Open John1231983 opened 7 years ago
I have done an implementation of GAN4Seg with tensorflow. But the results is not so good. The D can give different score on the real and fake samples. But the iou can not improved under the help of the D. Do you have the same difficulties?
Me too. I did not saw any improvement using GAN. As you saw in the paper, the author also mentioned that her method only has some gain in some dataset, while Pascal VOC is not. I think she based on the torch to implement. Could you try with another dataset?
Thanks for sharing the implementation. My question is similar question #2 . Could you update/show the performance of the implementation with/without GAN? I would like to know if my running is correct or not. Thanks