|
- # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
- import os
-
- from detectron2.checkpoint import DetectionCheckpointer
- from detectron2.config import get_cfg
- from detectron2.engine import default_argument_parser, default_setup, launch
- from detectron2.evaluation import COCOEvaluator
- from detectron2.evaluation.testing import verify_results
- from detectron2.utils import comm
-
- from configs import add_centernet_config
- from engine import CenterTrainer
-
- import warnings
- warnings.filterwarnings("ignore")
-
- class Trainer(CenterTrainer):
- @classmethod
- def build_evaluator(cls, cfg, dataset_name, output_folder=None):
- if output_folder is None:
- output_folder = os.path.join(cfg.OUTPUT_DIR, "inference")
- return COCOEvaluator(dataset_name, cfg, True, output_folder)
-
- def setup(args):
- """
- Create configs and perform basic setups.
- """
- cfg = get_cfg()
- add_centernet_config(cfg)
- cfg.merge_from_file(args.config_file)
- cfg.merge_from_list(args.opts)
- cfg.freeze()
- default_setup(cfg, args)
- return cfg
-
- def main(args):
- cfg = setup(args)
-
- if args.eval_only:
- model = Trainer.build_model(cfg)
- DetectionCheckpointer(model, save_dir=cfg.OUTPUT_DIR).resume_or_load(
- cfg.MODEL.WEIGHTS, resume=args.resume
- )
- res = Trainer.test(cfg, model)
- if comm.is_main_process():
- verify_results(cfg, res)
- return res
- """
- If you'd like to do anything fancier than the standard training logic,
- consider writing your own training loop or subclassing the trainer.
- """
- trainer = Trainer(cfg)
- trainer.resume_or_load(resume=args.resume)
-
- return trainer.train()
-
- if __name__ == "__main__":
- args = default_argument_parser().parse_args()
- print("Command Line Args:", args)
- launch(
- main,
- args.num_gpus,
- num_machines=args.num_machines,
- machine_rank=args.machine_rank,
- dist_url=args.dist_url,
- args=(args,),
- )
|