search

AndriyMulyar / bert_document_classification

architectures and pre-trained models for long document classification.
154 stars 47 forks source link

How to interpret the result? #4

Open shamitb opened 4 years ago

shamitb commented 4 years ago

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 commented 4 years ago

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

AndriyMulyar commented 4 years ago

Hi, these are label indicators.