Training data query

[riddhirdasani]

trafficstars

Hello Shashi, I am unable to understand why do we need these three directories and what role do they play in training? 1. preprocessed_data_directory 2. gold_summary_directory 3. doc_sentence_directory. Can you provide little more insights of these three.? When I was trying , one epoch has already finished and then this error appeared.

[shashiongithub]

For training you only need (1). (2) is used to estimate ROUGE scores. (1) and (3) is used during decoding. What error do you get after the first epoch?

[riddhirdasani]

File "/home/beast/riddhi/main/data_utils.py", line 116, in process_predictions_rankedtopthree docsents = open(sent_filename).readlines() FileNotFoundError: [Errno 2] No such file or directory: '/home/beast/riddhi/main/JP_herman/cnn/validation-sent/8f6b39e6c63b0ae3546cdfeb8209693f292b060e.summary.final.org_sents'

sent_filename which got generated in line 115 by using FLAGS.doc_sentence_directory, cannot be opened in line 116. I just presumed and made directory , what exactly should be there in this directory?

[shashiongithub]

It should point to 3) doc_sentence_directory directory.

[riddhirdasani]

Yes and what should be there, from where can I get it?

[shashiongithub]

Please check: https://github.com/shashiongithub/sidenet/issues/2