bert_document_classification icon indicating copy to clipboard operation
bert_document_classification copied to clipboard

How to interpret the result?

Open shamitb opened this issue 4 years ago • 2 comments

smoking_classifier.predict(["Smoking can lead to arterial congestions. This in the long run is injurious and even fatal as per a WHO advisory"])

I get result as:

tensor([[0.], [1.], [1.], [0.]]) How do I interpret the above tensor values?

How can I specify the labels and get the label as the output?

shamitb avatar Jan 28 '20 23:01 shamitb

Also how to train for a new area and a set of documents? Say cardiology or diabetes etc.

shamitb avatar Jan 28 '20 23:01 shamitb

Hi, these are label indicators.

AndriyMulyar avatar Jan 29 '20 17:01 AndriyMulyar