I got the same error as #109 for the develop branch when use_attention is set to False in sample.py:
RuntimeError: invalid argument 2: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Call
.contiguous() before .view(). at /pytorch/aten/src/THC/generic/THCTensor.cpp:226
However, the line predicted_softmax = function(... in forwrad_step() in model/decoder_rnn.py disappears. I'm not sure how/where to solve this problem.
I got the same error as #109 for the develop branch when
use_attention
is set to False insample.py
:However, the line
predicted_softmax = function(...
in forwrad_step() inmodel/decoder_rnn.py
disappears. I'm not sure how/where to solve this problem.