# tag=r-locomotive-1 start=2026-11-03T18:19:12+01:00 cmd=<home>/supratex-0311/venv/bin/python scripts/run_example.py --config <home>/supratex-0311/ready/models.json --input <home>/supratex-0311/in-rgb/locomotive.png --output <home>/supratex-0311/out/r-locomotive-1.glb
[    0.61] [Supra-Tex inference] attention=sdpa; sparse_attention=sdpa; low_vram=False
[    0.62] [1/2] Foreground, MoGe-2, geometry, material maps -> <home>/supratex-0311/out/r-locomotive-1_work/input
[    0.62] [Supra-Tex inference] attention=sdpa; sparse_attention=sdpa; low_vram=False
[   46.38] [2/2] Surface observations, PBR completion, GLB export -> <home>/supratex-0311/out/r-locomotive-1.glb
[   46.39] [Supra-Tex inference] attention=sdpa; sparse_attention=sdpa; low_vram=False
[   46.63] [SPARSE] Conv backend: flex_gemm; Attention backend: sdpa; Batch broadcast: direct
[   46.63] Floaters: removed 0 of 22 components (0 of 12512032 faces)
[   58.39] Observation: silhouette IoU 0.961 (geometry inside image 0.982, image covered 0.977); admitted 291634 of 307328 trusted pixels (missed geometry 1963, depth edge 3228, image-depth mismatch 10503)
[   58.39] Image depth gate: applied; 320981 paired depth pixels, 13979 mismatch pixels
[   58.40] Observation image depth: excluded 2586 additional voxel samples crossing the mismatch mask; 263276 observed voxels
[   59.41] [ATTENTION] Using backend: sdpa
[   59.41] Observation cache: enabled
[   74.63] 
Extracting GLB:   0%|          | 0/6 [00:00<?, ?it/s]
Building BVH:  17%|█▋        | 1/6 [00:00<00:00, 71.95it/s]
Building BVH:  33%|███▎      | 2/6 [00:03<00:06,  1.71s/it]
Cleaning mesh:  33%|███▎      | 2/6 [00:03<00:06,  1.71s/it]<home>/supratex-0311/venv/lib/python3.12/site-packages/cumesh/remeshing.py:220: UserWarning: Using torch.cross without specifying the dim arg is deprecated.
[   74.63] Please either pass the dim explicitly or simply use torch.linalg.cross.
[   74.63] The default value of dim will change to agree with that of linalg.cross in a future release. (Triggered internally at /__w/pytorch/pytorch/aten/src/ATen/native/Cross.cpp:63.)
[   74.63]   normals0 = torch.cross(mesh_vertices[atempt_triangles_0[:, 1]] - mesh_vertices[atempt_triangles_0[:, 0]], mesh_vertices[atempt_triangles_0[:, 2]] - mesh_vertices[atempt_triangles_0[:, 0]])
[   85.94] 
Cleaning mesh:  50%|█████     | 3/6 [00:03<00:03,  1.21s/it]
Parameterizing new mesh:  50%|█████     | 3/6 [00:03<00:03,  1.21s/it]
Parameterizing new mesh:  67%|██████▋   | 4/6 [00:07<00:04,  2.06s/it]
Sampling attributes:  67%|██████▋   | 4/6 [00:07<00:04,  2.06s/it]    
Sampling attributes:  83%|████████▎ | 5/6 [00:09<00:01,  1.92s/it]
Finalizing mesh:  83%|████████▎ | 5/6 [00:09<00:01,  1.92s/it]    
Finalizing mesh: 100%|██████████| 6/6 [00:14<00:00,  3.19s/it]
Finalizing mesh: 100%|██████████| 6/6 [00:14<00:00,  2.47s/it]
[   92.44] Textured mesh: <home>/supratex-0311/out/r-locomotive-1.glb
[   92.44] Intermediate files and run receipt: <home>/supratex-0311/out/r-locomotive-1_work