I am trying to run the render_hierarchy.py using Wayve101-Scene004 data then I meet an error:
Rendering ${DATASET_DIR}
------------LLFF HOLD-------------
Reading camera 1000/1000
125 test images
875 train images
Making Training Dataset
Making Test Dataset
WARNING: NO ANCHORS FOUND
No exposure to be loaded at ${DATASET_DIR}/exposure.json
0%| | 0/125 [00:00<?, ?it/s][ INFO ] Encountered quite large input images (>1.6K pixels width), rescaling to 1.6K.
If this is not desired, please explicitly specify '--resolution/-r' as 1
0%| | 0/125 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/path/to/code/hierarchical-3d-gaussians/render_hierarchy.py", line 140, in <module>
render_set(args, scene, pipe, os.path.join(args.out_dir, f"render_{tau}"), tau, args.eval)
File "/path/to/anaconda3/envs/h3dgs/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/path/to/code/hierarchical-3d-gaussians/render_hierarchy.py", line 82, in render_set
image = torch.clamp(render_post(
^^^^^^^^^^^^
File "/path/to/code/hierarchical-3d-gaussians/gaussian_renderer/__init__.py", line 158, in render_post
screenspace_points = torch.zeros_like(pc.get_xyz, dtype=pc.get_xyz.dtype, requires_grad=True, device="cuda") + 0
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: CUDA error: invalid configuration argument
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
By the way, the full_train.py seems work correctly in my environment and it gives the outputs like this:
Hello everyone!
I am trying to run the render_hierarchy.py using Wayve101-Scene004 data then I meet an error:
By the way, the full_train.py seems work correctly in my environment and it gives the outputs like this:
Environments: OS: Ubuntu 20.04.4 LTS GPU: NVIDIA A800 Driver Version: 535.183.01 CUDA Version: 12.2 Python Version: 3.12.4
Pip packages versions:
Does anyone have any idea about this error? If more detailed information is needed, please let me know.
Thanks for your help!