[F glutil.cpp:332] eglGetDisplay() failed

[Asianfleet]

The command I run：

python main.py --config configs/image.yaml input=/data/AIMH/pkgs/3D/Gen/dreamgaussian/data/anya_rgba.png save_path=/data/AIMH/pkgs/3D/Gen/dreamgaussian/outputs

The result：

Warning: Unable to load the following plugins:

    libio_e57.so: libio_e57.so does not seem to be a Qt Plugin.

Cannot load library /data/AIMH/envs/DMGS/lib/python3.9/site-packages/pymeshlab/lib/plugins/libio_e57.so: (/lib/x86_64-linux-gnu/libp11-kit.so.0: undefined symbol: ffi_type_pointer, version LIBFFI_BASE_7.0)

[INFO] load image from /data/AIMH/pkgs/3D/Gen/dreamgaussian/data/anya_rgba.png... Number of points at initialisation : 5000 [INFO] loading zero123... Keyword arguments {'trust_remote_code': True} are not expected by Zero123Pipeline and will be ignored. Loading pipeline components...: 100%|████████████████████████████████████████████████████████| 6/6 [00:00<00:00, 8.68it/s] [INFO] loaded zero123! 100%|████████████████████████████████████████████████████████████████████████████████████| 500/500 [00:32<00:00, 15.52it/s] [INFO] save model to /data/AIMH/pkgs/3D/Gen/dreamgaussian/outputs_model.ply. /data/AIMH/envs/DMGS/lib/python3.9/site-packages/torch/functional.py:478: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2894.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Tensor occ torch.Size([128, 128, 128]) torch.float32 cuda:0 ∈ [0.0, 72.29066467285156] μ = 0.5078492164611816 σ = 3.022645950317383 [INFO] mesh cleaning: (24268, 3) --> (12375, 3), (48532, 3) --> (24746, 3) [INFO] marching cubes result: torch.Size([12375, 3]) (-0.6998300552368164-0.6867133378982544), torch.Size([24746, 3]) [INFO] unwrap uv... [F glutil.cpp:332] eglGetDisplay() failed 已放弃 (核心已转储)

System：Ubuntu20.04 GPU：A100 40G

[linmi1]

the same question!

[linmi1]

The command I run：

python main.py --config configs/image.yaml input=/data/AIMH/pkgs/3D/Gen/dreamgaussian/data/anya_rgba.png save_path=/data/AIMH/pkgs/3D/Gen/dreamgaussian/outputs

The result：

Warning: Unable to load the following plugins:

    libio_e57.so: libio_e57.so does not seem to be a Qt Plugin.

Cannot load library /data/AIMH/envs/DMGS/lib/python3.9/site-packages/pymeshlab/lib/plugins/libio_e57.so: (/lib/x86_64-linux-gnu/libp11-kit.so.0: undefined symbol: ffi_type_pointer, version LIBFFI_BASE_7.0)

[INFO] load image from /data/AIMH/pkgs/3D/Gen/dreamgaussian/data/anya_rgba.png... Number of points at initialisation : 5000 [INFO] loading zero123... Keyword arguments {'trust_remote_code': True} are not expected by Zero123Pipeline and will be ignored. Loading pipeline components...: 100%|████████████████████████████████████████████████████████| 6/6 [00:00<00:00, 8.68it/s] [INFO] loaded zero123! 100%|████████████████████████████████████████████████████████████████████████████████████| 500/500 [00:32<00:00, 15.52it/s] [INFO] save model to /data/AIMH/pkgs/3D/Gen/dreamgaussian/outputs_model.ply. /data/AIMH/envs/DMGS/lib/python3.9/site-packages/torch/functional.py:478: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2894.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Tensor occ torch.Size([128, 128, 128]) torch.float32 cuda:0 ∈ [0.0, 72.29066467285156] μ = 0.5078492164611816 σ = 3.022645950317383 [INFO] mesh cleaning: (24268, 3) --> (12375, 3), (48532, 3) --> (24746, 3) [INFO] marching cubes result: torch.Size([12375, 3]) (-0.6998300552368164-0.6867133378982544), torch.Size([24746, 3]) [INFO] unwrap uv... [F glutil.cpp:332] eglGetDisplay() failed 已放弃 (核心已转储)

System：Ubuntu20.04 GPU：A100 40G

朋友，这个问题你解决了吗？ hello,have you solve this problem?

[UranusITS]

I fix this with force_cuda_rast=True

### training gaussian stage
# train 500 iters (~1min) and export ckpt & coarse_mesh to logs
python main.py --config configs/image.yaml input=data/name_rgba.png save_path=name force_cuda_rast=True