G ∗ = arg min G max D L c G A N ( G , D ) + λ L L 1 ( G ) G^{*}=\arg \min _{G} \max _{D} \mathcal{L}_{c G A N}(G, D)+\lambda \mathcal{L}_{L 1}(G) G∗=argGminDmaxLcGAN(G,D)+λLL1(G)
G^{*}=\arg \min_{G} \max_{D} \mathcal{L}_{cGAN}(G,D)+\lambda \mathcal{L}_{L1}(G)
L t a s k = λ 1 L p e r ( G s ( x ) , G t ( x ) ) + λ 1 L C E ( y , δ ( z s ) ) + λ 1 L F o c a l ( y , y o u t ) \begin{aligned} 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}) \end{aligned} Ltask=λ1Lper(Gs(x),Gt(x))+λ1LCE(y,δ(zs))+λ1LFocal(y,yout)
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