Search code examples
deep-learningmxnet

Extract Input parameters from "mxnet" model

I have saved the model using

mx.model.save(model = fit_dl, prefix = "model", iteration = 10)

and loaded later 

fit <- mx.model.load(prefix = "model", iteration = 10)

Now, using object fit, I want to extract the input features (column names of train data). How to do that

Solution

  • Posting for sake of all open source community

    As per my email exchange with maintner of mxnet packge, Qiang Kou replies following

    From: Qiang Kou To: Shiv Onkar Kumar Sent: Wednesday, 14 June 2017 10:33 PM Subject: Re: Extract Input parameters from “mxnet” model

    Hi, Shiv,

    I don't this is possible since we never store this information in the model.

    Best, Qiang Kou