变分自编码器与潜在空间
从学习到的分布中采样新数据
变分自编码器与潜在空间 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。
Beyond Plain Codes
A variational autoencoder, or VAE, does not store one fixed code per input. Instead it learns a smooth, organized latent space you can actually sample from.
Encode to a Distribution
The VAE encoder outputs a mean and a variance instead of a single point. Each input becomes a little cloud of likely latent codes.
mu, logvar = encoder(x)Sample From the Cloud
To get a code, you sample from that cloud using its mean and variance. Sampling adds the randomness that makes the space generative.
The Reparameterization Trick
Random sampling blocks gradients, so the reparameterization trick moves the randomness aside. Now you can still backpropagate through the sample.
std = torch.exp(0.5 * logvar)
z = mu + std * torch.randn_like(std)Two Losses, Not One
A VAE balances two goals: reconstruction loss for accurate rebuilds, plus a term that shapes the latent space. They pull against each other.
The KL Divergence Term
The second loss is the KL divergence. It nudges each cloud toward a standard normal, keeping the latent space tidy and continuous.
kl = -0.5 * torch.sum(1 + logvar - mu**2 - logvar.exp())A Smooth Latent Space
Thanks to the KL term, nearby codes decode to similar outputs. This smoothness means you can walk between points and get sensible results. ✨
Generate Brand-New Data
Because the space is organized, you can sample new codes from a normal distribution and decode them into fresh, never-seen samples.
z = torch.randn(1, latent_dim)
new_sample = decoder(z)Interpolate Between Inputs
Blend two latent codes and decode the mix to morph one input into another. This smooth interpolation is a signature VAE trick.
z = 0.5 * z_a + 0.5 * z_bVAE vs Plain Autoencoder
A plain autoencoder compresses; a VAE compresses and becomes generative. The extra KL term is what unlocks sampling new data.
Tune the Balance
Weighting the KL term, often called beta, controls the tradeoff. Higher beta gives a cleaner space but slightly blurrier reconstructions.
Quick Check
What gives a VAE its generative power?
Recap
A VAE encodes inputs as distributions, samples with the reparameterization trick, and adds a KL term for a smooth space you can sample and interpolate. 🎉
用 AI 导师学习 Python — 免费
在浏览器中编写并运行真实代码，获得全天候 AI 导师的即时帮助，并在网页或应用中继续学习。
- 课程
- 30
- 课程
- 120
常见问题解答
「变分自编码器与潜在空间」课时是免费的吗？
是的 — 「变分自编码器与潜在空间」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。
「变分自编码器与潜在空间」这节课中我会学到什么？
从学习到的分布中采样新数据 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。
「变分自编码器与潜在空间」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
- 编码器、瓶颈与解码器
- 去噪自编码器
- 变分自编码器与潜在空间
- 通过重建误差检测异常