torch.from_numpy(ndarray) → Tensor
Creates a Tensor from a numpy.ndarray.
The returned tensor and ndarray share the same memory. Modifications to the tensor will be reflected in the ndarray and vice versa. The returned tensor is not resizable.
It currently accepts ndarray with dtypes of numpy.float64, numpy.float32, numpy.float16, numpy.int64, numpy.int32, numpy.int16, numpy.int8, numpy.uint8, and numpy.bool.
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://blog.csdn.net/weixin_36670529/article/details/101776514