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

Quickstart Guide Fixes #531

Merged
merged 13 commits into from
Oct 3, 2022
Merged

Quickstart Guide Fixes #531

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
3fc3ec4
key fixes
Sep 23, 2022
ded72de
Update README.md
mcallisterdavid Sep 23, 2022
3a20251
Update run_eval.py
mcallisterdavid Sep 24, 2022
79aafe9
Merge branch 'master' into quickstart-changes
mcallisterdavid Sep 24, 2022
fb5b2e5
Merge branch 'master' into quickstart-changes
mcallisterdavid Sep 26, 2022
7631288
Merge fixed
Oct 1, 2022
eac6287
Merge branch 'master' into quickstart-changes
mcallisterdavid Oct 2, 2022
f8865af
Better error reporting
mcallisterdavid Oct 3, 2022
7c49733
lint
mcallisterdavid Oct 3, 2022
8bccb7a
Removed rgb fine change
mcallisterdavid Oct 3, 2022
dd30aa5
Readme updates
mcallisterdavid Oct 3, 2022
6f55ef9
Merge branch 'master' into quickstart-changes
mcallisterdavid Oct 3, 2022
032ed95
Justify centeR
mcallisterdavid Oct 3, 2022
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
4 changes: 2 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,10 +137,10 @@ To run with all the defaults, e.g. vanilla nerf method with the blender lego ima
python scripts/run_train.py --help

# Run a vanilla nerf model.
python scripts/run_train.py vanilla_nerf
python scripts/run_train.py vanilla-nerf

# Run a faster version with instant ngp using tcnn (without the viewer).
python scripts/run_train.py instant_ngp
python scripts/run_train.py instant-ngp
```

#### 3.x Training a model with the viewer
Expand Down
2 changes: 0 additions & 2 deletions nerfactory/models/vanilla_nerf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -218,8 +218,6 @@ def get_image_metrics_and_images(
"fine_psnr": float(fine_psnr),
"fine_ssim": float(fine_ssim),
"fine_lpips": float(fine_lpips),
"ray_loss_coarse": float(torch.mean(outputs["ray_loss_coarse"])),
"ray_loss_fine": float(torch.mean(outputs["ray_loss_fine"])),
}
images_dict = {"img": combined_rgb, "accumulation": combined_acc, "depth": combined_depth}
return metrics_dict, images_dict
2 changes: 1 addition & 1 deletion scripts/run_eval.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -151,7 +151,7 @@ class RenderTrajectory:
# Path to config YAML file.
load_config: Path
# Name of the renderer output to use. rgb, depth, etc.
rendered_output_name: str = "rgb"
rendered_output_name: str = "rgb_fine"
Copy link
Contributor

@tancik tancik Sep 24, 2022 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Keep this default to rgb, the method we expect people to use, intant-ngp, doesn't return a coarse and fine.
This is a bit confusing for the user. Perhaps we should should add some logic like

if rendered_output_name not in outputs:
  console.rule("Error", style="red")
  console.print(f"Could not find {rendered_output_name} in the model outputs", justify="center")
  console.print(f"Please set --rendered_output_name to one of: {outputs.keys()}")
  sys.exit(1)

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also for future branches, can you append your name to the beginning for organizational reasons (ie david/quickstart-changes). No need to this time.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@mcallisterdavid just bumping, not sure if you saw Matt's comments here

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hey Ethan, I got it set up on the new machine and am working through some issues. I should have some changes out tonight!

# Trajectory to render.
traj: Literal["spiral", "interp", "filename"] = "spiral"
# Scaling factor to apply to the camera image resolution.
Expand Down