ feature_layer ];
float * features = get_network_output_layer_gpu(feature_layer);
vector<size_t> sorted(num);
iota(sorted.begin(), sorted.end(), 0);
sort(sorted.begin(), sorted.end(), [&probs, &l](int i1, int i2) {
return probs[i1][max_index(probs[i1], l.classes)] > probs[i2][max_index(probs[i2], l.classes)];
});
for( int i = 0; i < num; ++i ) {
int idx = sorted[i];
int class1 = max_index( probs[ idx ], l.classes );
float prob = probs[ idx ][ class1 ];
if( prob < threshold ) {
continue;
}
int offset = class1 * 123457 % l.classes;
float red = get_color( 2, offset, l.classes );
float green = get_color( 1, offset, l.classes );
float blue = get_color( 0, offset, l.classes );
box b = boxes[ idx ];
int left = ( b.x - b.w / 2. )*im.w;
int right = ( b.x + b.w / 2. )*im.w;
int top = ( b.y - b.h / 2. )*im.h;
int bot = ( b.y + b.h / 2. )*im.h;
if( left < 0 ) left = 0;
if( right > im.w - 1 ) right = im.w - 1;
if( top < 0 ) top = 0;
if( bot > im.h - 1 ) bot = im.h - 1;
left = ofMap( left, 0, net.w, 0, originalWidth );
top = ofMap( top, 0, net.h, 0, originalHeight );
right = ofMap( right, 0, net.w, 0, originalWidth );
bot = ofMap( bot, 0, net.h, 0, originalHeight );
ofRectangle rect = ofRectangle( left, top, right - left, bot - top );
int rect_idx = floor(idx / l.n);
float overlap = 0.0;
for (auto d : detections) {
float left = max(rect.x, d.rect.x);
float right = min(rect.x+rect.width, d.rect.x+d.rect.width);
float bottom = min(rect.y+rect.height, d.rect.y+d.rect.height);
float top = max(rect.y, d.rect.y);
float area_intersection = max(0.0f, right-left) * max(0.0f, bottom-top);
overlap = max(overlap, area_intersection / (rect.getWidth() * rect.getHeight()));
}
if (overlap > maxOverlap) {
continue;
}
detected_object detection;
detection.label = names[ class1 ];
detection.probability = prob;
detection.rect = rect;
detection.color = ofColor( red * 255, green * 255, blue * 255);
for (int f=0; f<l1.c; f++) {
detection.features.push_back(features[rect_idx + l1.w * l1.h * f]);
}
detections.push_back( detection );
}
free_ptrs((void**) probs, num);
free(boxes);
return detections;
}
