import torch import argparse import config as cfg from ipeps.ipeps import * from ctm.generic.env import * from ctm.generic import ctmrg from models import coupledLadders from optim.ad_optim_lbfgs_mod import optimize_state from ctm.generic import transferops import json import unittest import logging log = logging.getLogger(__name__) # parse command line args and build necessary configuration objects parser = cfg.get_args_parser() # additional model-dependent arguments parser.add_argument("--alpha", type=float, default=0., help="inter-ladder coupling") parser.add_argument("--top_freq", type=int, default=-1, help="freuqency of transfer operator spectrum evaluation") parser.add_argument("--top_n", type=int, default=2, help="number of leading eigenvalues" + "of transfer operator to compute") args, unknown_args = parser.parse_known_args()
'n_parameters': n_parameters } if args.output_dir and utils.is_main_process(): with (output_dir / "log.txt").open("a") as f: f.write(json.dumps(log_stats) + "\n") # for evaluation logs if coco_evaluator is not None: (output_dir / 'eval').mkdir(exist_ok=True) if "bbox" in coco_evaluator.coco_eval: filenames = ['latest.pth'] if epoch % 50 == 0: filenames.append(f'{epoch:03}.pth') for name in filenames: torch.save(coco_evaluator.coco_eval["bbox"].eval, output_dir / "eval" / name) total_time = time.time() - start_time total_time_str = str(datetime.timedelta(seconds=int(total_time))) print('Training time {}'.format(total_time_str)) if __name__ == '__main__': parser = argparse.ArgumentParser('DETR training and evaluation script', parents=[get_args_parser()]) args = parser.parse_args() if args.output_dir: Path(args.output_dir).mkdir(parents=True, exist_ok=True) main(args)