areiner222
areiner222
Checking back in on this - any recommendations ?
Thanks for your reply. So to confirm, 1. In BEV, the feature vector is extracted at the x,y pixel location of the final x,y,z offsets and then a transformation occurs...
Thanks for the update @btaba. Yes will pin a prior version for now - 3.1.3 works just fine and will try 3.1.4. I was looking to upgrade in order to...
I see that you map to the convex mesh inside the collider function and compute face normals, edge directions, unique edges there. If the mesh vertices are jax arrays, is...
I'm relying on map_fn to extract ragged image patches using bounding boxes so I can then produce ragged bounding-box centered feature maps via convolutions. I am encountering the same bug...
Did you ever manage to curate a list of viable sequences for AMASS SMPL-X? I'm hopefully you might have given PHC-X in the works! 🤞 Thanks again!
Thank you for this impressive work! +1 on some demo code. A documented colab would be SO useful even if it starts from something like pre-computed (from LEMO or GT...
@MRL-00 I never determined a very reliable way to reconnect... I have successfully connected via BLE + COHN up to 6 cameras but I can't get it to work consistently...
Had similar issues - might have to do with [this](https://github.com/NVIDIA-Merlin/Transformers4Rec/pull/800)