Lukas

Hello together, i seem to be unable to get UCF101 to converge even with setting like the ones used on the densenet-general branch. KTH seems to be converging instantly though....

Sure, if I find the time to do that next week.

Sorry I did not have time to update the example

Hello, We ran into a similar problem. is there anything known about the Problems of HA configuration with metallb?

How did you set this up on microk8s?

Hey is there any Update on this? I am facing the same issue on microk8s 1.24.

The overlapp is used for classification on video level, while the provided predict function is clip level