ddghost

foggy cityscape dataset result

7

Hi, I follow the README steps to train the network, but the best MAP is only 35. I wonder if my train_s.txt, train_t.txt and test_t.txt differ from yours. Could you...

作者你好，在阅读您的论文中我注意到了如下两个公式，一个是用均方差计算 pixel-wise的对抗损失，在这个公式里源域图像的域标签应该是0  而下面还有一个应该是用交叉熵计算的上下文感知的实例级对抗损失，在这个公式中源域图像的域标签似乎应该是1？ 

About the trained model.

1

**Hi, when I use your trained model for clipart. The model can not find these parameters:** 'RCNN_base2.0.2.bn2.num_batches_tracked', 'RCNN_base3.0.5.bn2.num_batches_tracked', 'RCNN_base1.4.0.bn3.num_batches_tracked', 'RCNN_base3.0.6.bn1.num_batches_tracked', 'RCNN_base3.0.18.bn2.num_batches_tracked', 'RCNN_base3.0.4.bn1.num_batches_tracked', 'RCNN_base3.0.12.bn3.num_batches_tracked', 'RCNN_base3.0.16.bn3.num_batches_tracked', 'RCNN_base3.0.9.bn2.num_batches_tracked', 'RCNN_base1.4.0.downsample.1.num_batches_tracked', 'RCNN_base2.0.0.bn3.num_batches_tracked', 'RCNN_base1.4.2.bn3.num_batches_tracked', 'RCNN_base3.0.13.bn1.num_batches_tracked', 'RCNN_base3.0.20.bn2.num_batches_tracked',...

Hi，Thanks for your great work. It seems that the implementation of vgg16 is not complete?

我看start.go文件中的systray包好像是改过的，请问下能提供一下你的systray包吗？