smedjs / ow-vision Goto Github PK

View Code? Open in Web Editor NEW

20.0 2.0 9.0 14 MB

✅ An Overwatch 2 triggerbot using detection AI !

Python 100.00%

yolov8 detection detection-model overwatch overwatch-hack triggerbot

ow-vision's Introduction

ow-vision

About

ow-vision is an AI to detect enemy on Overwatch 2 ! It can detect hero and their head and click automatically on it

Features:

✅ Detect enemy and enemy's head
✅ Detect any hero
✅ Trigger bot - click automatically on enemy head
✅ Fast - 20ms to detect and click

Made with passion, raggae and YOLOv8

Content

The training

Trigger bot

ow-vision has a script to click automatically on enemy head (not allowed by Overwatch 2 so use at your own risk)

Example in game: https://cdn.discordapp.com/attachments/941415112135307314/1097663491814465566/ApplicationFrameHost_jwhkqyaIr9.gif

Code

run

python /scripts/main.py

train

!yolo train model=yolov8n.pt data=./datasets/v2/data.yaml epochs=150 imgsz=736 project=/models/result/v2 device=0

settings

# Detection.py
settings = {"toggleKey": "²", # the key to toggle the trigger bot, the square on the frame represent the state (red=disabled)
            "cooldown": 1.1, # cooldown between clicks in seconds (only for mode 0)
            "detect": [1], # detect enemy [0] or enemyHead [1] and [0, 1] for both
            "triggerDelay": 0} # delay between clicking on the target in seconds, 0 is fine

Changelogs

Version 2

Recode and larger dataset

Version 1.1

Started hero detection

Version 1 (test)

The AI could detect bot in the training range

ow-vision's People

Contributors

Stargazers

Watchers

Forkers

joaoregis itsrolltime 869322496 yoloaim yapeepee ring0jke approx104 seungheekim w314906718

ow-vision's Issues

Could you share the datasets?

It seems that you didn't share the datasets.

Is there any way to make it shoot the center of the box?

It works fine. but, it shoot empty space in the box a lot and Decrease hit rate.
Is there any way to make it shoot the center of the box?
Or is creating a new model the only way?

crashing after a couple of seconds

I can start it perfectly fine but the little preview window is not viewing my crosshair and after a couple of seconds it closes and I get this in ps

  File "C:\Users\imnot\Desktop\ow-vision-main\scripts\main.py", line 3, in <module>
    app = Detection()
  File "C:\Users\imnot\Desktop\ow-vision-main\scripts\ai\Detection.py", line 47, in __init__
    frame = model.predict(screenshot, save=False, classes=settings["detect"], verbose=False, device=0, half=False)
  File "C:\Users\imnot\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "C:\Users\imnot\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\ultralytics\yolo\engine\model.py", line 255, in predict
    return self.predictor.predict_cli(source=source) if is_cli else self.predictor(source=source, stream=stream)
  File "C:\Users\imnot\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\ultralytics\yolo\engine\predictor.py", line 190, in __call__
    return list(self.stream_inference(source, model))  # merge list of Result into one
  File "C:\Users\imnot\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\torch\utils\_contextlib.py", line 35, in generator_context
    response = gen.send(None)
  File "C:\Users\imnot\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\ultralytics\yolo\engine\predictor.py", line 252, in stream_inference
    self.results = self.postprocess(preds, im, im0s)
  File "C:\Users\imnot\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\ultralytics\yolo\v8\detect\predict.py", line 14, in postprocess
    preds = ops.non_max_suppression(preds,
  File "C:\Users\imnot\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\ultralytics\yolo\utils\ops.py", line 258, in non_max_suppression
    i = torchvision.ops.nms(boxes, scores, iou_thres)  # NMS
  File "C:\Users\imnot\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\torchvision\ops\boxes.py", line 41, in nms
    return torch.ops.torchvision.nms(boxes, scores, iou_threshold)
  File "C:\Users\imnot\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\torch\_ops.py", line 502, in __call__
    return self._op(*args, **kwargs or {})
NotImplementedError: Could not run 'torchvision::nms' with arguments from the 'CUDA' backend. This could be because the operator doesn't exist for this backend, or was omitted during the selective/custom build process (if using custom build). If you are a Facebook employee using PyTorch on mobile, please visit https://fburl.com/ptmfixes for possible resolutions. 'torchvision::nms' is only available for these backends: [CPU, QuantizedCPU, BackendSelect, Python, FuncTorchDynamicLayerBackMode, Functionalize, Named, Conjugate, Negative, ZeroTensor, ADInplaceOrView, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, AutogradMPS, AutogradXPU, AutogradHPU, AutogradLazy, AutogradMeta, Tracer, AutocastCPU, AutocastCUDA, FuncTorchBatched, FuncTorchVmapMode, Batched, VmapMode, FuncTorchGradWrapper, PythonTLSSnapshot, FuncTorchDynamicLayerFrontMode, PythonDispatcher].```

I'm not sure if I'm just being stupid or what but when I load everything up, it works for a solid 4-5 seconds and then the AI view goes completely black. Not sure what is causing it.
https://prnt.sc/WeNkxQfp9ThQ

EDIT: The black screen happens when I load into the practice range but does not stop when I leave the practice range. Game needs to be restarted for it to fix. Then blacks out again when I load in.

Also if you don't mind me asking, where do I use the !yolo training command? Pretty new to this stuff.

how to setup?

how to setup? I dont find anything anywhere and when i tried to do it manually i just got a pytorch error becauses of cuda not enabled or something, tried installing cuda etc and nothing works

hi bro, I run it successfully, but he doesn't do anything in the game, do you know what's going on? A model I trained myself.

hi bro, I run it successfully, but he doesn't do anything in the game, do you know what's going on? A model I trained myself. 136001#0354 Can you tell me at your convenience? Thank you,

How exactly do I use this?

how do i even start the thing? i have python installed, when i open Main.py it just opens cmd and instantly closes, how do i "train" the "!yolo" or what does that even mean? opening train.py and Detection.py instantly closes as well. I have CUDA but no idea on how to use python and run any scripts like this.