jacobw

Hi, have you already found the anwser? I have also met thie problem and i cant tell the difference when i use errD for the backpropogation since its only a...

also there is a step to ensure that the sample with higher prior weight is assigned id1. I think here you need prior_weights_[closest_exist_sample_pair.y] >prior_weights_[closest_exist_sample_pair.x] instead of prior_weights_[closest_exist_sample_pair.x] >prior_weights_[closest_exist_sample_pair.y]

@Luodian Hey, have you solved this problem or got any ideas? I am just starting to try to implement on my own:) And using this fs you have mentioned, in...

iter = 1/ 250000, loss_seg1 = 0.000 loss_seg2 = 4.504 loss_adv1 = 0.688, loss_adv2 = 0.701 loss_D1 = 0.691 loss_D2 = 0.693 exp = ./snapshots/GTA2Cityscapes_single iter = 2/ 250000, loss_seg1...

To my understanding and if i understand your question correctly, to fool the source discriminator as in conventional GAN, the attention work is required to attend to the most domain...

Thanks a lot. I will definitely try these.

Hi @yingfei1016 when i try to simply set with_multiview=False, an error would occur  Do you have any ideas? Or should i just replace it all with the one in...

Thanks a lot.

@yingfei1016 Hi sorry for the late reply. I have tried 1) and 3) and based on my experiments with own data, mAP improves slightly, but the error items increases. At...

Thanks for you kind reply.