train.py

"""
Train Mask R-CNN with HRNet-W32 backbone for FRT detection.

Usage:
    python train.py
    
Author: Bin Zhang
Date: 2026.02.23
"""
import argparse
import os
import os.path as osp
import time

from mmengine.config import Config, DictAction
from mmengine.registry import RUNNERS
from mmengine.runner import Runner
import utils

from mmdet.utils import setup_cache_size_limit_of_dynamo

import matplotlib
matplotlib.use('Agg')

# Default config path
CONFIG_FILE = './models/mask-rcnn_hrnetv2p-w32-2x_FAST.py'


def parse_args():
    parser = argparse.ArgumentParser(description='Train Mask R-CNN HRNet-W32 for FRT detection')
    parser.add_argument('--config', default=CONFIG_FILE,
                        help='train config file path')
    parser.add_argument('--work-dir', default=None,
                        help='the dir to save logs and models')
    parser.add_argument(
        '--amp',
        action='store_true',
        default=False,
        help='enable automatic-mixed-precision training')
    parser.add_argument(
        '--auto-scale-lr',
        action='store_true',
        help='enable automatically scaling LR.')
    parser.add_argument(
        '--resume',
        nargs='?',
        type=str,
        const='auto',
        help='If specify checkpoint path, resume from it, while if not '
        'specify, try to auto resume from the latest checkpoint '
        'in the work directory.')
    parser.add_argument(
        '--cfg-options',
        nargs='+',
        action=DictAction,
        help='override some settings in the used config, the key-value pair '
        'in xxx=yyy format will be merged into config file. If the value to '
        'be overwritten is a list, it should be like key="[a,b]" or key=a,b '
        'It also allows nested list/tuple values, e.g. key="[(a,b),(c,d)]" '
        'Note that the quotation marks are necessary and that no white space '
        'is allowed.')
    parser.add_argument(
        '--launcher',
        choices=['none', 'pytorch', 'slurm', 'mpi'],
        default='none',
        help='job launcher')
    parser.add_argument('--local_rank', '--local-rank', type=int, default=0)
    args = parser.parse_args()
    if 'LOCAL_RANK' not in os.environ:
        os.environ['LOCAL_RANK'] = str(args.local_rank)
    return args


def main():
    args = parse_args()

    # Reduce the number of repeated compilations and improve training speed.
    setup_cache_size_limit_of_dynamo()

    # load config
    cfg = Config.fromfile(args.config)
    cfg.launcher = args.launcher
    if args.cfg_options is not None:
        cfg.merge_from_dict(args.cfg_options)

    # work_dir is determined in this priority: CLI > segment in file > filename
    if args.work_dir is not None:
        cfg.work_dir = args.work_dir
    elif cfg.get('work_dir', None) is None:
        runtime = time.strftime("%y-%m-%d-%H-%M-%S")
        cfg.work_dir = osp.join('./work_dirs',
                                f'mask-rcnn_hrnetv2p-w32-2x_FAST_{runtime}')

    # enable automatic-mixed-precision training
    if args.amp is True:
        cfg.optim_wrapper.type = 'AmpOptimWrapper'
        cfg.optim_wrapper.loss_scale = 'dynamic'

    # enable automatically scaling LR
    if args.auto_scale_lr:
        if 'auto_scale_lr' in cfg and \
                'enable' in cfg.auto_scale_lr and \
                'base_batch_size' in cfg.auto_scale_lr:
            cfg.auto_scale_lr.enable = True
        else:
            raise RuntimeError('Can not find "auto_scale_lr" or '
                               '"auto_scale_lr.enable" or '
                               '"auto_scale_lr.base_batch_size" in your'
                               ' configuration file.')

    # resume is determined in this priority: resume from > auto_resume
    if args.resume == 'auto':
        cfg.resume = True
        cfg.load_from = None
    elif args.resume is not None:
        cfg.resume = True
        cfg.load_from = args.resume

    # build the runner from config
    if 'runner_type' not in cfg:
        runner = Runner.from_cfg(cfg)
    else:
        runner = RUNNERS.build(cfg)

    # start training
    runner.train()


if __name__ == '__main__':
    main()