Deep Learning Academy · 课时

ResNet：跳跃连接深入网络

利用残差克服梯度消失

ResNet：跳跃连接深入网络 是 CoddyKit 上的免费 Deep Learning Academy 课时。这是第 3 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。

Deeper Got Worse

Surprisingly, plain nets past a point trained worse as they got deeper. More layers should not hurt, yet they did. Something was broken.

The Real Culprit

Gradients shrank as they flowed back through many layers, a problem called vanishing gradients. Deep nets stopped learning.

The Skip Connection

ResNets fix is elegant: add a shortcut that lets the input jump past a block and add itself to the output.

Learn the Residual

Instead of learning the full mapping, each block only learns the residual, the small change to add on top of the input.

Easy to Stay Still

If a block is not useful, it can just learn zeros and pass the input straight through. Doing nothing becomes effortless.

A Gradient Highway

The shortcut gives gradients a clean path backward, so even very deep networks keep learning.

The Residual Block

A block computes some layers, then adds the original input back. That single add is the whole trick.

def forward(self, x):
    out = self.conv_layers(x)
    return self.relu(out + x)

Going Very Deep

With shortcuts, ResNet trained 50, 101, even 152 layers and won ImageNet 2015. Depth finally paid off.

The Bottleneck Block

Deeper ResNets use a 1x1, 3x3, 1x1 bottleneck to cut compute while keeping representational power.

Identity Everywhere

This residual idea spread far beyond vision. Transformers and many modern nets rely on the same identity shortcut.

A Tiny ResNet Block

You can sketch the core in a few lines: convolve, then add the input back before the activation. Here is the shape of it.

out = bn(conv(x))
out = relu(out + x)  # the skip connection

Quick Check

Focus on what the skip connection actually achieves.

Recap: Shortcuts Win

ResNets skip connections made extreme depth trainable by letting blocks learn residuals. One add changed everything. Great progress!

常见问题解答

「ResNet：跳跃连接深入网络」课时是免费的吗？

是的 — 「ResNet：跳跃连接深入网络」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。

「ResNet：跳跃连接深入网络」这节课中我会学到什么？

利用残差克服梯度消失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 3 节课，共 4 节。

「ResNet：跳跃连接深入网络」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