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

VOCdevkit dose not in path:'{}'.

Error message

VOCdevkit dose not in path:'{}'.

What it means

train_res50_fpn.py validates that `<args.data_path>/VOCdevkit` exists before constructing the VOC dataset; otherwise it raises FileNotFoundError. Same root-check pattern as the other training scripts.

Source

Thrown at pytorch_object_detection/faster_rcnn/train_res50_fpn.py:59

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. Extract the VOC2012 dataset so `<data_path>/VOCdevkit` exists
2. Pass the parent directory containing VOCdevkit as --data-path
3. Confirm the layout VOCdevkit/VOC2012/ImageSets/Main/train.txt exists

Example fix

# before
python train_res50_fpn.py --data-path ./VOCdevkit/VOC2012
# after
python train_res50_fpn.py --data-path ./  # ./VOCdevkit exists

import os
voc_root = args.data_path
if not os.path.exists(os.path.join(voc_root, "VOCdevkit")):
    raise SystemExit(f"VOCdevkit not found under {voc_root}")

try:
    train(args)
except FileNotFoundError as e:
    if "VOCdevkit" in str(e):
        print("Run scripts/download_voc2012.sh first")
        sys.exit(1)

When it happens

Trigger: Running train_res50_fpn.py with --data-path pointing to a directory without the VOCdevkit subfolder, or to VOCdevkit itself instead of its parent.

Common situations: Dataset not downloaded/extracted; wrong data-path argument; running from a different working directory so relative paths break.

Related errors

• VOCdevkit dose not in path:'{}'.
• VOCdevkit dose not in path:'{}'.
• VOCdevkit dose not in path:'{}'.
• image: {} isn't RGB mode.
• not find GPU device for training.

AI-assisted analysis of WZMIAOMIAO/deep-learning-for-image-processing@1ec3fe6f37 (2026-08-30). Data as JSON: /api/errors/ab0245e0673e4d8c. Report an issue: GitHub.