# Getting Started

Source: https://www.tensorplay.cn/docs/guide/index.html

This guide is the fastest path from “I just installed TensorPlay” to “I trained a model.”
It is organized as a small series of lessons, each short enough to read and run in one sitting.
Every example is copy-paste runnable against an installed TensorPlay.

- [Tensors](/docs/guide/tensors.html)

- [Datasets and DataLoaders](/docs/guide/datasets.html)

- [Transforms](/docs/guide/transforms.html)

- [Models](/docs/guide/models.html)

- [Autograd](/docs/guide/autograd.html)

- [Training](/docs/guide/training.html)

- [Save and Load the Model](/docs/guide/saveload.html)

## The path

Follow the pages in order. Each one builds on the previous.

- [Tensors](/docs/guide/tensors.html) — create, inspect, index, and do math with tensors.

- [Datasets and DataLoaders](/docs/guide/datasets.html) — organize data and stream it in batches.

- [Transforms](/docs/guide/transforms.html) — preprocess and augment data before it reaches a model.

- [Models](/docs/guide/models.html) — build a neural network with nn.Module.

- [Autograd](/docs/guide/autograd.html) — make tensors learnable and get gradients automatically.

- [Training](/docs/guide/training.html) — the loss + optimizer + loop that makes the model learn.

- [Save and Load](/docs/guide/saveload.html) — keep the trained weights and checkpoints.

After those seven lessons you can train, evaluate, and persist a real model.

## What TensorPlay is

TensorPlay is a tensor library for deep learning. It gives you three things you will use on
every line of code:

- Tensors — multi-dimensional arrays that carry a device, a data type, and support efficient vectorized math (tensorplay.Tensor).

- Automatic differentiation — every operation records itself into a graph, so for any scalar loss you can call loss.backward() and get the gradient of that loss with respect to every tensor that was involved (tensorplay.autograd).

- A neural-network toolkit — layers and models expressed as tensorplay.nn.Module, optimizers such as SGD and Adam (tensorplay.optim), vision transforms (tensorplay.vision.transforms), and data helpers such as DataLoader and TensorDataset (tensorplay.utils.data).

A defining design choice: the engine is explicit and readable. The graph that backward()
walks is real code you can step through, which makes TensorPlay a good place to learn how
the machinery works, not just to use it.

## Install and check it works

You can install the latest release, or build from source. See the [README](https://github.com/lexing-2026/TensorPlay/blob/main/README.md)
for the full install options including GPU variants. Once installed, run this smoke test:

```
import tensorplay as tp

x = tp.tensor([1.0, 2.0, 3.0], requires_grad=True)
y = (x * x).sum()
y.backward()
print(x.grad)  # tensor([2., 4., 6.])
```

If that prints 2 4 6 as a gradient, your installation is working.

## Where to go next

- API reference — every function and class, grouped by area. Start at [tensorplay](/docs/tensorplay.html) for the core tensor API, then [nn](/docs/nn.html) for layers and losses, and [optim](/docs/optim.html) for optimizers.

- Deep-dive notes — the [notes](/docs/notes/index.html) section explains the concepts behind the code: how autograd builds its graph, broadcasting rules, serialization, randomness, and more.