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

VOCdevkit dose not in path:'{}'.

Error message

VOCdevkit dose not in path:'{}'.

What it means

train_mobilenetv2.py validates the dataset root before training: if `<VOC_root>/VOCdevkit` does not exist, it raises FileNotFoundError. This guards against a wrong or unextracted VOC dataset path.

Source

Thrown at pytorch_object_detection/faster_rcnn/train_mobilenetv2.py:65

    # 检查保存权重文件夹是否存在，不存在则创建
    if not os.path.exists("save_weights"):
        os.makedirs("save_weights")

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

    VOC_root = "./"  # VOCdevkit
    aspect_ratio_group_factor = 3
    batch_size = 8
    amp = False  # 是否使用混合精度训练，需要GPU支持

    # 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 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=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, batch_size)

    nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8])  # number of workers
    print('Using %g dataloader workers' % nw)

View on GitHub (pinned to 1ec3fe6f37)

Solutions

1. Download and extract the VOC2012 dataset so that `<data_path>/VOCdevkit` exists
2. Pass the PARENT directory of VOCdevkit as --data-path (e.g. not .../VOCdevkit but .../VOCdevkit's parent)
3. Verify the dataset is the expected layout: VOCdevkit/VOC2012/ImageSets/Main/train.txt

Example fix

# before
python train_mobilenetv2.py --data-path ./VOCdevkit
# after
python train_mobilenetv2.py --data-path .   # directory that contains VOCdevkit/

import os
voc_root = "./data"
assert os.path.exists(os.path.join(voc_root, "VOCdevkit")), f"VOCdevkit missing under {voc_root}"

try:
    run_training(voc_root)
except FileNotFoundError as e:
    if "VOCdevkit" in str(e):
        download_and_extract_voc2012(voc_root)
        run_training(voc_root)

When it happens

Trigger: Running train_mobilenetv2.py with --data-path (or VOC_root) pointing to a directory that does not directly contain the VOCdevkit folder, or to the VOCdevkit folder itself instead of its parent.

Common situations: Forgetting to download/extract the VOC2012 dataset; passing the path of VOCdevkit rather than its parent; typo or relative path resolved from a different working directory.

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/46d36a36dd380dbb. Report an issue: GitHub.