Hello! I am creating a label checker for image to caption. The data to be labeled are the incorrect predictions of a model I have. This way, I have on one side the prediction of the model and on the other side the original label. I would like to be able to create a text-input and, on top of it, a title that shows (dynamically) the prediction of the model for the image.
Is this possible?
Thank you very much in advance!
I could be wrong, but it sounds like you're interested in assigning binary labels to images with an added label. Our docs have an example of this.
Depending on how you'd like the interface to look, you may prefer to make a custom recipe. That way, you might also be able to add extra information like the confidence that the model had while making the prediction. You might appreciate this section of the docs for more information on that.
In general, I want to emphasize that it's excellent to double-check the labels you're given. That's a great practice! You may also want to keep an eye on our YouTube channel, we may be posting a new video soon on this topic .