Sam Hodge

Sorry I found the correct documentation https://github.com/vsoch/watchme/blob/f209d3d4bf99a25cd2dcaeaa2431cf3ecfe68585/docs/_docs/watcher-tasks/gpu.md#use-as-a-decorator

Restarting seems fine.

I found that typing a directory and file name into the "invisible window" and hitting enter unblocks me from using this version, but less savvy users might abandon the software...

Made a change to 14 rather than 13 and ` if customized_focal:` become ` if customized_focal or True:`

Looks like this is a red hot tip: https://github.com/t-bence/exif-stats/blob/master/focal_stats.py#L44

Maybe all I needed was patience. 

Does this seem correct? @bianwenjing I am worried that my modification with the width and height ``` diff --git a/dataloading/dataset.py b/dataloading/dataset.py index d40af73..846273d 100644 --- a/dataloading/dataset.py +++ b/dataloading/dataset.py @@ -82,11...

Yeah nah, didn't work trying again with different intrinsics values ``` diff --git a/configs/Test/images.yaml b/configs/Test/images.yaml index 81a5824..264c4cf 100644 --- a/configs/Test/images.yaml +++ b/configs/Test/images.yaml @@ -12,4 +12,5 @@ training: auto_scheduler: True eval_pose_every:...

This is with training from COLMAP and hallucinated depth maps  https://github.com/ActiveVisionLab/nope-nerf/assets/102564797/2b64c14b-40b8-4109-af7e-f1d6c770d4c3 What are the limitations on the input dataset?

These are the videos from training https://github.com/google-research/google-research/assets/102564797/a807ac1f-23a8-496e-8ad8-f53c7086203d https://github.com/google-research/google-research/assets/102564797/4fef1236-1e1c-4ca0-946d-0dbb61a46f8d