yolov5代码阅读笔记1

今天开一个新坑，读一读Yolov5的代码，加些注释，供自己学习,如有不对，恳请指正
代码下载：链接

1. main

from pathlib import Path
#pathlib库是文件路径库 https://blog.csdn.net/itanders/article/details/88754606
#resolve() 返回一个新的路径，这个新路径就是当前Path对象的绝对路径，如果是软链接则直接被解析
FILE = Path(__file__).resolve()
ROOT = FILE.parents[0]  # YOLOv5 root directory
# os.getenv 该方法，用于获取全局变量
LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1))  # https://pytorch.org/docs/stable/elastic/run.html
RANK = int(os.getenv('RANK', -1))
WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1))


if __name__ == "__main__":
    opt = parse_opt()
    main(opt)

1.1 parse_opt

parse_opt就是读取命令行运行train.py时所带的参数,并保存为opt返回

参数讲解

'''
argparse 是python自带的命令行参数解析包，可以用来方便地读取命令行参数。
'''
def parse_opt(known=False):
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='initial weights path')
    parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
    parser.add_argument('--hyp', type=str, default=ROOT / 'data/hyps/hyp.scratch-low.yaml', help='hyperparameters path')
    parser.add_argument('--epochs', type=int, default=300)
    parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs, -1 for autobatch')
    parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)')
    parser.add_argument('--rect', action='store_true', help='rectangular training')
    parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
    parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
    parser.add_argument('--noval', action='store_true', help='only validate final epoch')
    parser.add_argument('--noautoanchor', action='store_true', help='disable AutoAnchor')
    parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations')
    parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
    parser.add_argument('--cache', type=str, nargs='?', const='ram', help='--cache images in "ram" (default) or "disk"')
    parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
    parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
    parser.add_argument('--optimizer', type=str, choices=['SGD', 'Adam', 'AdamW'], default='SGD', help='optimizer')
    parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
    parser.add_argument('--workers', type=int, default=8, help='max dataloader workers (per RANK in DDP mode)')
    parser.add_argument('--project', default=ROOT / 'runs/train', help='save to project/name')
    parser.add_argument('--name', default='exp', help='save to project/name')
    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
    parser.add_argument('--quad', action='store_true', help='quad dataloader')
    parser.add_argument('--cos-lr', action='store_true', help='cosine LR scheduler')
    parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
    parser.add_argument('--patience', type=int, default=100, help='EarlyStopping patience (epochs without improvement)')
    parser.add_argument('--freeze', nargs='+', type=int, default=[0], help='Freeze layers: backbone=10, first3=0 1 2')
    parser.add_argument('--save-period', type=int, default=-1, help='Save checkpoint every x epochs (disabled if < 1)')
    parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')

    # Weights & Biases arguments
    parser.add_argument('--entity', default=None, help='W&B: Entity')
    parser.add_argument('--upload_dataset', nargs='?', const=True, default=False, help='W&B: Upload data, "val" option')
    parser.add_argument('--bbox_interval', type=int, default=-1, help='W&B: Set bounding-box image logging interval')
    parser.add_argument('--artifact_alias', type=str, default='latest', help='W&B: Version of dataset artifact to use')

    opt = parser.parse_known_args()[0] if known else parser.parse_args()
    return opt

2.main

# Callbacks():
def main(opt, callbacks=Callbacks()):
    # Checks
    if RANK in [-1, 0]:
    	# 2.1 打印文件根路径
        print_args(FILE.stem, opt)
        # 2.2 检查github状态
        check_git_status()
        # 2.3 检查requirements
        check_requirements(exclude=['thop'])
    '''
        resume:恢复最近的train(被打断的train)
        evolve:寻找超参数
        check_wandb_resume: 令opt.weights = str(Path(modeldir) / "last.pt")
        如果最近有被打断的train且加载last.pt
        get_latest_run:找出最近的pt模型文件
        如果最近有被中断的训练，就查找上次的权重并恢复opt记录  
        opt.data:coco128.yaml 
        对wandb相关代码仅概述或略过
        get_latest_run: 
         1. glob模块是最简单的模块之一，内容非常少。用它可以查找符合特定规则的文件路径名。跟使用windows下的文件搜索差不多。
         2. 查找文件只用到三个匹配符：””, “?”, “[]”。””匹配0个或多个字符；”?”匹配单个字符；”[]”匹配指定范围内的字符，如：[0-9]匹配数字。
    '''
    # Resume
    if opt.resume and not check_wandb_resume(opt) and not opt.evolve:  # resume an interrupted run
        # ckpt:最近存储路径
        ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run()  # specified or most recent path
        assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist'
        with open(Path(ckpt).parent.parent / 'opt.yaml', errors='ignore') as f:
            opt = argparse.Namespace(**yaml.safe_load(f))  # replace
        opt.cfg, opt.weights, opt.resume = '', ckpt, True  # reinstate
        LOGGER.info(f'Resuming training from {ckpt}')
    else:
        opt.data, opt.cfg, opt.hyp, opt.weights, opt.project = \
            check_file(opt.data), check_yaml(opt.cfg), check_yaml(opt.hyp), str(opt.weights), str(opt.project)  # checks
        assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
        if opt.evolve:
            if opt.project == str(ROOT / 'runs/train'):  # if default project name, rename to runs/evolve
                opt.project = str(ROOT / 'runs/evolve')
            opt.exist_ok, opt.resume = opt.resume, False  # pass resume to exist_ok and disable resume
        opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))

    # DDP mode. 多卡训练
    device = select_device(opt.device, batch_size=opt.batch_size)
    if LOCAL_RANK != -1:
        msg = 'is not compatible with YOLOv5 Multi-GPU DDP training'
        assert not opt.image_weights, f'--image-weights {msg}'
        assert not opt.evolve, f'--evolve {msg}'
        assert opt.batch_size != -1, f'AutoBatch with --batch-size -1 {msg}, please pass a valid --batch-size'
        assert opt.batch_size % WORLD_SIZE == 0, f'--batch-size {opt.batch_size} must be multiple of WORLD_SIZE'
        assert torch.cuda.device_count() > LOCAL_RANK, 'insufficient CUDA devices for DDP command'
        torch.cuda.set_device(LOCAL_RANK)
        device = torch.device('cuda', LOCAL_RANK)
        dist.init_process_group(backend="nccl" if dist.is_nccl_available() else "gloo")
	'''
			如果参数未进化，就进行train
			如果参数已经改变，就选择训练好的参数进行加载，然后训练
			可以先看train部分，然后回头再看加载的参数部分
	'''

    # Train
    if not opt.evolve:
        train(opt.hyp, opt, device, callbacks)
        if WORLD_SIZE > 1 and RANK == 0:
            LOGGER.info('Destroying process group... ')
            dist.destroy_process_group()

    # Evolve hyperparameters (optional)
    else:
        # Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit)
        meta = {'lr0': (1, 1e-5, 1e-1),  # initial learning rate (SGD=1E-2, Adam=1E-3)
                'lrf': (1, 0.01, 1.0),  # final OneCycleLR learning rate (lr0 * lrf)
                'momentum': (0.3, 0.6, 0.98),  # SGD momentum/Adam beta1
                'weight_decay': (1, 0.0, 0.001),  # optimizer weight decay
                'warmup_epochs': (1, 0.0, 5.0),  # warmup epochs (fractions ok)
                'warmup_momentum': (1, 0.0, 0.95),  # warmup initial momentum
                'warmup_bias_lr': (1, 0.0, 0.2),  # warmup initial bias lr
                'box': (1, 0.02, 0.2),  # box loss gain
                'cls': (1, 0.2, 4.0),  # cls loss gain
                'cls_pw': (1, 0.5, 2.0),  # cls BCELoss positive_weight
                'obj': (1, 0.2, 4.0),  # obj loss gain (scale with pixels)
                'obj_pw': (1, 0.5, 2.0),  # obj BCELoss positive_weight
                'iou_t': (0, 0.1, 0.7),  # IoU training threshold
                'anchor_t': (1, 2.0, 8.0),  # anchor-multiple threshold
                'anchors': (2, 2.0, 10.0),  # anchors per output grid (0 to ignore)
                'fl_gamma': (0, 0.0, 2.0),  # focal loss gamma (efficientDet default gamma=1.5)
                'hsv_h': (1, 0.0, 0.1),  # image HSV-Hue augmentation (fraction)
                'hsv_s': (1, 0.0, 0.9),  # image HSV-Saturation augmentation (fraction)
                'hsv_v': (1, 0.0, 0.9),  # image HSV-Value augmentation (fraction)
                'degrees': (1, 0.0, 45.0),  # image rotation (+/- deg)
                'translate': (1, 0.0, 0.9),  # image translation (+/- fraction)
                'scale': (1, 0.0, 0.9),  # image scale (+/- gain)
                'shear': (1, 0.0, 10.0),  # image shear (+/- deg)
                'perspective': (0, 0.0, 0.001),  # image perspective (+/- fraction), range 0-0.001
                'flipud': (1, 0.0, 1.0),  # image flip up-down (probability)
                'fliplr': (0, 0.0, 1.0),  # image flip left-right (probability)
                'mosaic': (1, 0.0, 1.0),  # image mixup (probability)
                'mixup': (1, 0.0, 1.0),  # image mixup (probability)
                'copy_paste': (1, 0.0, 1.0)}  # segment copy-paste (probability)

        with open(opt.hyp, errors='ignore') as f:
            hyp = yaml.safe_load(f)  # load hyps dict
            if 'anchors' not in hyp:  # anchors commented in hyp.yaml
                hyp['anchors'] = 3
        opt.noval, opt.nosave, save_dir = True, True, Path(opt.save_dir)  # only val/save final epoch
        # ei = [isinstance(x, (int, float)) for x in hyp.values()]  # evolvable indices
        evolve_yaml, evolve_csv = save_dir / 'hyp_evolve.yaml', save_dir / 'evolve.csv'
        if opt.bucket:
            os.system(f'gsutil cp gs://{opt.bucket}/evolve.csv {evolve_csv}')  # download evolve.csv if exists

        for _ in range(opt.evolve):  # generations to evolve
            if evolve_csv.exists():  # if evolve.csv exists: select best hyps and mutate
                # Select parent(s)
                parent = 'single'  # parent selection method: 'single' or 'weighted'
                x = np.loadtxt(evolve_csv, ndmin=2, delimiter=',', skiprows=1)
                n = min(5, len(x))  # number of previous results to consider
                x = x[np.argsort(-fitness(x))][:n]  # top n mutations
                w = fitness(x) - fitness(x).min() + 1E-6  # weights (sum > 0)
                if parent == 'single' or len(x) == 1:
                    # x = x[random.randint(0, n - 1)]  # random selection
                    x = x[random.choices(range(n), weights=w)[0]]  # weighted selection
                elif parent == 'weighted':
                    x = (x * w.reshape(n, 1)).sum(0) / w.sum()  # weighted combination

                # Mutate
                mp, s = 0.8, 0.2  # mutation probability, sigma
                npr = np.random
                npr.seed(int(time.time()))
                g = np.array([meta[k][0] for k in hyp.keys()])  # gains 0-1
                ng = len(meta)
                v = np.ones(ng)
                while all(v == 1):  # mutate until a change occurs (prevent duplicates)
                    v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0)
                for i, k in enumerate(hyp.keys()):  # plt.hist(v.ravel(), 300)
                    hyp[k] = float(x[i + 7] * v[i])  # mutate

            # Constrain to limits
            for k, v in meta.items():
                hyp[k] = max(hyp[k], v[1])  # lower limit
                hyp[k] = min(hyp[k], v[2])  # upper limit
                hyp[k] = round(hyp[k], 5)  # significant digits

            # Train mutation
            results = train(hyp.copy(), opt, device, callbacks)
            callbacks = Callbacks()
            # Write mutation results
            print_mutation(results, hyp.copy(), save_dir, opt.bucket)

        # Plot results
        plot_evolve(evolve_csv)
        LOGGER.info(f'Hyperparameter evolution finished {opt.evolve} generations\n'
                    f"Results saved to {colorstr('bold', save_dir)}\n"
                    f'Usage example: $ python train.py --hyp {evolve_yaml}')

2.1 print_args

logging的使用

LOGGER.info的打印输出

import logging#日志输出
def print_args(name, opt):
    # Print argparser arguments
    LOGGER.info(colorstr(f'{name}: ') + ', '.join(f'{k}={v}' for k, v in vars(opt).items()))

2.1.1 colorstr

字符串输出的颜色美化函数

def colorstr(*input):
    # Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e.  colorstr('blue', 'hello world')
    *args, string = input if len(input) > 1 else ('blue', 'bold', input[0])  # color arguments, string
    '''
        *args, string = ('blue', 'bold', input[0])
    '''
    colors = {'black': '\033[30m',  # basic colors
              'red': '\033[31m',
              'green': '\033[32m',
              'yellow': '\033[33m',
              'blue': '\033[34m',
              'magenta': '\033[35m',
              'cyan': '\033[36m',
              'white': '\033[37m',
              'bright_black': '\033[90m',  # bright colors
              'bright_red': '\033[91m',
              'bright_green': '\033[92m',
              'bright_yellow': '\033[93m',
              'bright_blue': '\033[94m',
              'bright_magenta': '\033[95m',
              'bright_cyan': '\033[96m',
              'bright_white': '\033[97m',
              'end': '\033[0m',  # misc
              'bold': '\033[1m',
              'underline': '\033[4m'}
    # f-string 以大括号 {} 标明被替换的字段；f-string在本质上并不是字符串常量，而是一个在运行时运算求值的表达式
    # https://blog.csdn.net/yizhuanlu9607/article/details/89530982
    return ''.join(colors[x] for x in args) + f'{string}' + colors['end']

2.2 check_git_status

打印输出：github: skipping check (not a git repository), for updates see https://github.com/ultralytics/yolov5

@try_except
@WorkingDirectory(ROOT)
def check_git_status():
    # Recommend 'git pull' if code is out of date
    msg = ', for updates see https://github.com/ultralytics/yolov5'
    s = colorstr('github: ')  # string
    assert Path('.git').exists(), s + 'skipping check (not a git repository)' + msg
    assert not is_docker(), s + 'skipping check (Docker image)' + msg
    assert check_online(), s + 'skipping check (offline)' + msg

    cmd = 'git fetch && git config --get remote.origin.url'
    url = check_output(cmd, shell=True, timeout=5).decode().strip().rstrip('.git')  # git fetch
    branch = check_output('git rev-parse --abbrev-ref HEAD', shell=True).decode().strip()  # checked out
    n = int(check_output(f'git rev-list {branch}..origin/master --count', shell=True))  # commits behind
    if n > 0:
        s += f"⚠️ YOLOv5 is out of date by {n} commit{'s' * (n > 1)}. Use `git pull` or `git clone {url}` to update."
    else:
        s += f'up to date with {url} ✅'
    LOGGER.info(emojis(s))  # emoji-safe

1. assert: 断言,用于判断一个表达式，在表达式条件为 false 的时候触发异常。
2. Python3中的subprocess.check_output函数可以执行一条sh命令，并返回命令的输出内容
3. @try_except：语法糖，就是最外层套一个try,语法糖

2.3 check_requirements

检查所需依赖

@try_except
def check_requirements(requirements=ROOT / 'requirements.txt', exclude=(), install=True):
    # Check installed dependencies meet requirements (pass *.txt file or list of packages)
    prefix = colorstr('red', 'bold', 'requirements:')
    check_python()  # check python version
    if isinstance(requirements, (str, Path)):  # requirements.txt file
        file = Path(requirements)
        assert file.exists(), f"{prefix} {file.resolve()} not found, check failed."
        with file.open() as f:
            requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(f) if x.name not in exclude]
    else:  # list or tuple of packages
        requirements = [x for x in requirements if x not in exclude]

    n = 0  # number of packages updates
    for r in requirements:
        try:
            pkg.require(r)
        except Exception:  # DistributionNotFound or VersionConflict if requirements not met
            s = f"{prefix} {r} not found and is required by YOLOv5"
            if install:
                LOGGER.info(f"{s}, attempting auto-update...")
                try:
                    assert check_online(), f"'pip install {r}' skipped (offline)"
                    LOGGER.info(check_output(f"pip install '{r}'", shell=True).decode())
                    n += 1
                except Exception as e:
                    LOGGER.warning(f'{prefix} {e}')
            else:
                LOGGER.info(f'{s}. Please install and rerun your command.')

    if n:  # if packages updated
        source = file.resolve() if 'file' in locals() else requirements
        s = f"{prefix} {n} package{'s' * (n > 1)} updated per {source}\n" \
            f"{prefix} ⚠️ {colorstr('bold', 'Restart runtime or rerun command for updates to take effect')}\n"
        LOGGER.info(emojis(s))