Anqi Wu

icon indicating a website link https://sites.google.com/site/anqiwuresearch/

icon company Georgia Institute of Technology / Columbia University / Princeton University icon location Assist Prof at GT / Postdoc at Columbia / Ph.D in machine learning and computational neuroscience at Princeton University

Results 17 comments of Anqi Wu

Do videos placed in videos_dgp need to be labeled?

Hi videos_dgp should include all videos (labeled or not labeled). But you have to have some labeled frames input to DGP-labeled, as the ones you use for DLC. It seems...

Do videos placed in videos_dgp need to be labeled?

Hi Is this missing video a labeled one or an unlabeled one?

Insufficient memory problem

Also, have you tried run DLC? you have this memory issue with DLC?

Insufficient memory problem

You mean running DLC with the same data size and the bigger batch size like 10?

Code in command prompt runs, now what?

Hi If you finish training and just want to test the DGP model, you could start from https://github.com/paninski-lab/deepgraphpose/blob/main/demo/run_dgp_demo.py#L249 set snapshot to be the name of the snapshot you want to...

"Tensor had NaN values" when encountering improbable label values

Thanks for sharing this finding! This is very helpful to improve the package.

Do we need to train DLC prior to run the dgp pipeline

Hi Thanks for the update and clarification. For the error you posted, do you have that pose_cfg.yaml there? For the long time stucking, it might due to the selection of...