Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

use scikit instead of torchmcubes #26

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

use scikit instead of torchmcubes #26

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
omegaconf==2.3.0
Pillow==10.1.0
einops==0.7.0
git+https://github.com/tatsy/torchmcubes.git
scikit-image
transformers==4.35.0
trimesh==4.0.5
rembg
Expand Down
18 changes: 9 additions & 9 deletions tsr/models/isosurface.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,7 @@
import numpy as np
import torch
import torch.nn as nn
from torchmcubes import marching_cubes

from skimage import measure

class IsosurfaceHelper(nn.Module):
points_range: Tuple[float, float] = (0, 1)
Expand Down Expand Up @@ -42,11 +41,12 @@ def forward(
level: torch.FloatTensor,
) -> Tuple[torch.FloatTensor, torch.LongTensor]:
level = -level.view(self.resolution, self.resolution, self.resolution)
try:
v_pos, t_pos_idx = self.mc_func(level.detach(), 0.0)
except AttributeError:
print("torchmcubes was not compiled with CUDA support, use CPU version instead.")
v_pos, t_pos_idx = self.mc_func(level.detach().cpu(), 0.0)
v_pos = v_pos[..., [2, 1, 0]]
v_pos, t_pos_idx, _, __ = measure.marching_cubes(
(level.detach().cpu() if level.is_cuda else level.detach()).numpy(),
0.0) # self.mc_func(level.detach(), 0.0)
v_pos = torch.from_numpy(v_pos.copy()).type(torch.FloatTensor).to(level.device)
t_pos_idx = torch.from_numpy(t_pos_idx.copy()).type(torch.LongTensor).to(level.device)
v_pos = v_pos[..., [0, 1, 2]]
t_pos_idx = t_pos_idx[..., [1, 0, 2]]
v_pos = v_pos / (self.resolution - 1.0)
return v_pos.to(level.device), t_pos_idx.to(level.device)
return v_pos, t_pos_idx