简单说一下,就是torch.from_numpy()方法把数组转换成张量,且二者共享内存,对张量进行修改比如重新赋值,那么原始数组也会相应发生改变。
Example:
>>> a = numpy.array([1, 2, 3])
>>> t = torch.from_numpy(a)
>>> t
tensor([ 1, 2, 3])
>>> t[0] = -1
>>> a
array([-1, 2, 3])
原文链接:https://www.cnblogs.com/xyzluck/p/12807153.html