facebookresearch / facebookresearch/dva
Bin size was too small output maybe be incomplete
Open
- Dominant language
- Jupyter Notebook
- Stars
- 104
- Forks
- 7
- PR merge metrics
- No merged PRs in 30d
Description
Hi, I have managed to start training on ZJU dataset, and I am facing this warning
**Bin size was too small in the coarse rasterization phase. This caused an overflow, meaning output may be incomplete. To solve, try increasing max_faces_per_bin / max_points_per_bin, decreasing bin_size, or setting bin_size to 0 to use the naive rasterization**
Any changes I should make to the code?
Contributor guide
Assessment
This issue has not been assessed yet.