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

VOCdevkit dose not in path:'{}'.

Error message

VOCdevkit dose not in path:'{}'.

What it means

train_multi_GPU.py's main() checks that args.data_path contains a VOCdevkit directory before loading VOCSegmentation. If os.path.join(VOC_root, 'VOCdevkit') does not exist, it raises FileNotFoundError including the path, since the segmentation dataset layout is required under that folder.

Source

Thrown at pytorch_segmentation/deeplab_v3/train_multi_GPU.py:84

    return model


def main(args):
    init_distributed_mode(args)
    print(args)

    device = torch.device(args.device)
    # segmentation nun_classes + background
    num_classes = args.num_classes + 1

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

    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 -> Segmentation -> train.txt
    train_dataset = VOCSegmentation(args.data_path,
                                    year="2012",
                                    transforms=get_transform(train=True),
                                    txt_name="train.txt")
    # load validation data set
    # VOCdevkit -> VOC2012 -> ImageSets -> Segmentation -> val.txt
    val_dataset = VOCSegmentation(args.data_path,
                                  year="2012",
                                  transforms=get_transform(train=False),
                                  txt_name="val.txt")

    print("Creating data loaders")
    if args.distributed:
        train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset)
        test_sampler = torch.utils.data.distributed.DistributedSampler(val_dataset)

View on GitHub (pinned to 1ec3fe6f37)

Solutions

1. Set --data-path to the parent directory that directly contains VOCdevkit (which contains VOC2012).
2. Verify the layout: <data-path>/VOCdevkit/VOC2012/ImageSets/Segmentation/train.txt must exist.
3. Use an absolute path and check it exists before launching, e.g. ls $DATA_PATH/VOCdevkit.

Example fix

// before
python train_multi_GPU.py --data-path ./VOCdevkit
// after
python train_multi_GPU.py --data-path /data  # /data/VOCdevkit/VOC2012 exists

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

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

try:
    main(parser_data)
except FileNotFoundError as e:
    logging.error(f"Dataset layout wrong: {e}. Expected <data-path>/VOCdevkit/VOC2012"); raise

When it happens

Trigger: Running multi-GPU training with --data-path pointing to a directory that lacks the VOCdevkit subfolder (wrong root, dataset not extracted, or VOC2012 tar not unpacked).

Common situations: Pointing --data-path at the VOCdevkit folder itself instead of its parent; dataset downloaded but not extracted; typo or relative path resolved from a different working directory when launched via torchrun/torch.distributed.launch.

Related errors

• VOCdevkit dose not in path:'{}'.
• VOCdevkit dose not in path:'{}'.
• not found weights file: {}
• not found weights file: {}
• not found weights file: {}

AI-assisted analysis of WZMIAOMIAO/deep-learning-for-image-processing@1ec3fe6f37 (2026-08-30). Data as JSON: /api/errors/af8521713ecf9260. Report an issue: GitHub.