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

atpaino / deep-text-corrector

Deep learning models trained to correct input errors in short, message-like text

Apache License 2.0

1.23k stars 266 forks source link

Shape (10, ?, 1, 512) must have rank 0 #31

Open Sarathy-R opened 3 years ago

Sarathy-R commented 3 years ago

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)