【发布时间】:2020-07-29 16:39:35
【问题描述】:
我正在尝试加载数据集以实现超分辨率,并且我设置了两个函数,它们使用 Compose 来裁剪和调整图像大小。
我为输入图像创建的功能正常工作,并且按预期输出。目标图片的transform函数基本相同,只是省略了resize部分。
def input_trans(c_size, sF):
return Compose([
CenterCrop(c_size),
Resize(c_size // sF),
ToTensor(),
])
def goal_trans(c_size):
return Compose([
CenterCrop(c_size),
ToTensor(),
])
这些函数在加载图像时在我的数据集类中使用。我最初有目标 = input.Copy() 但我已经更改了它,因此输入和目标都分别加载图像。 (正在测试 .copy() 是否是问题
def __getitem__(self, idx):
input = Image.open(self.image_filenames[idx]).convert('RGB')
goal = Image.open(self.image_filenames[idx]).convert('RGB')
if self.input_transform:
input = self.input_transform(input)
if self.goal_transform:
print(goal)
print(goal.size)
goal = self.goal_transform(goal)
return input, goal
我收到的错误如下:
Traceback (most recent call last):
File "main.py", line 128, in <module>
main() # execute this only when run directly, not when imported!
File "main.py", line 55, in main
train_model(epoch)
File "main.py", line 40, in train_model
for data_item, batch in enumerate(training_data_loader):
File "C:\Users\[NAME]\anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 345, in __next__
data = self._next_data()
File "C:\Users\[NAME]\anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\dataloader.py", line 385, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "C:\Users\[NAME]\anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "C:\Users\[NAME]\anaconda3\envs\pytorch\lib\site-packages\torch\utils\data\_utils\fetch.py", line 44, in <listcomp>
data = [self.dataset[idx] for idx in possibly_batched_index]
File "main.py", line 118, in __getitem__
goal = self.goal_transform(goal)
File "C:\Users\[NAME]\anaconda3\envs\pytorch\lib\site-packages\torchvision\transforms\transforms.py", line 70, in __call__
img = t(img)
TypeError: ToTensor() takes no arguments
让我感到困惑,因为第一次转换似乎没有问题(我检查过,它在崩溃前确实输出了)。
如果你们能提供任何帮助,我将不胜感激,
谢谢:)
【问题讨论】:
标签: python pytorch torch torchvision