MMLab——train.py：命令行与非命令运行模型

系列文章目录

---

---

MMLab默认使用命令行运行参数文件，这使得在VScode命令行环境运行时无法进行断点调试，需要引入pdb包进行打印调试，其实初学者只需要在原始的train.py文件进行参数修改就可以轻松进行断点调试。

注意：config.py是参数文件，不能进行调试

经典的运行命令：

python tools/train.py \
    ${CONFIG_FILE} \
    --auto-scale-lr \
    [optional arguments]

---

一、train.py配置代码

python之parser介绍使用
大家可以对照原始文件进行比较

修改后代码如下：

import argparse
import logging
import os
import os.path as osp

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

from mmdet.utils import setup_cache_size_limit_of_dynamo


def parse_args():
    parser = argparse.ArgumentParser(description='Train a detector')
    parser.add_argument('--config', default=r"work_dir\test\20230916_134428\vis_data\config.py",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',
        default=None,
        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,
        default=None,
        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')
    # When using PyTorch version >= 2.0.0, the `torch.distributed.launch`
    # will pass the `--local-rank` parameter to `tools/train.py` instead
    # of `--local_rank`.
    parser.add_argument('--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，指定文件夹路径修改相关参数
    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:
        # update configs according to CLI args if args.work_dir is not None
        cfg.work_dir = args.work_dir
    elif cfg.get('work_dir', None) is None:
        # use config filename as default work_dir if cfg.work_dir is None
        cfg.work_dir = osp.join('./work_dirs',
                                osp.splitext(osp.basename(args.config))[0])

    # enable automatic-mixed-precision training
    if args.amp is True:
        optim_wrapper = cfg.optim_wrapper.type
        if optim_wrapper == 'AmpOptimWrapper':
            print_log(
                'AMP training is already enabled in your config.',
                logger='current',
                level=logging.WARNING)
        else:
            assert optim_wrapper == 'OptimWrapper', (
                '`--amp` is only supported when the optimizer wrapper type is '
                f'`OptimWrapper` but got {optim_wrapper}.')
            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 == None:
        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:
        # build the default runner
        runner = Runner.from_cfg(cfg)
    else:
        # build customized runner from the registry
        # if 'runner_type' is set in the cfg
        runner = RUNNERS.build(cfg)

    # start training
    runner.train()


if __name__ == '__main__':
    main()

二、test.py

代码如下：
mmdetection进行预测时需要参数文件（config文件中）指定图像路径和对应的图像Json文件

# Copyright (c) OpenMMLab. All rights reserved.
import argparse
import os
import os.path as osp
import warnings
from copy import deepcopy

from mmengine import ConfigDict
from mmengine.config import Config, DictAction
from mmengine.runner import Runner

from mmdet.engine.hooks.utils import trigger_visualization_hook
from mmdet.evaluation import DumpDetResults
from mmdet.registry import RUNNERS
from mmdet.utils import setup_cache_size_limit_of_dynamo


# TODO: support fuse_conv_bn and format_only
def parse_args():
    parser = argparse.ArgumentParser(
        description='MMDet test (and eval) a model')
    parser.add_argument('--config',default=None, help='test config file path')
    parser.add_argument('checkpoint', default=None,help='checkpoint file')
    parser.add_argument(
        '--work-dir',
        help='the directory to save the file containing evaluation metrics')
    parser.add_argument(
        '--out',
        type=str,
        default=None,
        help='dump predictions to a pickle file for offline evaluation')
    parser.add_argument(
        '--show', action='store_true', help='show prediction results')
    parser.add_argument(
        '--show_dir',
        default=None,
        help='directory where painted images will be saved. '
        'If specified, it will be automatically saved '
        'to the work_dir/timestamp/show_dir')
    parser.add_argument(
        '--wait-time', type=float, default=2, help='the interval of show (s)')
    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('--tta', action='store_true')
    # When using PyTorch version >= 2.0.0, the `torch.distributed.launch`
    # will pass the `--local-rank` parameter to `tools/train.py` instead
    # of `--local_rank`.
    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
    # testing 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:
        # update configs according to CLI args if args.work_dir is not None
        cfg.work_dir = args.work_dir
    elif cfg.get('work_dir', None) is None:
        # use config filename as default work_dir if cfg.work_dir is None
        cfg.work_dir = osp.join('./work_dirs',
                                osp.splitext(osp.basename(args.config))[0])

    cfg.load_from = args.checkpoint

    if args.show or args.show_dir:
        cfg = trigger_visualization_hook(cfg, args)

    if args.tta:

        if 'tta_model' not in cfg:
            warnings.warn('Cannot find ``tta_model`` in config, '
                          'we will set it as default.')
            cfg.tta_model = dict(
                type='DetTTAModel',
                tta_cfg=dict(
                    nms=dict(type='nms', iou_threshold=0.5), max_per_img=100))
        if 'tta_pipeline' not in cfg:
            warnings.warn('Cannot find ``tta_pipeline`` in config, '
                          'we will set it as default.')
            test_data_cfg = cfg.test_dataloader.dataset
            while 'dataset' in test_data_cfg:
                test_data_cfg = test_data_cfg['dataset']
            cfg.tta_pipeline = deepcopy(test_data_cfg.pipeline)
            flip_tta = dict(
                type='TestTimeAug',
                transforms=[
                    [
                        dict(type='RandomFlip', prob=1.),
                        dict(type='RandomFlip', prob=0.)
                    ],
                    [
                        dict(
                            type='PackDetInputs',
                            meta_keys=('img_id', 'img_path', 'ori_shape',
                                       'img_shape', 'scale_factor', 'flip',
                                       'flip_direction'))
                    ],
                ])
            cfg.tta_pipeline[-1] = flip_tta
        cfg.model = ConfigDict(**cfg.tta_model, module=cfg.model)
        cfg.test_dataloader.dataset.pipeline = cfg.tta_pipeline

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

    # add `DumpResults` dummy metric
    if args.out is not None:
        assert args.out.endswith(('.pkl', '.pickle')), \
            'The dump file must be a pkl file.'
        runner.test_evaluator.metrics.append(
            DumpDetResults(out_file_path=args.out))

    # start testing
    runner.test()


if __name__ == '__main__':
    main()