atpaino/deep-text-corrector

Shape (10, ?, 1, 512) must have rank 0

Sarathy-R opened this issue · 0 comments

I am getting this error:
In Seq2seq
828 top_states = [array_ops.reshape(e, [-1, 1, cell.output_size])
829 for e in encoder_outputs]
--> 830 attention_states = array_ops.concat(1, top_states)