how can I use the coarse 15000.pt to continue train.py?

Anttwo / SuGaR

[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

https://anttwo.github.io/sugar/

Other

2.36k stars 182 forks source link

how can I use the coarse 15000.pt to continue train.py? #41

Open 728388808 opened 11 months ago

728388808 commented 11 months ago

My gpu was out of memory when the train.py is running(temporarily), but I got the "coarse/data/15000.pt", Can I ignore # ----- Optimize coarse SuGaR ----- #step and run # ----- Extract mesh from coarse SuGaR -----# step directly by setting any parameters?

wen-yuan-zhang commented 11 months ago

same quesiton.

xuncpp commented 8 months ago

same quesiton.Is there any solution? Thank you so much!

xuncpp commented 8 months ago

I may have solved the problem, you can just run extract_refined_mesh_with_texture.py and set the corresponding parameters, but even though I just ran that program, I still ran out of memory.