Only <UNK> tokens are generated in summary.In data.py file, when we read the vocab file, it only takes the 'rb' mode not work with 'r'.

[JenuTandel]

[nozomi233]

Excuse me,Have you solve the problem?when i run "python run_summarization.py --mode=decode --data_path=/chunked/val_ --vocab_path=/vocab --log_root=*****/a/log/directory --exp_name=myexperiment" ,the generated summary is consist of UNK,could you please do me a favor?