Shape error during LSTM forward pass
anirudhs96 opened this issue · comments
Anirudh Suresh commented
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