You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
First of all, thank you for letting it be open source and the respiratory has a very interesting idea. I got this error when I want to plot batches after the learning round and also I have a question: How we can use this using real user feedback not simulate relevance feedback?
Thanks in advance
The text was updated successfully, but these errors were encountered:
Our visualization utility function supports two types of datasets: Image datasets, which have an imgs_train attribute providing a list of all training images or their filenames, or datasets with 2-dimensional data. Your dataset seems to be none of these, so the function does not know how to plot it.
Could you elaborate your use case further?
To integrate user feedback, one would call the ITAL.update method with the obtained feedback and then call ITAL.fetch_unlabelled to obtain a new batch of images to be annotated. During the entire process, you can also obtain the currently most relevant results using ITAL.top_results. It's probably useful to show both to the user. This way, the user can see the most relevant images at any stage of the process and decide when to stop and also improve the results further by annotating the provided active learning batch.
Hello
First of all, thank you for letting it be open source and the respiratory has a very interesting idea. I got this error when I want to plot batches after the learning round and also I have a question: How we can use this using real user feedback not simulate relevance feedback?
Thanks in advance
The text was updated successfully, but these errors were encountered: