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.

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

Erratic aiming #298

Open
Loham opened this issue Feb 10, 2025 · 1 comment
Open

Erratic aiming #298

Loham opened this issue Feb 10, 2025 · 1 comment

Comments

@Loham
Copy link

Loham commented Feb 10, 2025

Using just the Fast setup, onnx set to cpu. In Fortnite, when the assist is turned on, the crosshair aims up towards the sky. Trying to aim down manually with the assist on makes the crosshairs shake all over the place. Resolution, windowed/fullscreen don't have any effect on the issue either. Turning visuals on, in the popup window, I can see orange square and rectangles all jumbled up in the center even if there's not a human shape on screen i.e. the sky. The command prompt doesn't read any errors except for 1 line that it floods the prompt with infinitely as long as I'm running the script:
C:\Users\xloha/.cache\torch\hub\ultralytics_yolov5_master\models\common.py:867: FutureWarning: torch.cuda.amp.autocast(args...) is deprecated. Please use torch.amp.autocast('cuda', args...) instead.
with amp.autocast(autocast):

Windows 64-bit
AMD 9800x3d
NVIDIA RTX 5080
Python 3.10
CUDA 12.8

@chienniman
Copy link

chienniman commented Feb 28, 2025

@Loham

Add this code on the top of main.py and rebuild it

This code may only hide the error, but it doesn't address the underlying issue.

Image

Personally, I believe there is an issue with this script. It cannot control the mouse movement in some games. The original developer's goal of creating a script that works for all games is highly unlikely to be feasible, as each game can have different behaviors and requirements for mouse control and aiming.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants