Deep Learning Academy · 课时

您的第一个 torch.tensor

创建张量，并打印其形状和数据类型

您的第一个 torch.tensor 是 CoddyKit 上的免费 Deep Learning Academy 课时。这是第 4 节课，共 4 节。你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。这是 Deep Learning Academy 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 Deep Learning Academy 课程共包含 4 节课。

本课时的部分内容尚未翻译，以英文显示。

Meet the Tensor

A tensor is PyTorch's core data container, a grid of numbers much like a NumPy array but ready to run on a GPU. 🧮

Create One from a List

The simplest way to make a tensor is torch.tensor from a Python list. PyTorch copies your numbers into a fast numerical grid.

x = torch.tensor([1, 2, 3])

Print It Out

Printing a tensor shows its values wrapped in tensor(...), so you always know you are looking at PyTorch data, not a plain list.

print(x)

Shape Describes Structure

The shape tells you the size along each dimension. A flat list of three values has a shape of three.

print(x.shape)

Build a 2D Tensor

Nest lists to make a grid. This matrix has two rows and three columns, so its shape reads as two by three.

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

Dtype Is the Number Type

Every tensor has a dtype, the kind of number it stores. Whole numbers become int64, decimals become float32 by default.

print(x.dtype)

Floats for Training

Networks learn with decimals, so most model data is float32. Add a decimal point and PyTorch picks the float type for you.

y = torch.tensor([1.0, 2.0, 3.0])

Set the Dtype Yourself

You can request a type directly with the dtype argument, which is handy when you need floats from integer input.

z = torch.tensor([1, 2], dtype=torch.float32)

Tensors Full of Zeros

Need a blank tensor of a given size? torch.zeros fills the shape you ask for with zeros, perfect as a starting buffer.

torch.zeros(2, 3)

Random Tensors

Model weights often start random. torch.rand gives a tensor of the shape you choose, filled with values between zero and one.

torch.rand(2, 3)

Count the Dimensions

The number of dimensions is the tensor's rank. Read it with .ndim: a vector is rank one, a matrix is rank two.

print(m.ndim)

Quick Check

Reason about the shape of a nested-list tensor.

Recap

You created tensors from lists, read their shape and dtype, and made zeros and random grids. This is the data deep learning runs on. ✅

常见问题解答

「您的第一个 torch.tensor」课时是免费的吗？

是的 — 「您的第一个 torch.tensor」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 Deep Learning Academy 课程的其余内容，请升级到 CoddyKit PRO。 Deep Learning Academy 课程共包含 4 节课。

「您的第一个 torch.tensor」这节课中我会学到什么？

创建张量，并打印其形状和数据类型你通过在浏览器中直接运行的动手代码来练习 Deep Learning Academy，全天候 AI 导师会在你学习这节课的过程中回答你的问题。

学习 Deep Learning Academy 需要有经验吗？

无需任何先前经验。CoddyKit 上的 Deep Learning Academy 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。这是第 4 节课，共 4 节。

「您的第一个 torch.tensor」课时需要多长时间？

大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。

我能在这节 Deep Learning Academy 课中编写并运行代码吗？

能。每节 Deep Learning Academy 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。

此课程中的所有课时

← 返回 Deep Learning Academy