Deep Learning Academy · 课时

调用 backward() 获取梯度

用一行代码填充 .grad

调用 backward() 获取梯度 是 CoddyKit 上的免费 Deep Learning Academy 课时。这是第 2 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。

One Line to Differentiate

Once your graph is built, a single call does all the calculus. Run backward() on your output and gradients flow back to every input.

Start From a Scalar

You call backward on the final number you want to minimize, usually the loss. It must be a single scalar so autograd knows where to start.

y = x ** 2
y.backward()

Gradients Land in .grad

After backward runs, each leaf tensor's .grad holds the derivative of the output with respect to that tensor. The math is already done.

print(x.grad)

A Quick Check by Hand

For y equal to x squared, calculus says the derivative is 2x. At x equal to 2 that is 4, and PyTorch fills x.grad with exactly 4.0.

Backward Walks the Graph

backward() travels the graph from output to inputs, applying the chain rule at every node. You wrote only the forward math and got all of this free.

Gradients for Many Inputs

If your output depends on several tracked tensors, one backward call fills the .grad of each of them at once. That is how whole models update.

loss = (a * b + c).sum()
loss.backward()

The Graph Is Spent

By default the graph is freed after backward to save memory, so calling it twice errors. You build a fresh graph on the next forward pass.

Keep It If You Must

Need to call backward again on the same graph? Pass retain_graph equals true. You rarely need this, so skip it unless an error tells you to.

loss.backward(retain_graph=True)

Non-Scalar Outputs

If your output is a vector, backward needs a gradient argument saying how to weight each element. Most of the time you sum to a scalar instead.

This Is the Backward Pass

That single backward call is the famous backward pass of training. Forward computes predictions, backward computes how to fix the weights.

From Gradients to Learning

The numbers in .grad tell each weight which way to move. An optimizer reads them and nudges the weights to lower the loss a little.

Quick Check

Make sure backward is clear.

Recap

Call backward() on a scalar loss and autograd applies the chain rule across the graph, filling each tensor's .grad with its derivative. That is the backward pass. 🔁

常见问题解答

「调用 backward() 获取梯度」课时是免费的吗？

是的 — 「调用 backward() 获取梯度」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。

「调用 backward() 获取梯度」这节课中我会学到什么？

用一行代码填充 .grad 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 2 节课，共 4 节。

「调用 backward() 获取梯度」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