train.py TypeError
alexanderhanboli opened this issue · comments
Alexander Hanbo Li commented
TypeError: Expected int32, got list containing Tensors of type '_Message' instead.
It traced back to the line:
line 168, in build_model _, (c, h) = lstm_cell(inputs=tf.concat(1, [x[:,t,:], context]), state=[c, h])
Alexander Hughes commented
@AlexanderYogurt did you resolve this? I have run into the same issue. And cannot figure out a solution.
Laura Lopez Fuentes commented
You should change that line to:
(c, h) = lstm_cell(inputs=tf.concat([x[:,t,:], context], 1), state=[c, h])
or
(c, h) = lstm_cell(inputs=tf.concat(axis=1, [x[:,t,:], context]), state=[c, h])
EMCL commented
Post full error report