论文阅读笔记:Denoising Diffusion Implicit Models (3)

发布于:2025-04-02 ⋅ 阅读:(173) ⋅ 点赞:(0)

0、快速访问

论文阅读笔记:Denoising Diffusion Implicit Models (1)
论文阅读笔记:Denoising Diffusion Implicit Models (2)
论文阅读笔记:Denoising Diffusion Implicit Models (3)
论文阅读笔记:Denoising Diffusion Implicit Models (4)

4、DDPM与DDIM的相同点与不同点

4.1、 相同点

DDPM与DDIM的训练过程相同,因此DDPM训练的模型可以直接在DDIM当中使用,训练过程下所示
请添加图片描述

4.2、不同点

DDPM与DDIM在推理阶段是不同的。
DDPM在推理阶段的采样过程如下图所示。首先模型 ϵ θ \epsilon_\theta ϵθ​预测出 x 0 → x t x_0\to x_t x0​→xt​所添加的噪音 ϵ t \epsilon_t ϵt​,然后根据公式 ( x t − 1 − α t 1 − α ˉ t ⋅ ϵ t ) \Big(x_t-\frac{1-\alpha_t}{\sqrt{1-\bar{\alpha}_{t}}}\cdot \epsilon_t\Big) (xt​−1−αˉt​ ​1−αt​​⋅ϵt​)得到 x t − 1 x_{t-1} xt−1​分布的均值,最后在均值上添加对应的噪音,得到 x t − 1 x_{t-1} xt−1​
请添加图片描述
接下来介绍DDIM的采样过程。根据上文论文阅读笔记:Denoising Diffusion Implicit Models (2)中公式(2)所示的前向加噪过程:在给定 x 0 x_0 x0​和 x t x_t xt​的条件下, x t − 1 x_{t-1} xt−1​的分布 q σ ( x t − 1 ∣ x t , x 0 ) = N ( x t − 1 ∣ 1 − α t − 1 − σ t 2 1 − α t ⋅ x t + [ α t − 1 − α t ⋅ ( 1 − α t − 1 − σ t 2 ) 1 − α t ] ⋅ x 0 , σ t 2 I ) q_{\sigma}(x_{t-1}|x_t,x_0)=N\Bigg(x_{t-1}|\sqrt{\frac{1-\alpha_{t-1}-\sigma_t^2}{1-\alpha_{t}}}\cdot x_t+ \bigg[\sqrt{\alpha_{t-1}}- \frac{\sqrt{ \alpha_t\cdot (1-\alpha_{t-1}-\sigma_t^2} )}{\sqrt{1-\alpha_t}} \bigg] \cdot x_0 ,\sigma_t^2 I\Bigg) qσ​(xt−1​∣xt​,x0​)=N(xt−1​∣1−αt​1−αt−1​−σt2​​ ​⋅xt​+[αt−1​ ​−1−αt​ ​αt​⋅(1−αt−1​−σt2​ ​)​]⋅x0​,σt2​I),也就是 x t − 1 x_{t-1} xt−1​的计算过程如公式(1)所示。
x t − 1 = α t − 1 ⋅ x 0 + 1 − α t − 1 − σ t 2 ⋅ x t − α t x 0 1 − α t + σ t 2 ϵ t ⏟ 标准高斯分布 = α t − 1 ⋅ x t − 1 − α t ⋅ z t α t + 1 − α t − 1 − σ t 2 ⋅ 1 1 − α t ⋅ ( x t − α t ⋅ ( x t − 1 − α t ⋅ z t α t ) ) + σ t 2 ⋅ ϵ t = α t − 1 ⋅ x t − 1 − α t ⋅ z t α t + 1 − α t − 1 − σ t 2 ⋅ 1 1 − α t ⋅ ( x t − x t + 1 − α t ⋅ z t ) + σ t 2 ⋅ ϵ t = α t − 1 ⋅ x t − 1 − α t ⋅ z t α t ⏟ = x 0 + 1 − α t − 1 − σ t 2 ⋅ z t + σ t 2 ⋅ ϵ t \begin{equation} \begin{split} x_{t-1}&= \sqrt{\alpha_{t-1}}\cdot x_0+\sqrt{1-\alpha_{t-1}-\sigma_t^2}\cdot \frac{x_t-\sqrt{\alpha}_t x_0}{\sqrt{1-\alpha_t}} + \sigma_t^2 \underbrace{\epsilon_t}_{标准高斯分布} \\ &=\sqrt{\alpha_{t-1}}\cdot \frac{x_t-{\sqrt{1-\alpha_t}\cdot z_t}}{\sqrt{\alpha_t}} + \sqrt{1-\alpha_{t-1}-\sigma_t^2}\cdot \frac{1}{\sqrt{1-\alpha_t}}\cdot \bigg(x_t- \bcancel{\sqrt {\alpha_t}}\cdot \big(\frac{x_t-{\sqrt{1-\alpha_t}\cdot z_t}}{\bcancel{\sqrt{\alpha_t}}} \big) \bigg) + \sigma_t^2 \cdot\epsilon_t\\ &=\sqrt{\alpha_{t-1}}\cdot \frac{x_t-{\sqrt{1-\alpha_t}\cdot z_t}}{\sqrt{\alpha_t}}+ \sqrt{1-\alpha_{t-1}-\sigma_t^2}\cdot \frac{1}{\sqrt{1-\alpha_t}}\cdot (x_t - x_t + \sqrt{1-\alpha_t}\cdot z_t)+ \sigma_t^2 \cdot\epsilon_t\\ &=\sqrt{\alpha_{t-1}}\cdot \underbrace{ \frac{x_t-{\sqrt{1-\alpha_t}\cdot z_t}}{\sqrt{\alpha_t}}}_{=x_0}+ \sqrt{1-\alpha_{t-1}-\sigma_t^2}\cdot z_t + \sigma_t^2 \cdot\epsilon_t \end{split} \end{equation} xt−1​​=αt−1​ ​⋅x0​+1−αt−1​−σt2​ ​⋅1−αt​ ​xt​−α ​t​x0​​+σt2​标准高斯分布 ϵt​​​=αt−1​ ​⋅αt​ ​xt​−1−αt​ ​⋅zt​​+1−αt−1​−σt2​ ​⋅1−αt​ ​1​⋅(xt​−αt​ ​ ​⋅(αt​ ​ ​xt​−1−αt​ ​⋅zt​​))+σt2​⋅ϵt​=αt−1​ ​⋅αt​ ​xt​−1−αt​ ​⋅zt​​+1−αt−1​−σt2​ ​⋅1−αt​ ​1​⋅(xt​−xt​+1−αt​ ​⋅zt​)+σt2​⋅ϵt​=αt−1​ ​⋅=x0​ αt​ ​xt​−1−αt​ ​⋅zt​​​​+1−αt−1​−σt2​ ​⋅zt​+σt2​⋅ϵt​​​​
得到的公式(1)就是在推断时跳 1 1 1步的采样过程。
由前向加噪过程,可以推知 q σ ( x t − 2 ∣ x t − 1 , x 0 ) = N ( x t − 2 ∣ 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ x t − 1 + [ α t − 2 − α t − 1 ⋅ ( 1 − α t − 2 − σ t − 1 2 ) 1 − α t − 1 ] ⋅ x 0 , σ t − 1 2 I ) q_{\sigma}(x_{t-2}|x_{t-1},x_0)=N\bigg(x_{t-2}|\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot x_{t-1}+ \bigg[\sqrt{\alpha_{t-2}}- \frac{\sqrt{ \alpha_{t-1}\cdot (1-\alpha_{t-2}-\sigma_{t-1}^2} )}{\sqrt{1-\alpha_{t-1}}} \bigg] \cdot x_0 ,\sigma_{t-1}^2 I\bigg) qσ​(xt−2​∣xt−1​,x0​)=N(xt−2​∣1−αt−1​1−αt−2​−σt−12​​ ​⋅xt−1​+[αt−2​ ​−1−αt−1​ ​αt−1​⋅(1−αt−2​−σt−12​ ​)​]⋅x0​,σt−12​I)。接下来考虑,跳 2 2 2步时的采样过程,即在给定 x 0 x_0 x0​和 x t x_t xt​时, x t − 2 x_{t-2} xt−2​时的采样过程,即 q σ ( x t − 2 ∣ x 0 , x t ) q_\sigma(x_{t-2}|x_0,x_t) qσ​(xt−2​∣x0​,xt​)的分布。
首先,我们可以确定 q σ ( x t − 2 ∣ x 0 , x t ) q_\sigma(x_{t-2}|x_0,x_t) qσ​(xt−2​∣x0​,xt​)是高斯分布,假设其均值和方差分别为 μ t − 2 \mu_{t-2} μt−2​和 σ t − 2 2 \sigma_{t-2}^2 σt−22​。由于 q σ ( x t − 2 ∣ x 0 , x t ) q_\sigma(x_{t-2}|x_0,x_t) qσ​(xt−2​∣x0​,xt​)是 q σ ( x t − 2 , x t − 1 ∣ x 0 , x t ) q_\sigma(x_{t-2},x_{t-1}|x_0,x_t) qσ​(xt−2​,xt−1​∣x0​,xt​) 的边缘分布。

q σ ( x t − 2 ∣ x 0 , x t ) = ∫ q σ ( x t − 2 , x t − 1 ∣ x 0 , x t ) ⋅ d x t − 1 = ∫ q σ ( x t − 2 ∣ x 0 , x t − 1 ) ⋅ q σ ( x t − 1 ∣ x 0 , x t ) ⋅ d x t − 1 \begin{equation} \begin{split} q_\sigma(x_{t-2}|x_0,x_t)&= \int q_\sigma(x_{t-2},x_{t-1}|x_0,x_t) \cdot dx_{t-1} \\ &=\int q_\sigma(x_{t-2}|x_0,x_{t-1}) \cdot q_\sigma(x_{t-1}|x_0,x_{t}) \cdot dx_{t-1} \end{split} \end{equation} qσ​(xt−2​∣x0​,xt​)​=∫qσ​(xt−2​,xt−1​∣x0​,xt​)⋅dxt−1​=∫qσ​(xt−2​∣x0​,xt−1​)⋅qσ​(xt−1​∣x0​,xt​)⋅dxt−1​​​​

因此
μ t − 2 = E ( q σ ( x t − 2 ∣ x 0 , x t ) ) = ∫ x t − 2 ⋅ q σ ( x t − 2 ∣ x 0 , x t ) ⋅ d x t − 2 = ∫ x t − 2 ⋅ ( ∫ q σ ( x t − 2 , ∣ x 0 , x t − 1 ) ⋅ q σ ( x t − 1 ∣ x 0 , x t ) ⋅ d x t − 1 ) ⋅ d x t − 2 = ∫ ∫ x t − 2 ⋅ q σ ( x t − 2 , ∣ x 0 , x t − 1 ) ⋅ q σ ( x t − 1 ∣ x 0 , x t ) ⋅ d x t − 1 ⋅ d x t − 2 = ∫ ( ∫ x t − 2 ⋅ q σ ( x t − 2 ∣ x 0 , x t − 1 ) ⋅ d x t − 2 ) ⋅ q σ ( x t − 1 ∣ x 0 , x t ) ⋅ d x t − 1 = ∫ ( E ( q σ ( x t − 2 , ∣ x 0 , x t − 1 ) ) ⋅ q σ ( x t − 1 ∣ x 0 , x t ) ⋅ d x t − 1 = ∫ ( 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ x t − 1 + [ α t − 2 − α t − 1 ⋅ ( 1 − α t − 2 − σ t − 1 2 ) 1 − α t − 1 ] ⋅ x 0 ) ⋅ q σ ( x t − 1 ∣ x 0 , x t ) ⋅ d x t − 1 = ∫ ( 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ x t − 1 ) ⋅ q σ ( x t − 1 ∣ x 0 , x t ) ⋅ d x t − 1 + ∫ ( α t − 2 − α t − 1 ⋅ ( 1 − α t − 2 − σ t − 1 2 ) 1 − α t − 1 ) ⋅ x 0 ⋅ q σ ( x t − 1 ∣ x 0 , x t ) ⋅ d x t − 1 = 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ ∫ x t − 1 ⋅ q σ ( x t − 1 ∣ x 0 , x t ) ⋅ d x t − 1 + ( α t − 2 − α t − 1 ⋅ ( 1 − α t − 2 − σ t − 1 2 ) 1 − α t − 1 ) ⋅ x 0 ∫ q σ ( x t − 1 ∣ x 0 , x t ) ⋅ d x t − 1 ⏟ = 1 = 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ E ( q σ ( x t − 1 ∣ x 0 , x t ) ) + ( α t − 2 − α t − 1 ⋅ ( 1 − α t − 2 − σ t − 1 2 ) 1 − α t − 1 ) ⋅ x 0 = 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ ( 1 − α t − 1 − σ t 2 1 − α t ⋅ x t + [ α t − 1 − α t ⋅ ( 1 − α t − 1 − σ t 2 ) 1 − α t ] ⋅ x 0 ) + ( α t − 2 − α t − 1 ⋅ ( 1 − α t − 2 − σ t − 1 2 ) 1 − α t − 1 ) ⋅ x 0 = 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ 1 − α t − 1 − σ t 2 1 − α t ⋅ x t + 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ α t − 1 ⋅ x 0 − 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ α t ⋅ ( 1 − α t − 1 − σ t 2 ) 1 − α t ⋅ x 0 + α t − 2 ⋅ x 0 − α t − 1 ⋅ ( 1 − α t − 2 − σ t − 1 2 ) 1 − α t − 1 ⋅ x 0 = 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ 1 − α t − 1 − σ t 2 1 − α t ⋅ x t − 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ α t ⋅ ( 1 − α t − 1 − σ t 2 ) 1 − α t ⋅ x 0 + α t − 2 ⋅ x 0 ⏟ x 0 = x t − 1 − α t ⋅ z t α t = 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ 1 − α t − 1 − σ t 2 1 − α t ⋅ x t − 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ α t ⋅ ( 1 − α t − 1 − σ t 2 ) 1 − α t ⋅ x t − 1 − α t ⋅ z t α t + α t − 2 ⋅ x t − 1 − α t ⋅ z t α t = 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ 1 − α t − 1 − σ t 2 1 − α t ⋅ x t − 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ α t ⋅ ( 1 − α t − 1 − σ t 2 ) 1 − α t ⋅ x t α t + 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ α t ⋅ ( 1 − α t − 1 − σ t 2 ) 1 − α t ⋅ 1 − α t ⋅ z t α t + α t − 2 ⋅ x t − 1 − α t ⋅ z t α t = 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ α t ⋅ ⋅ ( 1 − α t − 1 − σ t 2 ) 1 − α t ⋅ 1 − α t ⋅ z t α t + α t − 2 ⋅ x t − 1 − α t ⋅ z t α t = α t − 2 ⋅ x t − 1 − α t ⋅ z t α t ⏟ = x 0 + 1 − α t − 2 − σ t − 1 2 1 − α t − 1 ⋅ 1 − α t − 1 − σ t 2 ⋅ z t \begin{equation} \begin{split} \mu_{t-2}&=E\big(q_\sigma(x_{t-2}|x_0,x_t)\big) \\ &=\int x_{t-2} \cdot q_\sigma(x_{t-2}|x_0,x_t)\cdot dx_{t-2} \\ &=\int x_{t-2} \cdot \bigg(\int q_\sigma(x_{t-2},|x_0,x_{t-1}) \cdot q_\sigma(x_{t-1}|x_0,x_{t}) \cdot dx_{t-1} \bigg) \cdot dx_{t-2} \\ &=\int \int x_{t-2} \cdot q_\sigma(x_{t-2},|x_0,x_{t-1}) \cdot q_\sigma(x_{t-1}|x_0,x_{t}) \cdot dx_{t-1} \cdot dx_{t-2} \\ &=\int \bigg( \int x_{t-2} \cdot q_\sigma(x_{t-2}|x_0,x_{t-1}) \cdot dx_{t-2} \bigg)\cdot q_\sigma(x_{t-1}|x_0,x_{t}) \cdot dx_{t-1} \\ &=\int \bigg(E(q_\sigma(x_{t-2},|x_0,x_{t-1}) \bigg)\cdot q_\sigma(x_{t-1}|x_0,x_{t}) \cdot dx_{t-1} \\ &=\int \bigg(\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot x_{t-1}+ \bigg[\sqrt{\alpha_{t-2}}- \frac{\sqrt{ \alpha_{t-1}\cdot (1-\alpha_{t-2}-\sigma_{t-1}^2} )}{\sqrt{1-\alpha_{t-1}}} \bigg] \cdot x_0 \bigg)\cdot q_\sigma(x_{t-1}|x_0,x_{t}) \cdot dx_{t-1} \\ &=\int \bigg(\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot x_{t-1} \bigg)\cdot q_\sigma(x_{t-1}|x_0,x_{t}) \cdot dx_{t-1} + \int \bigg(\sqrt{\alpha_{t-2}}- \frac{\sqrt{ \alpha_{t-1}\cdot (1-\alpha_{t-2}-\sigma_{t-1}^2} )}{\sqrt{1-\alpha_{t-1}}} \bigg) \cdot x_0 \cdot q_\sigma(x_{t-1}|x_0,x_{t}) \cdot dx_{t-1}\\ &=\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot \int x_{t-1}\cdot q_\sigma(x_{t-1}|x_0,x_{t}) \cdot dx_{t-1} +\bigg(\sqrt{\alpha_{t-2}}- \frac{\sqrt{ \alpha_{t-1}\cdot (1-\alpha_{t-2}-\sigma_{t-1}^2} )}{\sqrt{1-\alpha_{t-1}}} \bigg) \cdot x_0 \underbrace{ \int q_\sigma(x_{t-1}|x_0,x_{t}) \cdot dx_{t-1}}_{=1}\\ &=\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot E\bigg(q_\sigma(x_{t-1}|x_0,x_{t})\bigg) +\bigg(\sqrt{\alpha_{t-2}}- \frac{\sqrt{ \alpha_{t-1}\cdot (1-\alpha_{t-2}-\sigma_{t-1}^2} )}{\sqrt{1-\alpha_{t-1}}} \bigg) \cdot x_0 \\ &=\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot \bigg(\sqrt{\frac{1-\alpha_{t-1}-\sigma_t^2}{1-\alpha_{t}}}\cdot x_t+ \bigg[\sqrt{\alpha_{t-1}}- \frac{\sqrt{ \alpha_t\cdot (1-\alpha_{t-1}-\sigma_t^2} )}{\sqrt{1-\alpha_t}} \bigg] \cdot x_0 \bigg) +\bigg(\sqrt{\alpha_{t-2}}- \frac{\sqrt{ \alpha_{t-1}\cdot (1-\alpha_{t-2}-\sigma_{t-1}^2} )}{\sqrt{1-\alpha_{t-1}}} \bigg) \cdot x_0 \\ &=\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot \sqrt{\frac{1-\alpha_{t-1}-\sigma_t^2}{1-\alpha_{t}}}\cdot x_t + \bcancel{\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}} \cdot \sqrt{\alpha_{t-1}}\cdot x_0} -\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot \frac{\sqrt{ \alpha_t\cdot (1-\alpha_{t-1}-\sigma_t^2} )}{\sqrt{1-\alpha_t}} \cdot x_0 + \sqrt{\alpha_{t-2}} \cdot x_0 - \bcancel{\frac{\sqrt{ \alpha_{t-1}\cdot (1-\alpha_{t-2}-\sigma_{t-1}^2} )}{\sqrt{1-\alpha_{t-1}}} \cdot x_0}\\ &=\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot \sqrt{\frac{1-\alpha_{t-1}-\sigma_t^2}{1-\alpha_{t}}}\cdot x_t -\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot \frac{\sqrt{ \alpha_t\cdot (1-\alpha_{t-1}-\sigma_t^2} )}{\sqrt{1-\alpha_t}} \cdot x_0 + \sqrt{\alpha_{t-2}} \cdot \underbrace{x_0}_{x_0=\frac{x_t-{\sqrt{1-\alpha_t}\cdot z_t}}{\sqrt{\alpha_t}}} \\ &=\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot \sqrt{\frac{1-\alpha_{t-1}-\sigma_t^2}{1-\alpha_{t}}}\cdot x_t -\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot \frac{\sqrt{ \alpha_t\cdot (1-\alpha_{t-1}-\sigma_t^2} )}{\sqrt{1-\alpha_t}} \cdot \frac{x_t-{\sqrt{1-\alpha_t}\cdot z_t}}{\sqrt{\alpha_t}} + \sqrt{\alpha_{t-2}} \cdot \frac{x_t-{\sqrt{1-\alpha_t}\cdot z_t}}{\sqrt{\alpha_t}} \\ &=\bcancel{\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot \sqrt{\frac{1-\alpha_{t-1}-\sigma_t^2}{1-\alpha_{t}}}\cdot x_t} -\bcancel{\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot \frac{\sqrt{ \alpha_t\cdot (1-\alpha_{t-1}-\sigma_t^2} )}{\sqrt{1-\alpha_t}} \cdot \frac{x_t}{\sqrt{\alpha_t}}} +\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot \frac{\sqrt{ \alpha_t\cdot (1-\alpha_{t-1}-\sigma_t^2} )}{\sqrt{1-\alpha_t}} \cdot \frac{{\sqrt{1-\alpha_t}\cdot z_t}}{\sqrt{\alpha_t}} + \sqrt{\alpha_{t-2}} \cdot \frac{x_t-{\sqrt{1-\alpha_t}\cdot z_t}}{\sqrt{\alpha_t}} \\ &=\sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot \frac{\bcancel{\sqrt{\alpha_t}}\cdot \sqrt{ \cdot (1-\alpha_{t-1}-\sigma_t^2} )}{\bcancel{\sqrt{1-\alpha_t}}} \cdot \frac{{\bcancel{\sqrt{1-\alpha_t}}\cdot z_t}}{\bcancel{\sqrt{\alpha_t}}} + \sqrt{\alpha_{t-2}} \cdot \frac{x_t-{\sqrt{1-\alpha_t}\cdot z_t}}{\sqrt{\alpha_t}} \\ &=\sqrt{\alpha_{t-2}} \cdot \underbrace{ \frac{x_t-{\sqrt{1-\alpha_t}\cdot z_t}}{\sqrt{\alpha_t}}}_{=x_0}+ \sqrt{\frac{1-\alpha_{t-2}-\sigma_{t-1}^2}{1-\alpha_{t-1}}}\cdot \sqrt{ 1-\alpha_{t-1}-\sigma_t^2} \cdot z_t \\ \end{split} \end{equation} μt−2​​=E(qσ​(xt−2​∣x0​,xt​))=∫xt−2​⋅qσ​(xt−2​∣x0​,xt​)⋅dxt−2​=∫xt−2​⋅(∫qσ​(xt−2​,∣x0​,xt−1​)⋅qσ​(xt−1​∣x0​,xt​)⋅dxt−1​)⋅dxt−2​=∫∫xt−2​⋅qσ​(xt−2​,∣x0​,xt−1​)⋅qσ​(xt−1​∣x0​,xt​)⋅dxt−1​⋅dxt−2​=∫(∫xt−2​⋅qσ​(xt−2​∣x0​,xt−1​)⋅dxt−2​)⋅qσ​(xt−1​∣x0​,xt​)⋅dxt−1​=∫(E(qσ​(xt−2​,∣x0​,xt−1​))⋅qσ​(xt−1​∣x0​,xt​)⋅dxt−1​=∫(1−αt−1​1−αt−2​−σt−12​​ ​⋅xt−1​+[αt−2​ ​−1−αt−1​ ​αt−1​⋅(1−αt−2​−σt−12​ ​)​]⋅x0​)⋅qσ​(xt−1​∣x0​,xt​)⋅dxt−1​=∫(1−αt−1​1−αt−2​−σt−12​​ ​⋅xt−1​)⋅qσ​(xt−1​∣x0​,xt​)⋅dxt−1​+∫(αt−2​ ​−1−αt−1​ ​αt−1​⋅(1−αt−2​−σt−12​ ​)​)⋅x0​⋅qσ​(xt−1​∣x0​,xt​)⋅dxt−1​=1−αt−1​1−αt−2​−σt−12​​ ​⋅∫xt−1​⋅qσ​(xt−1​∣x0​,xt​)⋅dxt−1​+(αt−2​ ​−1−αt−1​ ​αt−1​⋅(1−αt−2​−σt−12​ ​)​)⋅x0​=1 ∫qσ​(xt−1​∣x0​,xt​)⋅dxt−1​​​=1−αt−1​1−αt−2​−σt−12​​ ​⋅E(qσ​(xt−1​∣x0​,xt​))+(αt−2​ ​−1−αt−1​ ​αt−1​⋅(1−αt−2​−σt−12​ ​)​)⋅x0​=1−αt−1​1−αt−2​−σt−12​​ ​⋅(1−αt​1−αt−1​−σt2​​ ​⋅xt​+[αt−1​ ​−1−αt​ ​αt​⋅(1−αt−1​−σt2​ ​)​]⋅x0​)+(αt−2​ ​−1−αt−1​ ​αt−1​⋅(1−αt−2​−σt−12​ ​)​)⋅x0​=1−αt−1​1−αt−2​−σt−12​​ ​⋅1−αt​1−αt−1​−σt2​​ ​⋅xt​+1−αt−1​1−αt−2​−σt−12​​ ​⋅αt−1​ ​⋅x0​ ​−1−αt−1​1−αt−2​−σt−12​​ ​⋅1−αt​ ​αt​⋅(1−αt−1​−σt2​ ​)​⋅x0​+αt−2​ ​⋅x0​−1−αt−1​ ​αt−1​⋅(1−αt−2​−σt−12​ ​)​⋅x0​ ​=1−αt−1​1−αt−2​−σt−12​​ ​⋅1−αt​1−αt−1​−σt2​​ ​⋅xt​−1−αt−1​1−αt−2​−σt−12​​ ​⋅1−αt​ ​αt​⋅(1−αt−1​−σt2​ ​)​⋅x0​+αt−2​ ​⋅x0​=αt​ ​xt​−1−αt​ ​⋅zt​​ x0​​​=1−αt−1​1−αt−2​−σt−12​​ ​⋅1−αt​1−αt−1​−σt2​​ ​⋅xt​−1−αt−1​1−αt−2​−σt−12​​ ​⋅1−αt​ ​αt​⋅(1−αt−1​−σt2​ ​)​⋅αt​ ​xt​−1−αt​ ​⋅zt​​+αt−2​ ​⋅αt​ ​xt​−1−αt​ ​⋅zt​​=1−αt−1​1−αt−2​−σt−12​​ ​⋅1−αt​1−αt−1​−σt2​​ ​⋅xt​ ​−1−αt−1​1−αt−2​−σt−12​​ ​⋅1−αt​ ​αt​⋅(1−αt−1​−σt2​ ​)​⋅αt​ ​xt​​ ​+1−αt−1​1−αt−2​−σt−12​​ ​⋅1−αt​ ​αt​⋅(1−αt−1​−σt2​ ​)​⋅αt​ ​1−αt​ ​⋅zt​​+αt−2​ ​⋅αt​ ​xt​−1−αt​ ​⋅zt​​=1−αt−1​1−αt−2​−σt−12​​ ​⋅1−αt​ ​ ​αt​ ​ ​⋅⋅(1−αt−1​−σt2​ ​)​⋅αt​ ​ ​1−αt​ ​ ​⋅zt​​+αt−2​ ​⋅αt​ ​xt​−1−αt​ ​⋅zt​​=αt−2​ ​⋅=x0​ αt​ ​xt​−1−αt​ ​⋅zt​​​​+1−αt−1​1−αt−2​−σt−12​​ ​⋅1−αt−1​−σt2​ ​⋅zt​​​​
结果貌似与论文中的(本文中公式4)略有不同…论文和代码中使用的跳 n n n步的采样过程如公式(4)所示。
x t − n = α t − n ⋅ x t − 1 − α t ⋅ z t α t ⏟ 预测出 z t , 进而计算出 x 0 + 1 − α t − n − σ t 2 ⋅ z t + σ t 2 ϵ t ⏟ 标准高斯分布 \begin{equation} \begin{split} x_{t-n}&=\sqrt{\alpha_{t-n}}\cdot \underbrace{\frac{x_t-{\sqrt{1-\alpha_t}\cdot z_t}}{\sqrt{\alpha_t}}}_{预测出z_t,进而计算出x_0}+\sqrt{1-\alpha_{t-n}-\sigma_t^2}\cdot z_t + \sigma_t^2 \underbrace{ \epsilon_t}_{标准高斯分布} \\ \end{split} \end{equation} xt−n​​=αt−n​ ​⋅预测出zt​,进而计算出x0​ αt​ ​xt​−1−αt​ ​⋅zt​​​​+1−αt−n​−σt2​ ​⋅zt​+σt2​标准高斯分布 ϵt​​​​​​


微信公众号

今日签到

点亮在社区的每一天
去签到