'results', model_name)
#con'figs_det = det.load_configs(model_name='fpn_resnet')
datafile = WaymoDataFileReader(data_fullpath)
datafile_iter = iter(datafile) # initialize dataset iterator
## Initialize object detection
configs_det = det.load_configs(
model_name) # options are 'darknet', 'fpn_resnet'
model_det = det.create_model(configs_det)
configs_det.use_labels_as_objects = False # True = use groundtruth labels as objects, False = use model-based detection
configs_det.save_results = False
print(configs_det.use_labels_as_objects)
## Initialize tracking
KF = Filter() # set up Kalman filter
association = Association() # init data association
manager = Trackmanagement() # init track manager
lidar = None # init lidar sensor object
camera = None # init camera sensor object
## Selective execution and visualization
exec_data = ['pcl_from_rangeimage'] #ID_S2_EX1, ID_S'2_EX2, S4
#exec_data = ['pcl_from_rangeimage', 'load_image'] #ID_S3_EX1
#exec_detection = [] # ID_S1_EX1,2 options are 'bev_from_pcl', 'detect_objects', 'validate_object_labels', 'measure_detection_performance'; options not in the list will be loaded from file
exec_tracking = [
] # options are 'perform_tracking' ID_S1_EX1,2, ID_S2_EX1,2,3, S3_EX1, S4
exec_detection = ['bev_from_pcl'] #ID_S2_EX1, ID_S2_EX2,3
#exec_detection = ['bev_from_pcl', 'detect_objects'] #ID_S3_EX1
#exec_detection = ['bev_from_pcl', 'detect_objects', 'validate_object_labels', 'measure_detection_performance'] #S4
#exec_visualization = ['show_detection_performance'] #S4