hiranumn / IntegratedGradients

Python/Keras implementation of integrated gradients presented in "Axiomatic Attribution for Deep Networks" for explaining any model defined in Keras framework.
MIT License
216 stars 51 forks source link

Choosing a Baseline #10

Open samridhim opened 5 years ago

samridhim commented 5 years ago

What is the baseline for text data? Can i take my own, if yes, how?

hiranumn commented 5 years ago

What exactly is your input?

samridhim commented 5 years ago

One hot encoded embedded motif dna sequences similar to DeepBind!

samridhim commented 5 years ago

I tried passing the reference array as a 3d array and each element is 0.25. But I can't interpret the output