Max Tkachenko
Max Tkachenko
In this case it's weird: LS 1.0 docker doesn't have ML backend at all.
Hi, please, check this issue, hope it'll help. https://github.com/heartexlabs/label-studio/issues/675#issuecomment-802585890
@kbv72 sorry for a late answer :slightly_frowning_face: > Is it correct way of viewing the predictions? yes, it looks ok. > If so, how to get prediction scores? You have...
@aczy99 Try to set model version on Project Settings => Machine Learning. Also it's better to include "model_version" field to the prediction root too.
Please check this docs https://labelstud.io/tutorials/object-detector.html And also this video might be helpful https://youtu.be/CyRe73VD4EE
Also please check this issue, it might be useful - https://github.com/heartexlabs/label-studio/issues/732#issuecomment-810731402
@FredHaa Hi! Try to add random ids to each result, e.g.: ``` { "id": "abc123", "type": "labels", "value": { "end": 41, "start": 0, "labels": [ "Speech" ] }, "to_name": [...
"to_name": [ "audio" ], => "to_name": "audio",
Could you please use the latest version from the master? (It's 1.0.7 as I remember)
Hi! Have you seen these articles? 1. https://labelstud.io/guide/ml.html#Start-your-custom-ML-backend-with-Label-Studio 2. https://labelstud.io/guide/ml_create.html#main 3. https://labelstud.io/tutorials/dummy_model.html 4. https://labelstud.io/tutorials/object-detector.html