Mmodlist May 2026

# List of images (numpy arrays or dlib array2d) images = [img1, img2, ...] boxes_per_image = [ [mmod_rect(...), mmod_rect(...)], # image 0 [mmod_rect(...)], # image 1 [] # image 2 (no objects) ] Example construction: import dlib def load_mmodlist_from_annotation(image_path, annotation_dict): img = dlib.load_rgb_image(image_path) rects = [] for obj in annotation_dict['objects']: r = dlib.rectangle( left=obj['x'], top=obj['y'], right=obj['x']+obj['w'], bottom=obj['y']+obj['h'] ) # label: 0 for 'car', 1 for 'pedestrian', etc. m = dlib.mmod_rect(r, label=obj['class_id'], ignore=obj.get('ignore', False)) rects.append(m) return rects 4. Training a MMOD Detector with mmodlist Once you have images and mmodlists , training is:

Under the hood, train_simple_object_detector converts mmodlist into the internal MMOD loss format. The ignore flag is critical for hard examples: mmodlist

std::vector<mmod_rect> mmodlist; mmod_rect mr; mr.rect = rectangle(10,20,50,80); mr.label = 0; mr.ignore = false; mmodlist.push_back(mr); # List of images (numpy arrays or dlib

detector = dlib.train_simple_object_detector(images, mmodlists, options) img = dlib.load_rgb_image("test.jpg") dets = detector(img) for det in dets: print(f"Class det.label at det.rect, score det.detection_confidence") The ignore flag is critical for hard examples:

for xml_file in glob.glob("annotations/*.xml"): # Load dlib's XML format (which uses mmod_rect internally) rects = dlib.load_image_dataset(images, xml_file, "image") # rects is already list of mmod_rect mmodlists.append(rects)

options = dlib.simple_object_detector_training_options() options.C = 1 options.num_threads = 8 options.add_left_right_image_flips = True

1. What is mmodlist ? mmodlist (short for Max-Margin Object Detection List ) is not a standalone class but a specific data format used by dlib’s fhog_object_detector and loss_mmod_ layers. It is a list of mmod_rect objects.