How to use PyTorch with Python?

In order to use PyTorch with Python, you first need to install the PyTorch library. You can find installation instructions on the official PyTorch website and choose the appropriate installation method based on your operating system and configuration.

After installation is complete, you can use the following code to verify if PyTorch is installed and running correctly:

import torch

# 创建一个张量
x = torch.tensor([[1, 2, 3], [4, 5, 6]])

# 打印张量
print(x)

# 运行在GPU上
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
x = x.to(device)

# 运行张量上的操作
y = torch.sum(x, dim=1)

# 打印结果
print(y)

This is a basic example that demonstrates how to create, print, and perform operations on tensors in PyTorch. You can utilize more complex models and functions to conduct research and application development in deep learning using PyTorch’s additional features according to your needs.