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
253 stars 11 forks source link

Training error caused by inplace operations #33

Open LeoDarcy opened 6 days ago

LeoDarcy commented 6 days ago

https://github.com/nv-tlabs/XCube/blob/d0ee1c26ebd67a9a8ff803835333b088155fb051/xcube/modules/autoencoding/base_encoder.py#L63

It leads to "RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation" during training.

LeoDarcy commented 6 days ago

After making modifications, I still encounter similar errors. May I ask if there are any other code that need to be modified? Thank you very much.