Image classifier without softmax

Question

I'm using Turi Create to generate a Core ML image classifier like this:

import turicreate as tc
data =  tc.SFrame('data.sframe')
model = tc.image_classifier.create(data, target='label')
model.export_coreml('classifier.mlmodel')

However, the model gives me softmax confidence values and in my application, I need pre-softmax values (I'll calculate softmax in the app). Is there a way to turn off the softmax layer?

I've had models like this supplied to me in the past, but now I need to generate my own. I've read through the docs and looked through source code (which I'm willing to modify if needed), but I don't know enough about machine learning to figure it out.

Answer 1

Here is how you can access attributes of the models. It means features, coefficients etc.

Turi Documentation

Let me know if it helps