extra_mesh out of Memory (200 images) #114
Description
wsl ubuntu22.04 cuda11.8 3090
File "/home/app/miniconda3/envs/gof/lib/python3.8/site-packages/einops/_backends.py", line 288, in einsum
return self.torch.einsum(pattern, *x)
File "/home/app/miniconda3/envs/gof/lib/python3.8/site-packages/torch/functional.py", line 386, in einsum
return _VF.einsum(equation, operands) # type: ignore[attr-defined]
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 29.06 GiB. GPU 0 has a total capacity of 24.00 GiB of which 0 bytes is free. Including non-PyTorch memory, this process has 17179869184.00 GiB memory in use. Of the allocated memory 40.85
GiB is allocated by PyTorch, and 242.63 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)