low performance about intrada

[feipanir]

Hi are you doing the experiment from GTA5->Cityscapes? I guess the problem is from the first stage that you got 41.98, which is a bit low than what is expected. I suggest you to train more iterations in the first stage. In our experiments, we got BEST IOU at around 80k iteration or so. And also double check your learning rate, image size, pytorch version, etc.

[jianlong-yuan]

I am doing the experiment from GTA5->Cityscapes.
I just use your default settings.
How much miou do you achieve for the first stage?

By the way, pytorch version is 1.5, CUDA10.1

[feipanir]

We conduct the experiment on pytorch=0.4.1 and our best miou would be around 43.8 for the inter-da stage. Right now you are using pytoch=1.5. I guess it is probably due to pytorch version but I am not really sure. I will double check it on my local server.

[jianlong-yuan]

With pytorch0.4.1, i got 42.4miou at 5w iters. I have finished 10w iters.

[feipanir]

It's still a bit low than expected. We usually got 43.8± 0.2. Actually our experiments setup of inter-da keep the same as ADVENT.

[feipanir]

A little concern is also from the CUDA version. As I tried on my machine, by using CUDA=9.2 I got the same performance, rather it becomes lower when I switch to CUDA=10.2. So be careful about which cuda version is used currently.

[xdeng7]

With pytorch0.4.1, i got 42.4miou at 5w iters. I have finished 10w iters.

Hi, I was using pytorch1.5.1 and CUDA10.2. I was able to achieve 43.75 for ADVENT, the first stage. And 46.28 for the second stage adaptation.

[feipanir]

Hi @xdeng7 thank you for your effort and sharing this information!
Regards