PyTorch-RuntimeError:参数0无效：除维度0外，张量的大小必须匹配。在维度2中得到224和244

我正在尝试用两个类进行语义切分。 我有224x224x3图像和224x224二进制分割遮罩。我正在将遮罩重塑为224x224x1（我在某处读到，这是我应该传递给模型的格式）。 当我尝试在train data loader中循环时，它要么运行无误，要么出现以下错误（随机）：

main.py：

import torch
import torchvision.transforms as transforms
from torch.utils.data import DataLoader

from roof_edges_dataset import RoofEdgesDataset

# Device
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Hyperparameters
in_im_shape = (3, 224, 224)
num_classes = 2  # Edge / Non-edge
learning_rate = 0.001
batch_size = 4
n_epochs = 10

# Data - 60% Train - 20% Val - 20% Test
transformations = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

dataset = RoofEdgesDataset(im_path='data/images', ann_path='data/annotations', transform=transformations)

train_size = int(0.8 * len(dataset))
test_size = len(dataset) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(dataset, [train_size, test_size])

train_size = int(0.8 * len(train_dataset))
val_size = len(train_dataset) - train_size
train_dataset, val_dataset = torch.utils.data.random_split(train_dataset, [train_size, val_size])

train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
val_loader = DataLoader(dataset=val_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=True)

# Model

# Loss and Optimizer

# Train
for epoch in range(n_epochs):
    for batch_idx, (image, annotation) in enumerate(train_loader):
        image = image.to(device=device)
        annotation = annotation.to(device=device)
        print(image.shape)
        print(annotation.shape)

    break

# Evaluate

如果你让我知道某件事是否做得错误或愚蠢，以及如何做得更好，我也会非常感激

---

提前谢谢

您的训练图像似乎有不同的大小，例如一个是224x224，另一个是244x244。

---

向所有图像添加裁剪/调整大小转换，以便将它们连接在一起形成一个批。

伙计，我真是瞎了眼。我读的是“得到224和224”而不是244。我现在就去修。你觉得呢，其他的都好吗？总的来说，我在做一些愚蠢的事情吗？例如，我觉得有一种更好的方法可以进行训练/验证/测试拆分。@Codearts（1）我也花了几秒钟才“看到”224！=你没事。（2） 我没有检查你的代码，所以不是这个地方。非常感谢你的帮助。是的，我知道这样做不是为了这个。只是我是Pytork的新手，我问过，万一我做了太糟糕的事情，本质上是错误的，那么糟糕，会让你大吃一惊。如果是这样的话，我想有人会提到一些事情。再次感谢你。

import os
import cv2 as cv
from torch.utils.data import Dataset
from torchvision.transforms import transforms

from utils import create_binary_mask, get_labelme_shapes, plot_segmentation_dataset


class RoofEdgesDataset(Dataset):
    def __init__(self, im_path, ann_path, transform=None):
        self.im_path = im_path
        self.ann_path = ann_path
        self.transform = transform

        self.im_fn_list = sorted(os.listdir(im_path), key=lambda x: int(x.split('.')[0]))
        self.ann_fn_list = sorted(os.listdir(ann_path), key=lambda x: int(x.split('.')[0]))

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

    def __getitem__(self, index):
        im_path = os.path.join(self.im_path, self.im_fn_list[index])
        im = cv.imread(im_path)

        ann_path = os.path.join(self.ann_path, self.ann_fn_list[index])
        ann = create_binary_mask(im, get_labelme_shapes(ann_path))
        ann = ann.reshape(ann.shape[0], ann.shape[1], 1)
        ann = transforms.ToTensor()(ann)

        if self.transform:
            im = self.transform(im)

        return im, ann

import torch
import torchvision.transforms as transforms
from torch.utils.data import DataLoader

from roof_edges_dataset import RoofEdgesDataset

# Device
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Hyperparameters
in_im_shape = (3, 224, 224)
num_classes = 2  # Edge / Non-edge
learning_rate = 0.001
batch_size = 4
n_epochs = 10

# Data - 60% Train - 20% Val - 20% Test
transformations = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

dataset = RoofEdgesDataset(im_path='data/images', ann_path='data/annotations', transform=transformations)

train_size = int(0.8 * len(dataset))
test_size = len(dataset) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(dataset, [train_size, test_size])

train_size = int(0.8 * len(train_dataset))
val_size = len(train_dataset) - train_size
train_dataset, val_dataset = torch.utils.data.random_split(train_dataset, [train_size, val_size])

train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
val_loader = DataLoader(dataset=val_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=True)

# Model

# Loss and Optimizer

# Train
for epoch in range(n_epochs):
    for batch_idx, (image, annotation) in enumerate(train_loader):
        image = image.to(device=device)
        annotation = annotation.to(device=device)
        print(image.shape)
        print(annotation.shape)

    break

# Evaluate