PyTorch 错误 RuntimeError: view size is not compatible with input tensor‘s size and stride (at least o

PyTorch 错误 RuntimeError: view size is not compatible with input tensor’s size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(…) instead.

flyfish
具体提示如下

Processinggender.py:212: UserWarning: This overload of cuda is deprecated:
	cuda(torch.device device, bool async, *, torch.memory_format memory_format)
Consider using one of the following signatures instead:
	cuda(torch.device device, bool non_blocking, *, torch.memory_format memory_format) (Triggered internally at  /pytorch/torch/csrc/utils/python_arg_parser.cpp:882.)
  inputs, targets = inputs.cuda(), targets.cuda(async=True)
Traceback (most recent call last):
    correct_k = correct[:k].view(-1)
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
解决方案
 按照提示
 correct_k = correct[:k].view(-1)
 更改为
 correct_k = correct[:k].contiguous().view(-1)
                    PyTorch 错误 RuntimeError: view size is not compatible with input tensor‘s size and stride (at least o
                    PyTorch 错误 RuntimeError: view size is not compatible with input tensor’s size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(…) instead.flyfish具体提示如下Processinggender.py:212: UserWarning: This overload of cuda is 
view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
错误代码：
prec1 = accuracy(-1 * dist_xt_ct.data, target_targets, topk=(1,))[0].item()
正确代码：
					
RuntimeError: view size is not compatible with input tensor‘s size and stride解决记录
				
File "/home/yuanlina/PycharmProjects/ViT-pytorch-main/test1-10.py", line 136, in Accuracy
    correct_k = correct[:k].view(-1).float().sum(0, keepdim=True)
correct_k = correct[:k].contiguous().view(-1).float().sum(0, keepdim=True)
				
python运行报错：RuntimeError: view size is not compatible with input tensor’s size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(…) instead.
感谢 柠檬树下你和我 的文章，知道了报错原因和解决方案。报错原因： view()需要Tensor中的元素地址是连续的，实际操作时可能出现Tensor不连续的
				PyTorch - transforms.ColorJitter 改变图像的属性：亮度（brightness）、对比度（contrast）、饱和度（saturation）和色调（hue)
					63204