XCube

XCube copied to clipboard

GPU memory cost

11

Could you share the memory cost by different stage and different dataset? I met the problem that I train fine VAE on 80GB GPU with batch_size=1 will OOM at epoch0

VLadImirluren

plyfager

Training error caused by inplace operations

1

https://github.com/nv-tlabs/XCube/blob/d0ee1c26ebd67a9a8ff803835333b088155fb051/xcube/modules/autoencoding/base_encoder.py#L63 It leads to "RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation" during training.

LeoDarcy

fvdb pip install build fails

1

At the FVDB install step, I am facing an issue where the build fails. It appears that system runs out of memory. I have 32 GB ram in the system....

d32sharm

Thanks to your great job. When will the code for waymo data processing be available?

Man-Mango

ShapeNet Data Access

2

Hey, thank you for sharing such wonderful work! I am wondering whether it is possible to grant access to your shapenet dataset?  Many thanks again!

thua919

How do I build fvdb on Jetson?

6

I am trying to get xcube to run on a nvidia Jetson Orin Nano. It is currently running with Jetpack 6.0. During the setup process I ran into an error...

chgarner

Evaluation script

1

Hi! Thanks for your great work. I'm trying to reproduce your results, and I would like to know if you could make your evaluation script available. I have tried to...

nuneslu

Error occur in training diffusion

6

At first I try to train coarse VAE using the given command python train.py ./configs/shapenet/chair/train_vae_16x16x16_dense.yaml --wname 16x16x16-kld-0.03_dim-16 --max_epochs 100 --cut_ratio 16 --gpus 1 --batch_size 16 Due to the GPU different...

VLadImirluren

Thanks to your greate job. When the objaverse training code will be release?

VLadImirluren