search

nv-tlabs / XCube

[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies
https://research.nvidia.com/labs/toronto-ai/xcube/
Other
344 stars 20 forks source link

Waymo Inference has issues 'fvdb._Cpp.JaggedTensor' object has no attribute 'numpy #5

Closed yshen47 closed 5 months ago

yshen47 commented 5 months ago

I am able to run inference for shapenet without problem. But for waymo, the command below, it complains AttributeError: 'fvdb._Cpp.JaggedTensor' object has no attribute 'numpy'. I am wondering how to fix this issue.

python inference/sample_waymo.py none --total_len 20 --batch_len 4 --ema --use_ddim --ddim_step 100 --extract_mesh

Traceback (most recent call last): File "/scratch/bczy/yshen47/MMCityGen/mmcitygen/third_parties/XCube/inference/sample_waymo.py", line 132, in <module> udf_mesh = field.extract_dual_mesh() File "/scratch/bczy/yshen47/MMCityGen/mmcitygen/third_parties/XCube/ext/nksr-cuda/nksr/fields/base_field.py", line 206, in extract_dual_mesh dual_c = self.texture_field.evaluate_f_bar( File "/scratch/bczy/yshen47/MMCityGen/mmcitygen/third_parties/XCube/ext/nksr-cuda/nksr/fields/base_field.py", line 114, in evaluate_f_bar f_chunk = self.evaluate_f( File "/scratch/bczy/yshen47/MMCityGen/mmcitygen/third_parties/XCube/ext/nksr-cuda/nksr/fields/pcnn_field.py", line 39, in evaluate_f _, idx = self.kdtree.query(xyz.detach().cpu().numpy()) AttributeError: 'fvdb._Cpp.JaggedTensor' object has no attribute 'numpy'

xrenaa commented 5 months ago

Hi, I just fix this issue. Could you try again?

yshen47 commented 5 months ago

Thanks for the fast response! Do I need to recompile fvdb after pulling?