pytorch实现numpy与tensor之间的转换

1.tensor转numpy:

a = torch.ones(2,2)b = a.numpy()c=np.array(a) #也可以转numpy数组print(type(a))print(type(b))print(a)print(b)

结果<class ‘torch.Tensor’><class ‘numpy.ndarray’>tensor([[1., 1.],[1., 1.]])[[1. 1.][1. 1.]]

2.numpy转tensor：

2345678910import torchimport numpy as np a = np.ones(5)b = torch.from_numpy(a)c=torch.Tensor(a) #也可以转pytorch Tensorprint(type(a))print(type(b))print(a)print(b)

输出：
<class ‘numpy.ndarray’><class ‘torch.Tensor’>[1. 1. 1. 1. 1.]tensor([1., 1., 1., 1., 1.], dtype=torch.float64)

pytorch的tensor对象与numpy数组是可以相互转换的，且numpy数组的默认类型是double