mengxuyiGit
mengxuyiGit
I also encountered the same problem on RTX3090 gpu: while the GPU mem is only about 2GB, it will produce OOM at this line
+1, same request
Thanks for instant reply! So can I use this train_renderer with the generated data to train renderer stand alone ?
i would like to train the renderer alone, may i have a file containing "particle_pos" of bunny? thanks!
Thanks very much! By the way, when I train using the default 4 views settign on 1 GPU, it will give OOM error. The num_views in the trainer_renderer loops can...
maybe try replacing "**from_pretrained**" to "**from_pretrained_2d**" in https://github.com/xxlong0/Wonder3D/blob/deeba9833570fce09dd4da393f6318475e85a735/train_mvdiffusion_joint.py#L251 ?
Same problem here. Have you found a correct rendering scale?
The tricks that worked for 3DGS (such as TORCH_ARCH_LIST and ` extra_compile_args={"nvcc": ["-Xcompiler", "-fno-gnu-unique", "-I" + os.path.join(os.path.dirname(os.path.abspath(__file__)), "third_party/glm/")]})` will not work anymore)
I switch to a different pytorch & cuda version and it finally works: torch==2.1.3 and cuda=12.1
Thanks for replying!