kenmbkr

I tried to download the universal model and got the following message. Could you please double-check the link? 

GPU memory increases during training

1

I am using the [refactored U-2-Net](https://github.com/xuebinqin/U-2-Net/blob/master/model/u2net_refactor.py) and the GPU memory increases every few iterations during training. I noticed in the code that there are function definitions in the forward functions...

Code correspondence for relative transfer in the appendix

11

I was looking at relative transfer in the appendix but I have difficulty following the corresponding [code](https://github.com/AliaksandrSiarohin/first-order-model/blob/ca49071ce60051200f58f03a0e4e65e675a54e27/animate.py#L27). ```python if use_relative_movement: kp_value_diff = (kp_driving['value'] - kp_driving_initial['value']) kp_value_diff *= adapt_movement_scale kp_new['value'] =...

I found the evaluation dataset and the evaluation script [here](https://github.com/AliaksandrSiarohin/motion-cosegmentation). The evaluation data contains only static images, not source-driving pairs. As far as I know, the source and the driving...

How to do style mixing quickly?

3

I am trying to do style mixing between two images using `file_based_simple_style_transfer.py` with the following command, but it takes a couple of minutes to optimize and the artifacts are noticeable...

Any suggestions to quickly test the cropping strategy?

1

Depending on the availability of videos and their contents, sometimes it takes a few minutes to get an initial result in the `out_folder` if I am lucky or half to...