Kristina Tan

icon company Communication University of China icon location Beijing, China icon location šŸ‘‹ Hi there! Iā€™m Kristina šŸš€ šŸŒ± Iā€™m always looking to challenge myself and expand my horizons.

Results 4 comments of Kristina Tan

Running on a multi-video dataset

Hi, Would you mind sharing the configuration you used for training on Venice? Iā€™m really curious about the time it takes you to train one epoch, as my training duration...

How to move depths to the same gpu as decoded_imgs?

> Hi @kristinat8, > > Thank you for reaching out. Can you try: > > ``` > combined = fn.cat(decoded_imgs, depths.gpu(), axis=2) > ``` If I want to process the...

How to move depths to the same gpu as decoded_imgs?

> Hi [@kristinat8](https://github.com/kristinat8), > > I'm not sure if I understand your ask. > > * if you want to specify the `depths` layout - please use `layout` argument of...

How to move depths to the same gpu as decoded_imgs?

``````> > Hi [@kristinat8](https://github.com/kristinat8), > > I'm not sure if I understand your ask. > > > > * if you want to specify the `depths` layout - please use...