markdown 上下结构编排（GAN的损失编排）

$$G^{\ast }=\arg \underset{G}{\min }\underset{D}{\max }{\mathcal{L}}_{cGAN}(G,D)+\lambda {\mathcal{L}}_{L1}(G)$$

 G^{*}=\arg \min_{G} \max_{D} \mathcal{L}_{cGAN}(G,D)+\lambda \mathcal{L}_{L1}(G) 

$$\begin{array}{rl}{L}_{task}=& {\lambda }_1{L}_{per}(G_s(x),G_t(x))+{\lambda }_1{L}_{CE}(y,\delta (z_s))\\ & +{\lambda }_1{L}_{Focal}(y,y_{out})\end{array}$$

L_{task} = &\lambda_1 L_{per}(G_s(x),G_t(x))  +\lambda_1  L_{CE}(y,\delta(z_s))\\ & + \lambda_1L_{Focal}(y,y_{out})

引用：https://blog.csdn.net/weixin_43402775/article/details/112002261