You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
[14:46:48] Auto image downscale factor of 4 nerfstudio_dataparser.py:484
Loading latest checkpoint from load_dir
✅ Done loading checkpoint from outputs/object/splatfacto/2024-05-22_170348/nerfstudio_models/step-000019999.ckpt
model/nerfstudio/nerfstudio/data/scene_box.py:105: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
comp_l = torch.tensor(-S / 2)
model/nerfstudio/nerfstudio/data/scene_box.py:106: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
comp_m = torch.tensor(S / 2)
Any help ?
The text was updated successfully, but these errors were encountered:
is there a way to remove background from the exported splat (from splatfacto) ?
I used ns-export with the following options but it crashed
ns-export gaussian-splat --load-config outputs/object/splatfacto/2024-05-22_170348/config.yml --output-dir ../app/ --obb-center -0.0700000003 -0.0299999993 -0.0799999982 --obb_scale 1.0000000000 1.0000000000 1.0000000000 --obb_rotation 0.0000000000 0.0000000000 -0.7805307416_
[14:46:48] Auto image downscale factor of 4 nerfstudio_dataparser.py:484
Loading latest checkpoint from load_dir
✅ Done loading checkpoint from outputs/object/splatfacto/2024-05-22_170348/nerfstudio_models/step-000019999.ckpt
model/nerfstudio/nerfstudio/data/scene_box.py:105: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
comp_l = torch.tensor(-S / 2)
model/nerfstudio/nerfstudio/data/scene_box.py:106: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
comp_m = torch.tensor(S / 2)
Any help ?
The text was updated successfully, but these errors were encountered: