Unable to save meshes, everything else worked.

[andytriboletti]

Description

I can generate videos of objects, but when I try to save the mesh, it fails.

Steps to Reproduce

I ran:
python3 main.py --text "a margherita pizza" --workspace trial5 -O

Which saved a mp4 of a pizza rotating.
I tried to save meshes:
python3 main.py --workspace trial5 -O --test --save_mesh

andy@andys-pc:/stable-dreamfusion$ python3 main.py --workspace trial5 -O --test --save_mesh
Namespace(file=None, text=None, negative='', O=True, O2=False, test=True, six_views=False, eval_interval=1, test_interval=100, workspace='trial5', seed=None, image=None, image_config=None, known_view_interval=4, IF=False, guidance=['SD'], guidance_scale=100, save_mesh=True, mcubes_resolution=256, decimate_target=50000.0, dmtet=False, tet_grid_size=128, init_with='', lock_geo=False, perpneg=False, negative_w=-2, front_decay_factor=2, side_decay_factor=10, iters=10000, lr=0.001, ckpt='latest', cuda_ray=True, taichi_ray=False, max_steps=1024, num_steps=64, upsample_steps=32, update_extra_interval=16, max_ray_batch=4096, latent_iter_ratio=0.2, albedo_iter_ratio=0, min_ambient_ratio=0.1, textureless_ratio=0.2, jitter_pose=False, jitter_center=0.2, jitter_target=0.2, jitter_up=0.02, uniform_sphere_rate=0, grad_clip=-1, grad_clip_rgb=-1, bg_radius=1.4, density_activation='exp', density_thresh=10, blob_density=5, blob_radius=0.2, backbone='grid', optim='adan', sd_version='2.1', hf_key=None, fp16=True, vram_O=False, w=64, h=64, known_view_scale=1.5, known_view_noise_scale=0.002, dmtet_reso_scale=8, batch_size=1, bound=1, dt_gamma=0, min_near=0.01, radius_range=[3.0, 3.5], theta_range=[45, 105], phi_range=[-180, 180], fovy_range=[10, 30], default_radius=3.2, default_polar=90, default_azimuth=0, default_fovy=20, progressive_view=False, progressive_view_init_ratio=0.2, progressive_level=False, angle_overhead=30, angle_front=60, t_range=[0.02, 0.98], dont_override_stuff=False, lambda_entropy=0.001, lambda_opacity=0, lambda_orient=0.01, lambda_tv=0, lambda_wd=0, lambda_mesh_normal=0.5, lambda_mesh_laplacian=0.5, lambda_guidance=1, lambda_rgb=1000, lambda_mask=500, lambda_normal=0, lambda_depth=10, lambda_2d_normal_smooth=0, lambda_3d_normal_smooth=0, save_guidance=False, save_guidance_interval=10, gui=False, W=800, H=800, radius=5, fovy=20, light_theta=60, light_phi=0, max_spp=1, zero123_config='./pretrained/zero123/sd-objaverse-finetune-c_concat-256.yaml', zero123_ckpt='pretrained/zero123/zero123-xl.ckpt', zero123_grad_scale='angle', dataset_size_train=100, dataset_size_valid=8, dataset_size_test=100, exp_start_iter=0, exp_end_iter=10000, images=None, ref_radii=[], ref_polars=[], ref_azimuths=[], zero123_ws=[], default_zero123_w=1)
NeRFNetwork(
(encoder): GridEncoder: input_dim=3 num_levels=16 level_dim=2 resolution=16 -> 2048 per_level_scale=1.3819 params=(6098120, 2) gridtype=hash align_corners=False interpolation=smoothstep
(sigma_net): MLP(
(net): ModuleList(
(0): Linear(in_features=32, out_features=64, bias=True)
(1): Linear(in_features=64, out_features=64, bias=True)
(2): Linear(in_features=64, out_features=4, bias=True)
)
)
(encoder_bg): FreqEncoder: input_dim=3 degree=6 output_dim=39
(bg_net): MLP(
(net): ModuleList(
(0): Linear(in_features=39, out_features=32, bias=True)
(1): Linear(in_features=32, out_features=3, bias=True)
)
)
)
[INFO] Cmdline: main.py --workspace trial5 -O --test --save_mesh
[INFO] opt: Namespace(file=None, text=None, negative='', O=True, O2=False, test=True, six_views=False, eval_interval=1,
test_interval=100, workspace='trial5', seed=None, image=None, image_config=None, known_view_interval=4, IF=False,
guidance=['SD'], guidance_scale=100, save_mesh=True, mcubes_resolution=256, decimate_target=50000.0, dmtet=False,
tet_grid_size=128, init_with='', lock_geo=False, perpneg=False, negative_w=-2, front_decay_factor=2,
side_decay_factor=10, iters=10000, lr=0.001, ckpt='latest', cuda_ray=True, taichi_ray=False, max_steps=1024,
num_steps=64, upsample_steps=32, update_extra_interval=16, max_ray_batch=4096, latent_iter_ratio=0.2,
albedo_iter_ratio=0, min_ambient_ratio=0.1, textureless_ratio=0.2, jitter_pose=False, jitter_center=0.2,
jitter_target=0.2, jitter_up=0.02, uniform_sphere_rate=0, grad_clip=-1, grad_clip_rgb=-1, bg_radius=1.4,
density_activation='exp', density_thresh=10, blob_density=5, blob_radius=0.2, backbone='grid', optim='adan',
sd_version='2.1', hf_key=None, fp16=True, vram_O=False, w=64, h=64, known_view_scale=1.5, known_view_noise_scale=0.002,
dmtet_reso_scale=8, batch_size=1, bound=1, dt_gamma=0, min_near=0.01, radius_range=[3.0, 3.5], theta_range=[45, 105],
phi_range=[-180, 180], fovy_range=[10, 30], default_radius=3.2, default_polar=90, default_azimuth=0, default_fovy=20,
progressive_view=False, progressive_view_init_ratio=0.2, progressive_level=False, angle_overhead=30, angle_front=60,
t_range=[0.02, 0.98], dont_override_stuff=False, lambda_entropy=0.001, lambda_opacity=0, lambda_orient=0.01, lambda_tv=0,
lambda_wd=0, lambda_mesh_normal=0.5, lambda_mesh_laplacian=0.5, lambda_guidance=1, lambda_rgb=1000, lambda_mask=500,
lambda_normal=0, lambda_depth=10, lambda_2d_normal_smooth=0, lambda_3d_normal_smooth=0, save_guidance=False,
save_guidance_interval=10, gui=False, W=800, H=800, radius=5, fovy=20, light_theta=60, light_phi=0, max_spp=1,
zero123_config='./pretrained/zero123/sd-objaverse-finetune-c_concat-256.yaml',
zero123_ckpt='pretrained/zero123/zero123-xl.ckpt', zero123_grad_scale='angle', dataset_size_train=100,
dataset_size_valid=8, dataset_size_test=100, exp_start_iter=0, exp_end_iter=10000, images=None, ref_radii=[],
ref_polars=[], ref_azimuths=[], zero123_ws=[], default_zero123_w=1)
[INFO] Trainer: df | 2023-08-19_19-57-10 | cuda | fp16 | trial5
[INFO] #parameters: 12204151
[INFO] Loading latest checkpoint ...
[INFO] Latest checkpoint is trial5/checkpoints/df_ep0100.pth
[INFO] loaded model.
[INFO] load at epoch 100, global step 10000
[WARN] Failed to load optimizer.
[INFO] loaded scheduler.
[INFO] loaded scaler.
==> Start Test, save results to trial5/results
100% 100/100 [00:13<00:00, 8.23it/s]==> Finished Test.
100% 100/100 [00:13<00:00, 7.18it/s]
==> Saving mesh to trial5/mesh
[INFO] marching cubes thresh: 10 (0.0 ~ 9316.431640625)
[INFO] mesh cleaning: (65714, 3) --> (42247, 3), (128936, 3) --> (84958, 3)
[INFO] mesh decimation: (42247, 3) --> (24790, 3), (84958, 3) --> (50000, 3)
[INFO] running xatlas to unwrap UVs for mesh: v=(24790, 3) f=(50000, 3)
Killed
andy@andys-pc:/stable-dreamfusion$

Expected Behavior

I expected to run the command and be able to see a obj file.

Environment

Windows subsystem for Linux running Ubuntu
PC with 12Gb GPU

[andytriboletti]

I was using 16GB ram. I ordered 64GB.