jeremiedb / mxnet_r_bucketing Goto Github PK

I got problem in understanding the purpose of the embedding layer (corresponding to the para num.embed in rnn.graph). Could I ask what's its purpose and could I set it to be any arbitrary non-negative integer? Thanks a lot.

I am trying to use time series example from https://jeremiedb.github.io/mxnet_R_bucketing/TimeSeries_CPU with latest MXNetR

However, when I follow the tutorial, it fails at

infer <- mx.infer.rnn.one.unroll(infer.data = data, 
                              symbol = symbol.infer.ini,                                  
                              num_hidden = 50,
                           arg.params = model$arg.params,
                          aux.params = model$aux.params,
                         init_states = NULL,
                               ctx = ctx)

The error message is

Error in mxnet:::mx.symbol.bind(symbol = symbol, arg.arrays = c(dlist, :
executor.cc:124: RCheck failed: Rcpp::is(source_array[i]) Expect input arg_arrays to be list of MXNDArray

Could you help me on how to use this API and what maybe going wrong.

Wanna know if I can change softmaxoutput to regression(linear) to do regression?

What is the purpose of shuffling here?

https://github.com/jeremiedb/mxnet_R_bucketing/blob/master/mx_io_bucket_iter.R#L38