Sk_Kim

Could not find json file to retraining train.agent file

2

could you upload json param file?

Hi, author. To visualize your results attention map, how can you visualize this? 1) Use Encoder (ViT)? 2) Use Decoder (VIT)? given input x -> y = encoder(x) -> decoder(y)....

CUDA version

1

what is coda version for MSDA

About Framework of ViCLIP

3

Thank you for nice work. In training ViCLIP, I would like to clarify my understanding of this paper. If vision transforms is not pre-trained such as MAE method, then, it...

Question for input

1

1. for pre-training FM, how many frames are used ? (150fr? for each batch)? 2. for downstream task, I see that you used 224 224 with 1 frame for segmentation....

How to create US probe with 3D visualization.

1

Hi, how can I create real time us probe navigator as navig.gif? Thanks

loading Kubrick point tracking dataset

1

I followed code and it looks like data processing is very time consuming. is there a better approach for that?

Hi, I wonder if during the training, it should be the same length of the video. In inference steps, how can you infer if the video is longer or shorter...

Hi, I wonder if during the training, it should be the same length of the video. In inference steps, how can you infer if the video is longer or shorter...