yolov7训练自定义数据集时的注意事项

慢慢记录吧

yolov7的数据集格式和yolov5是一样的，基本上直接将yolov5的数据集拿过来用即可

 文件层级：

├—data

│ ├—train

│ │ ├—images
│ │ │ ├—000000000001.jpg
│ │ │ ├—000000000002.jpg
│ │ ├—labels
│ │ │ ├—000000000001.txt
│ │ │ ├—000000000002.txt

│ ├—valid
│ │ ├—images
│ │ ├—labels

 区别就在yaml文件上，

yolov5的文件格式：

 yolov7的文件格式：

区别就是没了path，主要是有些数据比较大，不想移来移去，所以直接修改v7的代码

主要修改的是yolov7\utils\general.py

将以下代码加入check_dataset函数即可：

    FILE = Path(__file__).resolve()
    ROOT = FILE.parents[1]
    path = Path(dict.get('path') or '')
    if not path.is_absolute():
        path = (ROOT / path).resolve()
    for k in 'train', 'val', 'test':
        if dict.get(k):  # prepend path
            dict[k] = str(path / dict[k]) if isinstance(dict[k], str) else [str(path / x) for x in dict[k]]

def check_dataset(dict):
    FILE = Path(__file__).resolve()
    ROOT = FILE.parents[1]
    path = Path(dict.get('path') or '')
    if not path.is_absolute():
        path = (ROOT / path).resolve()
    for k in 'train', 'val', 'test':
        if dict.get(k):  # prepend path
            dict[k] = str(path / dict[k]) if isinstance(dict[k], str) else [str(path / x) for x in dict[k]]
    # Download dataset if not found locally
    val, s = dict.get('val'), dict.get('download')
    if val and len(val):
        val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])]  # val path
        if not all(x.exists() for x in val):
            print('\nWARNING: Dataset not found, nonexistent paths: %s' % [str(x) for x in val if not x.exists()])
            if s and len(s):  # download script
                print('Downloading %s ...' % s)
                if s.startswith('http') and s.endswith('.zip'):  # URL
                    f = Path(s).name  # filename
                    torch.hub.download_url_to_file(s, f)
                    r = os.system('unzip -q %s -d ../ && rm %s' % (f, f))  # unzip
                else:  # bash script
                    r = os.system(s)
                print('Dataset autodownload %s\n' % ('success' if r == 0 else 'failure'))  # analyze return value
            else:
                raise Exception('Dataset not found.')

        这样就只需要在配置文件中改数据集路径即可。

        还有点需要注意就是用yolov5训练后的cache文件，在训练yolov7时要删除，不然会报_pickle.UnpicklingError: STACK_GLOBAL requires str