今天在写代码时遇到了一个奇怪的问题，当我定义一个全部为整型的tensor变量，我发现其中的元素会自动转换成浮点型：
找了很久原因才发现是方法名有着极微的差别：
torch.Tensor()是用来定义浮点型tensor类型的，也就是说不管你里面元素填的什么类型，最终都会变成浮点型
而torch.tensor() 注意是小写t，才是用来定义tensor类型变量的，你里面写什么类型的元素他就是什么类型的
另外记录一下tensor的类型转化方法：dtype=troch.int32
- 版权声明： 本博客所有文章除特别声明外，均采用 CC BY 4.0 CN协议 许可协议。转载请注明出处！
Maybe you could buy me a cup of coffee.
Scan this qrcode
Open alipay app scan this qrcode, buy me a coffee!
Scan this qrcode
Open wechat app scan this qrcode, buy me a coffee!
When interacting with Large Language Models (LLMs) like GPT, BERT, or T5, the magic happens not only in the training but also in the decoding phase. D
Large Language Models (LLMs) have gained immense popularity due to their ability to generate, comprehend, and reason over text. But their usefulness g
Large Language Models (LLMs) are revolutionizing how machines understand, generate, and interact with human language. From powering chatbots to aiding
PyTorch is one of the most popular deep learning frameworks due to its ease of use, flexibility, and dynamic computational graph. If you’re new to PyT
转眼间25届的秋招提前批已经开始啦，不禁让我想起了去年这个时间段边实习边秋招边完成毕业论文的煎熬。一直坚持到12月份之后感觉整体结果还是满意的。我同时参加了大陆的秋招和香港小部分公司的招聘（因为感觉香港没有分春秋招，全年可投），拿到的offer情况如下： 大陆秋招总共投递了300多家公司，拿到6个互
/* .article-header{ font-family: Times New Roman } */ h1[itemprop="title"]{ font-weight: bolder; } h1{ font-weight: normal; /* margin-top: 30px; */ }
h1[itemprop="title"]{ font-weight: bolder; } .translate{ position: absolute; right: 10px; font-size: 18px; font-weight: bolder; font-family: Apple Cha
实习 Hong Kong Hospital Authority Student Programmer July 2023 - Present 大语言模型在问诊系统中的研究与应用 负责研究与开发最新的LLM, Fine-tune以及Evaluation。 巴卡拉能源科技 图像算法实习生 June 20
v1.5.2