可视化脚本用于使用MMDetection库进行图像的目标检测

# Copyright (c) OpenMMLab. All rights reserved.
import asyncio
from argparse import ArgumentParser

from mmdet.apis import (async_inference_detector, inference_detector,
                        init_detector, show_result_pyplot)
import denseclip

# 解析命令行参数
def parse_args():
    parser = ArgumentParser()
    parser.add_argument('img', help='Image file')  # 图像文件路径
    parser.add_argument('config', help='Config file')  # 配置文件路径
    parser.add_argument('checkpoint', help='Checkpoint file')  # 检查点文件路径
    parser.add_argument('--out-file', default=None, help='Path to output file')  # 输出结果文件路径
    parser.add_argument(
        '--device', default='cuda:0', help='Device used for inference')  # 使用进行推理的设备
    parser.add_argument(
        '--palette',
        default='coco',
        choices=['coco', 'voc', 'citys', 'random'],
        help='Color palette used for visualization')  # 可视化使用的颜色调色板
    parser.add_argument(
        '--score-thr', type=float, default=0.3, help='bbox score threshold')  # 框得分阈值
    parser.add_argument(
        '--async-test',
        action='store_true',
        help='whether to set async options for async inference.')  # 是否进行异步推理
    args = parser.parse_args()
    return args


# 主函数
def main(args):
    # 从配置文件和检查点文件构建模型
    model = init_detector(args.config, args.checkpoint, device=args.device)
    # 对单张图像进行测试
    result = inference_detector(model, args.img)
    # 显示结果
    show_result_pyplot(
        model,
        args.img,
        result,
        palette=args.palette,
        score_thr=args.score_thr,
        out_file=args.out_file)


# 异步主函数
async def async_main(args):
    # 从配置文件和检查点文件构建模型
    model = init_detector(args.config, args.checkpoint, device=args.device)
    # 对单张图像进行异步测试
    tasks = asyncio.create_task(async_inference_detector(model, args.img))
    result = await asyncio.gather(tasks)
    # 显示结果
    show_result_pyplot(
        model,
        args.img,
        result[0],
        palette=args.palette,
        score_thr=args.score_thr,
        out_file=args.out_file)


# 主程序入口
if __name__ == '__main__':
    args = parse_args()
    if args.async_test:
        asyncio.run(async_main(args))  # 如果设置了异步选项，则运行异步主函数
    else:
        main(args)  # 否则运行同步主函数

用命令行指定具体文件

基本示例

python your_script.py path/to/image.jpg path/to/config.py path/to/checkpoint.pth

指定输出文件

python your_script.py path/to/image.jpg path/to/config.py path/to/checkpoint.pth --out-file path/to/output.jpg

设置边界框得分阈值

python your_script.py path/to/image.jpg path/to/config.py path/to/checkpoint.pth --score-thr 0.5

或者用下面的分布式测试

import argparse
import os
import warnings

import mmcv
import torch
from mmcv import Config, DictAction
from mmcv.cnn import fuse_conv_bn
from mmcv.parallel import MMDataParallel, MMDistributedDataParallel
from mmcv.runner import (get_dist_info, init_dist, load_checkpoint,
                         wrap_fp16_model)

from mmdet.apis import multi_gpu_test, single_gpu_test
from mmdet.datasets import (build_dataloader, build_dataset,
                            replace_ImageToTensor)
from mmdet.models import build_detector
import denseclip

def parse_args():
    parser = argparse.ArgumentParser(
        description='MMDet test (and eval) a model')
    parser.add_argument('config', help='test config file path')
    parser.add_argument('checkpoint', help='checkpoint file')
    parser.add_argument('--out', help='output result file in pickle format')
    parser.add_argument(
        '--fuse-conv-bn',
        action='store_true',
        help='Whether to fuse conv and bn, this will slightly increase'
        'the inference speed')
    parser.add_argument(
        '--format-only',
        action='store_true',
        help='Format the output results without perform evaluation. It is'
        'useful when you want to format the result to a specific format and '
        'submit it to the test server')
    parser.add_argument(
        '--eval',
        type=str,
        nargs='+',
        help='evaluation metrics, which depends on the dataset, e.g., "bbox",'
        ' "segm", "proposal" for COCO, and "mAP", "recall" for PASCAL VOC')
    parser.add_argument('--show', action='store_true', help='show results')
    parser.add_argument(
        '--show-dir', help='directory where painted images will be saved')
    parser.add_argument(
        '--show-score-thr',
        type=float,
        default=0.3,
        help='score threshold (default: 0.3)')
    parser.add_argument(
        '--gpu-collect',
        action='store_true',
        help='whether to use gpu to collect results.')
    parser.add_argument(
        '--tmpdir',
        help='tmp directory used for collecting results from multiple '
        'workers, available when gpu-collect is not specified')
    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(
        '--options',
        nargs='+',
        action=DictAction,
        help='custom options for evaluation, the key-value pair in xxx=yyy '
        'format will be kwargs for dataset.evaluate() function (deprecate), '
        'change to --eval-options instead.')
    parser.add_argument(
        '--eval-options',
        nargs='+',
        action=DictAction,
        help='custom options for evaluation, the key-value pair in xxx=yyy '
        'format will be kwargs for dataset.evaluate() function')
    parser.add_argument(
        '--launcher',
        choices=['none', 'pytorch', 'slurm', 'mpi'],
        default='none',
        help='job launcher')
    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)

    if args.options and args.eval_options:
        raise ValueError(
            '--options and --eval-options cannot be both '
            'specified, --options is deprecated in favor of --eval-options')
    if args.options:
        warnings.warn('--options is deprecated in favor of --eval-options')
        args.eval_options = args.options
    return args


def main():
    args = parse_args()

    assert args.out or args.eval or args.format_only or args.show \
        or args.show_dir, \
        ('Please specify at least one operation (save/eval/format/show the '
         'results / save the results) with the argument "--out", "--eval"'
         ', "--format-only", "--show" or "--show-dir"')

    if args.eval and args.format_only:
        raise ValueError('--eval and --format_only cannot be both specified')

    if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
        raise ValueError('The output file must be a pkl file.')

    cfg = Config.fromfile(args.config)
    if args.cfg_options is not None:
        cfg.merge_from_dict(args.cfg_options)
    # import modules from string list.
    if cfg.get('custom_imports', None):
        from mmcv.utils import import_modules_from_strings
        import_modules_from_strings(**cfg['custom_imports'])
    # set cudnn_benchmark
    if cfg.get('cudnn_benchmark', False):
        torch.backends.cudnn.benchmark = True
    cfg.model.pretrained = None
    if cfg.model.get('neck'):
        if isinstance(cfg.model.neck, list):
            for neck_cfg in cfg.model.neck:
                if neck_cfg.get('rfp_backbone'):
                    if neck_cfg.rfp_backbone.get('pretrained'):
                        neck_cfg.rfp_backbone.pretrained = None
        elif cfg.model.neck.get('rfp_backbone'):
            if cfg.model.neck.rfp_backbone.get('pretrained'):
                cfg.model.neck.rfp_backbone.pretrained = None

    # in case the test dataset is concatenated
    if isinstance(cfg.data.test, dict):
        cfg.data.test.test_mode = True
    elif isinstance(cfg.data.test, list):
        for ds_cfg in cfg.data.test:
            ds_cfg.test_mode = True

    # init distributed env first, since logger depends on the dist info.
    if args.launcher == 'none':
        distributed = False
    else:
        distributed = True
        init_dist(args.launcher, **cfg.dist_params)

    # build the dataloader
    samples_per_gpu = cfg.data.test.pop('samples_per_gpu', 1)
    if samples_per_gpu > 1:
        # Replace 'ImageToTensor' to 'DefaultFormatBundle'
        cfg.data.test.pipeline = replace_ImageToTensor(cfg.data.test.pipeline)
    dataset = build_dataset(cfg.data.test)
    data_loader = build_dataloader(
        dataset,
        samples_per_gpu=samples_per_gpu,
        workers_per_gpu=cfg.data.workers_per_gpu,
        dist=distributed,
        shuffle=False)

    # build the model and load checkpoint
    if 'DenseCLIP' in cfg.model.type:
        cfg.model.class_names = list(dataset.CLASSES)

    if not hasattr(cfg, 'test_cfg'):
        cfg.test_cfg = None
    model = build_detector(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        wrap_fp16_model(model)
    checkpoint = load_checkpoint(model, args.checkpoint, map_location='cpu')
    if args.fuse_conv_bn:
        model = fuse_conv_bn(model)
    # old versions did not save class info in checkpoints, this walkaround is
    # for backward compatibility
    if 'CLASSES' in checkpoint['meta']:
        model.CLASSES = checkpoint['meta']['CLASSES']
    else:
        model.CLASSES = dataset.CLASSES

    if not distributed:
        model = MMDataParallel(model, device_ids=[0])
        outputs = single_gpu_test(model, data_loader, args.show, args.show_dir,
                                  args.show_score_thr)
    else:
        model = MMDistributedDataParallel(
            model.cuda(),
            device_ids=[torch.cuda.current_device()],
            broadcast_buffers=False)
        outputs = multi_gpu_test(model, data_loader, args.tmpdir,
                                 args.gpu_collect)

    rank, _ = get_dist_info()
    if rank == 0:
        if args.out:
            print(f'\nwriting results to {args.out}')
            mmcv.dump(outputs, args.out)
        kwargs = {} if args.eval_options is None else args.eval_options
        if args.format_only:
            dataset.format_results(outputs, **kwargs)
        if args.eval:
            eval_kwargs = cfg.get('evaluation', {}).copy()
            # hard-code way to remove EvalHook args
            for key in [
                    'interval', 'tmpdir', 'start', 'gpu_collect', 'save_best',
                    'rule'
            ]:
                eval_kwargs.pop(key, None)
            eval_kwargs.update(dict(metric=args.eval, **kwargs))
            print(dataset.evaluate(outputs, **eval_kwargs))


if __name__ == '__main__':
    main()