def main(): parser = argparse.ArgumentParser() parser.add_argument('--in_root', default=os.path.join(fs_root(), 'data/learnlarge/merged_parametrized')) parser.add_argument('--folds', default=['train', 'val', 'test', 'full']) parser.add_argument('--query_dates', type=list, default=[ '2015-08-14-14-54-57', # roadworks, overcast '2014-11-18-13-20-12', # sun, clouds '2014-12-17-18-18-43', # night, rain '2015-02-03-08-45-10', # snow '2014-06-26-09-24-58' # overcast, alternate-route (validation area) ] ) args = parser.parse_args() print(flags_to_args(args)) folds = args.folds in_root = args.in_root query_dates = args.query_dates set_aside_queries(in_root, folds, query_dates)
default=os.path.join(fs_root(), 'data/learnlarge/shuffled')) parser.add_argument('--out_root', default=os.path.join(fs_root(), 'data/learnlarge/clusters')) parser.add_argument('--num_clusters', type=dict, default={ 'train': 7000, 'test': 2000, 'val': 1000 }) parser.add_argument('--r', type=int, default=5) args = parser.parse_args() flags_to_args(args) in_root = args.in_root num_clusters = args.num_clusters out_root = args.out_root r = args.r test_ref_date = args.test_ref_date train_ref_date = args.train_ref_date val_ref_date = args.val_ref_date if not os.path.exists(out_root): os.makedirs(out_root) for mode in ['ref']: for s in ['train', 'val', 'test']: cluster(in_root, out_root, s, mode, r)