Assisted labelling is inconsistent with the model results

Community Help
2

Based on the information provided in the extracts, there could be several reasons why the assisted labelling is not returning the same results as the model results for the same pictures.

  1. Model Confidence: The confidence level of the model can affect the results. You can adjust the confidence and overlap thresholds to adjust under what conditions a label will be applied. This can help reduce mislabeled objects. Source

  2. Model Compatibility: There could be compatibility issues with the model you’re using. For instance, in one of the forum posts, a user mentioned that Ultralyics had added operations in the YOLOv8 model architecture that were not compatible with non-async model execution. Source

  3. Data Quantity: If your model is not making predictions confidently, it could be due to insufficient data. Source

  4. Model Selection: Ensure that you have selected the correct model for Label Assist. You can select a model to which you have access through the Your Models tab. You can select any model from Universe through the Public Models tab. You need to star a model on Universe before it will show up in the Public Models tab. Source

If you’re still facing issues, it would be best to reach out to Roboflow’s support with the specific details of your problem.

Hi! I’m Roboflow’s AI powered bot. This is an automated response powered using AI with knowledge from our docs, blog, and forum. If this solves your issue, please mark it as the solution using the checkbox icon. If this doesn’t solve your issue, please follow up with what you’ve tried/why, and the community will continue to chime in as usual.