No applicable method for 'predict' applied to an object of class “MXFeedForwardModel”

Question

I have created a Neural network model using the mxnet package in R studio. I tested the model on local and it works as expected. I have deployed the same model as a webservice in AzureML using a publish web service() function from R.

When I try to predict the test data with the web service using consume() function:

pred_cnn <- consume(endpoint_cnn, testdf)

it always throws the following error:

Error: AzureML returns error code: HTTP status code : 400 AzureML error code : LibraryExecutionError

Module execution encountered an internal library error.

The following error occurred during evaluation of R script: R_tryEval: return error: Error in UseMethod("predict") :

no applicable method for 'predict' applied to an object of class "MXFeedForwardModel"

Answer 1

Call a traceback function to check what went wrong with the HTTP request. 

You can try avoiding not calling  your data, as that will mask a built-in R function. 

For predict you should supply the fitted mode.