Skip to content

Fix instructions for cuda-architecture specific Docker build #1

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

Open
JRombouts wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Fix instructions for cuda-architecture specific Docker build #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1888c39
Correct instructions for Docker build
JRombouts Mar 5, 2023
c0c714c
Fix minor scannet bug. (#1555)
ponimatkin Mar 5, 2023
70c9005
Merge branch 'main' into JRombouts-docker-build-instruction-fix
JRombouts Mar 5, 2023
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 docs/quickstart/installation.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,7 +140,7 @@ To restrict to only CUDA architectures that you have available locally, use the
build arg and look up [the compute capability for your GPU](https://developer.nvidia.com/cuda-gpus).
For example, here's how to build with support for GeForce 30xx series GPUs:
```bash
docker build --build-arg CUDA_ARCHITECTURES=86 -tag nerfstudio-86 .
docker build --build-arg CUDA_ARCHITECTURES=86 --tag nerfstudio-86 -f Dockerfile .
```

### Using an interactive container
Expand Down
6 changes: 3 additions & 3 deletions nerfstudio/data/dataparsers/scannet_dataparser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,9 +82,9 @@ def _generate_dataparser_outputs(self, split="train"):
K = np.loadtxt(self.config.data / "intrinsic" / "intrinsic_color.txt")
for img, depth, pose in zip(img_dir_sorted, depth_dir_sorted, pose_dir_sorted):
pose = np.loadtxt(pose)
frame_pose[0:3, 1:3] *= -1
frame_pose = frame_pose[np.array([1, 0, 2, 3]), :]
frame_pose[2, :] *= -1
pose[0:3, 1:3] *= -1
pose = pose[np.array([1, 0, 2, 3]), :]
pose[2, :] *= -1

# We cannot accept files directly, as some of the poses are invalid
if np.isinf(pose).any():
Expand Down