search

DensoITLab / Fed3DGS

Official implementation of "Fed3DGS: Scalable 3D Gaussian Splatting with Federated Learning"
Other
89 stars 6 forks source link

RuntimeError: CUDA out of memory #7

Open haggleSS opened 1 week ago

haggleSS commented 1 week ago

Excuse me, I'm encountering issues when building a global model; I am using a 4090 GPU with 24GB of VRAM; each client has 80 images。 total 7 clients

perrying commented 1 week ago

Updating the global model requires more than twice as much GPU memory as training the local model.

haggleSS commented 1 week ago

Updating the global model requires more than twice as much GPU memory as training the local model.

The model being trained is around 1GB in size, but an out-of-memory (OOM) issue occurs during the model aggregation phase. Are there any ways to reduce the usage of GPU memory?

perrying commented 1 week ago

You can reduce GPU memory by reducing the resolution of the rendered images, which can be changed with the --resolution option (default is 4, which will render images at a quarter of the default resolution defined by the camera intrinsics).