WZMIAOMIAO/deep-learning-for-image-processing · error · FileNotFoundError

VOCdevkit dose not in path:'{}'.

Error message

VOCdevkit dose not in path:'{}'.

What it means

Identical guard to error 50 but in change_backbone_without_fpn.py: the script verifies that os.path.join(args.data_path, 'VOCdevkit') exists before instantiating VOCDataSet, otherwise raising FileNotFoundError with the bad root. It fails fast so the VOC dataset layout is present before training/replacing the backbone.

Source

Thrown at pytorch_object_detection/faster_rcnn/change_backbone_without_fpn.py:72

def main(args):
    device = torch.device(args.device if torch.cuda.is_available() else "cpu")
    print("Using {} device training.".format(device.type))

    # 用来保存coco_info的文件
    results_file = "results{}.txt".format(datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))

    data_transform = {
        "train": transforms.Compose([transforms.ToTensor(),
                                     transforms.RandomHorizontalFlip(0.5)]),
        "val": transforms.Compose([transforms.ToTensor()])
    }

    VOC_root = args.data_path
    # check voc root
    if os.path.exists(os.path.join(VOC_root, "VOCdevkit")) is False:
        raise FileNotFoundError("VOCdevkit dose not in path:'{}'.".format(VOC_root))

    # load train data set
    # VOCdevkit -> VOC2012 -> ImageSets -> Main -> train.txt
    train_dataset = VOCDataSet(VOC_root, "2012", data_transform["train"], "train.txt")
    train_sampler = None

    # 是否按图片相似高宽比采样图片组成batch
    # 使用的话能够减小训练时所需GPU显存，默认使用
    if args.aspect_ratio_group_factor >= 0:
        train_sampler = torch.utils.data.RandomSampler(train_dataset)
        # 统计所有图像高宽比例在bins区间中的位置索引
        group_ids = create_aspect_ratio_groups(train_dataset, k=args.aspect_ratio_group_factor)
        # 每个batch图片从同一高宽比例区间中取
        train_batch_sampler = GroupedBatchSampler(train_sampler, group_ids, args.batch_size)

    # 注意这里的collate_fn是自定义的，因为读取的数据包括image和targets，不能直接使用默认的方法合成batch
    batch_size = args.batch_size
    nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8])  # number of workers

View on GitHub (pinned to 1ec3fe6f37)

Solutions

1. Point --data-path at the directory that directly contains VOCdevkit.
2. Extract the VOC2012 archive so <data-path>/VOCdevkit/VOC2012 exists.
3. Confirm the expected tree exists: <data-path>/VOCdevkit/VOC2012/ImageSets/Main/train.txt.
4. Use an absolute path to avoid cwd confusion.
5. Adapt the check/dataset if your data uses a different layout.

Example fix

# before
python change_backbone_without_fpn.py --data-path ~/data/VOCdevkit
# after
python change_backbone_without_fpn.py --data-path ~/data  # ~/data/VOCdevkit must exist

import os
voc_root = args.data_path
assert os.path.isdir(os.path.join(voc_root, 'VOCdevkit')), f"VOCdevkit missing under {voc_root}"

def is_valid_voc_root(path: str) -> bool:
    return os.path.isdir(os.path.join(path, 'VOCdevkit', 'VOC2012'))

try:
    main(args)
except FileNotFoundError as e:
    print(f'Bad --data-path: {e}. Expected <data-path>/VOCdevkit.')
    sys.exit(2)

When it happens

Trigger: Invoking change_backbone_without_fpn.py with --data-path lacking a VOCdevkit subdirectory — wrong parent folder, archive not extracted, dataset moved, or path typo.

Common situations: Same as [50]: pointing at VOCdevkit itself, unextracted VOC2012 archive, using COCO-style data, or relative path resolved from a different cwd.

Related errors

• VOCdevkit dose not in path:'{}'.
• VOCdevkit dose not in path:'{}'.
• Image '{}' format not JPEG
• VOCdevkit dose not in path:'{}'.
• VOCdevkit dose not in path:'{}'.

AI-assisted analysis of WZMIAOMIAO/deep-learning-for-image-processing@1ec3fe6f37 (2026-08-30). Data as JSON: /api/errors/a85b783fbf657bda. Report an issue: GitHub.