使用Pytorch数据集和数据加载器加载图像数据的问题

Question

我在加载图像数据时遇到问题。

train_dir = 'images'
train_mask_dir = 'masks'

class TissueDataset(Dataset):
    def __init__(self, image_dir, mask_dir, transforms=None):
        self.image_dir = image_dir
        self.mask_dir = mask_dir
        self.transforms = transforms
        self.images = os.listdir(image_dir)

    def __len__(self):
        return len(self.images)

    def __getitem__(self, idx):
        img_path = os.path.join(self.image_dir, self.images[idx])
        mask_path = os.path.join(self.mask_dir, self.images[idx])

        image = np.array(Image.open(img_path).convert('RGB'))
        mask = np.array(Image.open(mask_path).convert('L'), dtype=np.float32)
        mask = np.round(mask / 255).astype(np.float32)
        if self.transforms:
            aug = self.transforms(image=image, mask=mask)
            image = aug['image']
            mask = aug['mask']
            
            return image, mask

train_dataset = TissueDataset(
    image_dir = train_dir,
    mask_dir = train_mask_dir,
    transforms=None
)

train_loader = DataLoader(
        train_dataset,
        batch_size=BATCH_SIZE,
        num_workers=2,
        pin_memory=PIN_MEMORY,
        shuffle=True
    )

x, y = next(iter(train_loader))

print(f'x = shape: {x.shape}; type: {x.dtype}')
print(f'x = min: {x.min()}; max: {x.max()}')
print(f'y = shape: {y.shape}; class: {y.unique()}; type: {y.dtype}')

我遇到的错误如下：

FileNotFoundError                         Traceback (most recent call last)
<ipython-input-36-869de9fa31b7> in <module>()
----> 1 x, y = next(iter(train_loader))
      2 
      3 print(f'x = shape: {x.shape}; type: {x.dtype}')
      4 print(f'x = min: {x.min()}; max: {x.max()}')
      5 print(f'y = shape: {y.shape}; class: {y.unique()}; type: {y.dtype}')

3 frames
/usr/local/lib/python3.7/dist-packages/torch/_utils.py in reraise(self)
    432             # instantiate since we don't know how to
    433             raise RuntimeError(msg) from None
--> 434         raise exception
    435 
    436 

FileNotFoundError: Caught FileNotFoundError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
    data = fetcher.fetch(index)
  File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 49, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "<ipython-input-29-c33cd66a240c>", line 16, in __getitem__
    mask = np.array(Image.open(mask_path).convert('L'), dtype=np.float32)
  File "/usr/local/lib/python3.7/dist-packages/PIL/Image.py", line 2843, in open
    fp = builtins.open(filename, "rb")
FileNotFoundError: [Errno 2] No such file or directory: 'masks/2018_74969_1-1_2019-02-2100_48_39-lv1-35186-14908-3285-3747.jpg'

当图像和蒙版位于正确的目录中时，我无法理解为什么它为错误的文件（或其他）显示正确的目录。我还检查了我的自定义数据集，似乎它工作正常（我可以打开此图像）。

img_path = os.path.join(train_dir, os.listdir(train_dir)[0])
mask_path = os.path.join(train_mask_dir, os.listdir(train_mask_dir)[3])
image = np.array(Image.open(img_path).convert('RGB'))
mask = np.array(Image.open(mask_path).convert('L'), dtype=np.float32)
mask = np.round(mask / 255).astype(np.float32)
print(mask_path)
print(img_path)

输出：

masks/18-09530A_2019-05-0723_50_03-lv1-34626-18358-3736-6181_mask.jpg
images/18-09530A_2019-05-0723_50_03-lv1-34626-18358-3736-6181.jpg

我非常感谢有关此问题的任何帮助或提示。

Answer 1

您可以使用“C:\sample_folder\masks\example.jpg”等精确路径来使用“masks/example.jpg”等相对路径。

请检查这些分配的值

img_path = os.path.join(train_dir, os.listdir(train_dir)[0])
mask_path = os.path.join(train_mask_dir, os.listdir(train_mask_dir)[3])