ayushexel / bridge Goto Github PK

On completion of training with MLflow logger enabled, the following exception is raised:

MlflowException: Invalid artifact path: '[/Shared/YOLOv8](https://file+.vscode-resource.vscode-cdn.net/Shared/YOLOv8)'. 

Names may be treated as files in certain cases, and must not resolve to other names when treated as such. 

This name would resolve to '[/Shared/YOLOv8](https://file+.vscode-resource.vscode-cdn.net/Shared/YOLOv8)

This arrises as logging artefacts attempts to write to '/Shared/YOLOv8', set below

experiment_name = trainer.args.project or '/Shared/YOLOv8'

Suggest using an alternative to '/Shared/YOLOv8'

Environment

Any

Minimal Reproducible Example

It is necessary to set a valid MLflow instance url and run model.train

os.environ["MLFLOW_TRACKING_URI"] = "https://dev-mlflow.bla.com/"

Additional

No response

Are you willing to submit a PR?

I'm trying Yolov8 with screen capture but it doesn't seem to work. I'm using the win32gui.GetDesktopWindow() to get the screenshot

Here my code

   self.model = YOLO('yolov8n.pt')
    frame = wincap.getScreenshot(detection_box)
    results = self.model(frame)
    print(results)

Here is what the output looks like.

[Ultralytics YOLO <class 'ultralytics.yolo.engine.results.Results'> instance
Ultralytics YOLO <class 'ultralytics.yolo.engine.results.Boxes'> masks
type: <class 'torch.Tensor'>
shape: torch.Size([0, 6])
dtype: torch.float32
original size: (270, 480)
]
When I try

print(results.boxes) or print(results.masks)
I get this error

AttributeError: 'list' object has no attribute 'boxes'