Skip to content

QUICK_START.md example broken due to bfshi/AutoGaze no longer existing #6

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

QUICK_START.md example broken due to bfshi/AutoGaze no longer existing #6

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
6 changes: 3 additions & 3 deletions QUICK_START.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,8 +13,8 @@ from autogaze.datasets.video_utils import read_video_pyav, transform_video_for_p
from autogaze.models.autogaze import AutoGazeImageProcessor, AutoGaze

# Load AutoGaze model and its preprocessor from HuggingFace
autogaze_transform = AutoGazeImageProcessor.from_pretrained("bfshi/AutoGaze")
autogaze_model = AutoGaze.from_pretrained("bfshi/AutoGaze")
autogaze_transform = AutoGazeImageProcessor.from_pretrained("nvidia/AutoGaze")
autogaze_model = AutoGaze.from_pretrained("nvidia/AutoGaze")

# Load a video
video_path = "<path_to_autogaze_code>/assets/example_input.mp4" # Fill in the path of AutoGaze codebase
Expand Down Expand Up @@ -92,7 +92,7 @@ Let's take SigLIP2-SO400M with 384x384 input resolution and 14x14 patch size as

```python
# Load AutoGaze preprocessor with size of 392
autogaze_392_transform = AutoGazeImageProcessor.from_pretrained("bfshi/AutoGaze", size=(392, 392))
autogaze_392_transform = AutoGazeImageProcessor.from_pretrained("nvidia/AutoGaze", size=(392, 392))

# Preprocess the video with AutoGaze preprocessor
video_input_autogaze_392 = transform_video_for_pytorch(raw_video, autogaze_392_transform) # T * C * H * W
Expand Down