ML Local Hosting Not Giving Annotation Suggestions

[zshar7]

I used your library to import a new custom YOLO model which is yolo11 extra large segmentation model.
I put it into the models folder and mounted using the docker local hosting. The AI is on http://localhost:9090 with the label-studio being on http://localhost:8080

When I press send test request it returned:

500
{
  "detail": "ML backend did not return any predictions, check ML backend logs for more details"
}

The model was successfully connected according to the Label-Studio and Docker.

Now when I went into the tasks and loaded up an image (I had "Use predictions to prelabel tasks" on). And no labeling was done by the YOLO model. It cannot be the model not detecting anything because I did a prediction with the same image and the YOLO model detected the object and segmented it successfully.
On the docker logs it says the following:

[2025-06-17 21:07:21,248] [DEBUG] [label_studio_ml.api::log_response_info::193] Response body: b'{"detail":"ValueError: No suitable 
control tags (e.g. Choices, RectangleLabels, RectangleLabels, PolygonLabels, KeyPointLabels, VideoRectangle, TimelineLabels connected to
Image or Video object tags) detected in the label config:\\n<View>\\n\\n  <Header value=\\"Select label and click the image to start\\"/>\\n 
<Image name=\\"image\\" value=\\"$image\\" zoom=\\"true\\"/>\\n\\n  <PolygonLabels \\n                 name=\\"label\\" \\n                
model_path=\\"testings.pt\\" \\n                 toName=\\"image\\"\\n                 opacity=\\"0.1\\" \\n                 model_score_threshold=\\"0.01\\">\\n 
<Label value=\\"tissue\\" background=\\"#002aff\\"/>\\n  </PolygonLabels>\\n\\n</View>","request":{},"result":{"traceback":"Traceback (most
recent call last):\\n  File \\"/opt/conda/lib/python3.10/site-packages/label_studio_ml/exceptions.py\\", line 39, in exception_f\\n    return
f(*args, **kwargs)\\n  File \\"/opt/conda/lib/python3.10/site-packages/label_studio_ml/api.py\\", line 69, in _predict\\n    response =
model.predict(tasks, context=context, **params)\\n  File \\"/app/model.py\\", line 109, in predict\\n    control_models =
self.detect_control_models()\\n  File \\"/app/model.py\\", line 88, in detect_control_models\\n    raise ValueError(\\nValueError: No suitable
control tags (e.g. Choices, RectangleLabels, RectangleLabels, PolygonLabels, KeyPointLabels, VideoRectangle, TimelineLabels connected to
Image or Video object tags) detected in the label config:\\n<View>\\n\\n  <Header value=\\"Select label and click the image to start\\"/>\\n 
<Image name=\\"image\\" value=\\"$image\\" zoom=\\"true\\"/>\\n\\n  <PolygonLabels \\n                 name=\\"label\\" \\n                
model_path=\\"testings.pt\\" \\n                 toName=\\"image\\"\\n                 opacity=\\"0.1\\" \\n                 model_score_threshold=\\"0.01\\">\\n 
<Label value=\\"tissue\\" background=\\"#002aff\\"/>\\n  </PolygonLabels>\\n\\n</View>\\n"},"status":500}\n'

I really do not know what the issue is.
Also here is the annotation file (the custom model is called testings.pt):

<View>

  <Header value="Select label and click the image to start"/>
  <Image name="image" value="$image" zoom="true"/>

  <PolygonLabels 
                 name="label" 
                 model_path="testings.pt" 
                 toName="image"
                 opacity="0.1" 
                 model_score_threshold="0.01">
  <Label value="tissue" background="#002aff"/>
  </PolygonLabels>

</View>

[zshar7]

got fixed, used "tissue" instead of the correct "path"
double check your values and labels and see if they align with your custom model :)