Shape error during LSTM forward pass

IntelLabs / bayesian-torch

A library for Bayesian neural network layers and uncertainty estimation in Deep Learning extending the core of PyTorch

BSD 3-Clause "New" or "Revised" License

518 stars 72 forks source link

Shape error during LSTM forward pass #1

Closed anirudhs96 closed 3 years ago

anirudhs96 commented 3 years ago

I'm seeing this shape error during forward pass of Bayesian LSTM. Is there an issue at my end? Can you please upload an example script for LSTMs for testing?

  File "XXXX/python3.6/site-packages/bayesian_torch/layers/variational_layers/rnn_variational.py", line 131, in forward
    c_t = f_t * c_t + i_t * g_t
RuntimeError: The size of tensor a (512) must match the size of tensor b (128) at non-singleton dimension 2