The tensorflow and pytorch implementations of the MDvsFA_cGAN model which is proposed in ICCV2019 paper "Huan Wang, Luping Zhou and Lei Wang. Miss Detection vs. False Alarm: Adversarial Learing for Small Object Segmentation in Infrared Images. International Conference on Computer Vision, Oct.27-Nov.2,2019. Seoul, Republic of Korea".
在代码的443-444行： for r in optimizer_g2.param_groups: r['lr'] = 0.2
想请问一下这句中您原本的意思是否是 for r in optimizer_d.param_groups: r['lr'] = 0.2？
因为如果按现在您代码的书写方式，则在此处您对g2的学习率进行了两遍*=0.2，却没有对D的学习率进行修改
CPaul33
commented
3 months ago
在代码的443-444行： for r in optimizer_g2.param_groups: r['lr'] = 0.2 想请问一下这句中您原本的意思是否是 for r in optimizer_d.param_groups: r['lr'] = 0.2？ 因为如果按现在您代码的书写方式，则在此处您对g2的学习率进行了两遍*=0.2，却没有对D的学习率进行修改