如何解决torchmeta的Miniimagenet数据完整性问题？

问题描述

我正在尝试测试torchMeta：

import torch

import torchvision.transforms as transforms

from torchMeta.datasets.helpers import miniimagenet
from torchMeta.utils.data import BatchMetaDataLoader

from tqdm import tqdm

from pathlib import Path

Meta_split = 'train'
data_path = Path('~/data/').expanduser()
dataset = miniimagenet(data_path,ways=5,shots=5,test_shots=15,Meta_split=Meta_split,download=True)
DataLoader = BatchMetaDataLoader(dataset,batch_size=16,num_workers=4)
print(f'len normal = {len(DataLoader)}')

num_batches = 10
with tqdm(DataLoader,total=num_batches) as pbar:
    for batch_idx,batch in enumerate(pbar):
        train_inputs,train_targets = batch["train"]
        print(train_inputs.size())
        # print(batch_idx)
        if batch_idx >= num_batches:
            break

print('success\a'

但失败：

Using downloaded and verified file: /home/miranda9/data/miniimagenet/mini-imagenet.tar.gz
Traceback (most recent call last):
  File "pro/experiments/Meta_learning/Meta_learning_experiments_submission.py",line 421,in <module>
    main(args)
  File "proj/experiments/Meta_learning/Meta_learning_experiments_submission.py",line 328,in main
    Meta_split='train',download=True)
  File "/home/miranda9/miniconda/envs/Meta-learning/lib/python3.7/site-packages/torchMeta/datasets/helpers.py",line 126,in miniimagenet
    seed=seed,defaults=defaults,**kwargs)
  File "/home/miranda9/miniconda/envs/Meta-learning/lib/python3.7/site-packages/torchMeta/datasets/helpers.py",line 34,in helper_with_default
    dataset = klass(folder,num_classes_per_task=ways,**kwargs)
  File "/home/miranda9/miniconda/envs/Meta-learning/lib/python3.7/site-packages/torchMeta/datasets/miniimagenet.py",line 89,in __init__
    download=download)
  File "/home/miranda9/miniconda/envs/Meta-learning/lib/python3.7/site-packages/torchMeta/datasets/miniimagenet.py",line 127,in __init__
    raise RuntimeError('MiniImagenet integrity check Failed')

其他人在这里报告了该问题，但他们的解决方案对我不起作用：

https://github.com/sungyubkim/GBML/issues/3

我尝试设置download=True标志。现在，我将尝试将本地副本发送到群集，看看是否可行...

解决方法

暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！

如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@）