Question

我正在尝试创建一个自定义 pytorch 数据集以插入 DataLoader，该数据集由单通道图像 (20000 x 1 x 28 x 28)、单通道掩码 (20000 x 1 x 28 x 28) 和三个标签(20000 X 3)。

按照文档，我想我会测试使用以下代码创建具有单通道图像和单通道蒙版的数据集：

class CustomDataset(Dataset):

    def __init__(self, images, masks, transforms=None, train=True): 
        self.images = images
        self.masks = masks
        self.transforms = transforms

    def __getitem__(self, index):
        image = self.images.iloc[index, :]
        image = np.asarray(image).astype(np.float64).reshape(28, 28, 1)
        mask = self.masks.iloc[index, :]
        mask = np.asarray(mask).astype(np.float64).reshape(28, 28, 1)
        transformed_image = self.transforms(image)
      
        return transformed_image, mask

    def __len__(self):  

       return len(self.images)

使用该类，我从两个 Pandas 数据帧形成数据集并插入 DataLoader。

transform = transforms.Compose(
    [transforms.ToPILImage(),
     transforms.ToTensor(),
     transforms.Normalize((0.5, ), (0.5, ))
])

train_images = pd.read_csv('train.csv')
train_masks = pd.read_csv('masks.csv')

train_data = CustomDataset(train_images, train_masks, transform)
trainloader = DataLoader(train_data, batch_size=128, shuffle=True)

对于左侧的图像和右侧的蒙版，我希望 trainloader 中单个批次的形状为 ([128, 1, 28, 28], [128, 1, 28, 28])。

相反，单个批次 trainloader 的形状是 ([128, 1, 28, 28], [128])，这让我觉得掩码已以某种方式转化为标签。

我该如何解决这个问题，除了蒙版之外，我该如何添加实际标签？预先感谢您的帮助！

Answer 1

也许您也需要在掩码上应用变换（不包括归一化）。喜欢

class CustomDataset(Dataset):

def __init__(self, images, masks, transforms_image=None, transforms_mask=None, train=True): 
    self.images = images
    self.masks = masks
    self.transforms_image = transforms_image
    self.transforms_mask = transforms_mask
def __getitem__(self, index):
    image = self.images.iloc[index, :]
    image = np.asarray(image).astype(np.float64).reshape(28, 28, 1)
    mask = self.masks.iloc[index, :]
    mask = np.asarray(mask).astype(np.float64).reshape(28, 28, 1)
    transformed_image = self.transforms(image)
  
    return transformed_image, mask

def __len__(self):  

   return len(self.images)

和

   transform_image = transforms.Compose(
    [transforms.ToPILImage(),
     transforms.ToTensor(),
     transforms.Normalize((0.5, ), (0.5, ))
])

   transform_mask = transforms.Compose(
    [transforms.ToPILImage(),
     transforms.ToTensor()
])
train_images = pd.read_csv('train.csv')
train_masks = pd.read_csv('masks.csv')

train_data = CustomDataset(train_images, train_masks, transform_image, transform_mask)
trainloader = DataLoader(train_data, batch_size=128, shuffle=True)

如何创建具有多个标签和掩码的自定义 Pytorch 数据集？

1 个答案: