torch.tensor

`torch.tensor` 是 PyTorch 库中的一个函数，用于创建并返回一个新的张量（tensor）。张量是 PyTorch 中最基本的数据结构，类似于 NumPy 中的多维数组，但可以在 GPU 上运行以加速计算。`torch.tensor` 可以接受多种类型的参数，如 Python 列表、NumPy 数组、标量值等，并将其转换为张量。例如，以下代码创建了一个形状为 (2, 3) 的张量：

import torch

x = torch.tensor([[1, 2, 3], [4, 5, 6]])
print(x)

输出结果为：

tensor([[1, 2, 3],
        [4, 5, 6]])

相关问题

torch.Tensor

torch.Tensor is a multi-dimensional array in PyTorch, similar to a NumPy array. It is the fundamental data structure of PyTorch and is used to store and manipulate data in deep learning models. A tensor can be created with the torch.Tensor() constructor or by converting a NumPy array to a PyTorch tensor using the torch.from_numpy() function. Tensors can be manipulated using a wide range of mathematical operations and can be moved to different devices, such as a GPU, using the to() method.