-
Notifications
You must be signed in to change notification settings - Fork 22
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.
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
Generated images without movable objects #7
Comments
The visualization you show and the box projection at inference time are not executed at the same time. It is possible that the visualization is correct but the box is not actually projected onto the canvas. DriveArena/WorldDreamer/dataset/map_utils.py Line 121 in ba7dd86
|
@jokester-zzz thank you very much! I have solved this problem. Due to mismatched opencv version, cv2.line may raise an tuple error, so by |
Congratulations on solving the problem! And it reminds me to add some instructions there😆 |
Hi, great work for your job!

Why are there no foreground objects such as cars in the pictures I generated?
By the way,I have no openai account so i can't generate updated_description_.pkl file, so i just use original 12Hz_.pkl as WorldDreamer's input, is that the reason?
The text was updated successfully, but these errors were encountered: