UniqAI/gaussian-splatting
1
0
Fork 0
mirror of https://github.com/graphdeco-inria/gaussian-splatting synced 2024-11-25 21:28:17 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Snosixtyboo 2023-08-29 14:17:54 +02:00 committed by GitHub
parent 9d977c702b
commit 436ca31125
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -483,6 +483,9 @@ python convert.py -s <location> --skip_matching [--resize] #If not resizing, Ima
| ![Default learning rate result](assets/worse.png "title-1") <!-- --> | <!-- --> ![Reduced learning rate result](assets/better.png "title-2") | | ![Default learning rate result](assets/worse.png "title-1") <!-- --> | <!-- --> ![Reduced learning rate result](assets/better.png "title-2") |
| --- | --- | | --- | --- |
- *I'm on Windows and I can't manage to build the submodules* Consider following the steps in the excellent video tutorial [here](https://www.youtube.com/watch?v=UXtuigy_wYc), hopefully they should help. The order in which the steps are done is important!
- *I'm on macOS/Puppy Linux/Greenhat and I can't manage to build* Sorry, we can't provide support for platforms outside of the ones we list in this README.
- *I don't have 24 GB of VRAM for training, what do I do?* The VRAM consumption is determined by the number of points that are being optimized, which increases over time. If you only want to train to 7k iterations, you will need significantly less. To do the full training routine and avoid running out of memory, you can increase the ```--densify_grad_threshold```, ```--densification_interval``` or reduce the value of ```--densify_until_iter```. Note however that this will affect the quality of the result. Also try setting ```--test_iterations``` to ```-1``` to avoid memory spikes during testing. If ```--densify_grad_threshold``` is very high, no densification should occur and training should complete if the scene itself loads successfully. - *I don't have 24 GB of VRAM for training, what do I do?* The VRAM consumption is determined by the number of points that are being optimized, which increases over time. If you only want to train to 7k iterations, you will need significantly less. To do the full training routine and avoid running out of memory, you can increase the ```--densify_grad_threshold```, ```--densification_interval``` or reduce the value of ```--densify_until_iter```. Note however that this will affect the quality of the result. Also try setting ```--test_iterations``` to ```-1``` to avoid memory spikes during testing. If ```--densify_grad_threshold``` is very high, no densification should occur and training should complete if the scene itself loads successfully.