search

mikeqzy / 3dgs-avatar-release

3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting
MIT License
315 stars 30 forks source link

CUDA out of memory #9

Closed ZhaoLizz closed 6 months ago

ZhaoLizz commented 6 months ago

Hi! I encountered an issue while running the training code with python train.py dataset=ps_female_3 option=iter30k pose_correction=none on a single Nvidia RTX 4090 GPU with default config setting. It appears that the rasterizer is demanding 33.47 GB GPU memory.

I'm reaching out to inquire if any specific parameters within the script or configuration can be adjusted to reduce the GPU memory requirements to a more manageable level.

Thank you for your assistance.

image
ZhaoLizz commented 6 months ago

I tried to change the init Gaussians number from 50k to 10k in Dataset. It worked.