jamescasia/torch_rnn

Issues

• Add NaN input safety

  #3 opened 2 years ago by jamescasia
  0

• Sequence should be RNN with bidirectional, many to many/one to many, previous y when null input options

  #6 opened 2 years ago by jamescasia
  0

• Refactor to match Pytorch Module patterns

  #5 opened 2 years ago by jamescasia
  0

• Add support for LSTMs

  #4 opened 2 years ago by jamescasia
  0

• If RNN has output_dim >=2, and the seq_length < time_steps. The outputs will just be copied over and won't make sense.

  #1 opened 2 years ago by jamescasia
  1

• Model doesn't take into account different length inputs

  #2 opened 2 years ago by jamescasia
  1