Pytorch c++ BLSTM

[scottrs (Scott Smallwood)]

i am trying to solve a BLSTM model in c++ using pytorch. I copied the code from here

How to use Bidirectional LSTM in C++ API correctly?

Dear Community, I’ve been trying to test out a bidirectional LSTM in Pytorch’s C++ API, but I can’t get it to work. If I define a LSTM-module with the option bidirectional(true), does it automatically create a reverse version of the input sequence and feed that into to reverse LSTM? Does it also automatically concatenate the output tensors into one, that can be directly fed into a dense layer, and how to format it to feed it into one? My Code: auto bilstm = torch::nn::LSTM(torch::nn…

however i am getting an error that output is not a member of ltsm1 (which apparently is a tuple of at::Tensor).

i assume this code must have worked at some point but it doesn’t now. any thoughts?

here is the exactly error

|Error (active)|E0135|class std::tuple<at::Tensor, std::tuple<at::Tensor, at::Tensor>> has no member output|testpyt|W:\bb\git\testpyt\srstst.cpp|84||