本文共 971 字，大约阅读时间需要 3 分钟。
torch.flip(input, dims) → Tensor
Reverse the order of a n-D tensor along given axis in dims. 对n维张量的指定维度进行反转（倒序）NOTE
torch.flip makes a copy of input’s data. This is different from NumPy’s np.flip, which returns a view in constant time. Since copying a tensor’s data is more work than viewing that data, torch.flip is expected to be slower than np.flip.
注意torch.flip是反序地复制一份新的数据，这一点与NumPy不同，NumPy是返回一个view，因而使用torch.flip耗时更久。Parameters
Example:
>>> x = torch.arange(10).view(2, 5)>>> xtensor([[0, 1, 2, 3, 4], [5, 6, 7, 8, 9]])>>> torch.flip(x, dims=[0]) # 对第0维进行反转tensor([[5, 6, 7, 8, 9], [0, 1, 2, 3, 4]])>>> torch.flip(x, dims=[1]) # 对第1维进行反转tensor([[4, 3, 2, 1, 0], [9, 8, 7, 6, 5]])>>> torch.flip(x, dims=[0, 1]) # 对第0、1维进行反转tensor([[9, 8, 7, 6, 5], [4, 3, 2, 1, 0]])>>> x.flip(dims=[0, 1]) # 对第0、1维进行反转，与上一句效果相同tensor([[9, 8, 7, 6, 5], [4, 3, 2, 1, 0]])
转载地址：http://thvrj.baihongyu.com/