When I run "python scripts/inference_layout2depth_demo0.py", an OOM error appeared like this
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 114.00 MiB. GPU 0 has a total capacity of 23.64 GiB of which 36.12 MiB is free. Process 3051286 has 19.04 GiB memory in use. Process 3429391 has 4.56 GiB memory in use. Of the allocated memory 4.16 GiB is allocated by PyTorch, and 26.03 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)
When I run "python scripts/inference_layout2depth_demo0.py", an OOM error appeared like this
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 114.00 MiB. GPU 0 has a total capacity of 23.64 GiB of which 36.12 MiB is free. Process 3051286 has 19.04 GiB memory in use. Process 3429391 has 4.56 GiB memory in use. Of the allocated memory 4.16 GiB is allocated by PyTorch, and 26.03 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)