search

adymaharana / VLCStoryGan

Official code repository for the EMNLP 2021 paper
MIT License
26 stars 5 forks source link

Parser error #3

Open AhmedEwis opened 2 years ago

AhmedEwis commented 2 years ago

Hello.

I am getting this below error:

NameError: name 'parser' is not defined

adymaharana commented 2 years ago

Hi there,

I am continuing the issue from #2 here. Could you please elaborate on the error you are facing? I just reran the parse.py script with the required arguments and it is working. Please be advised that the commands are for spAcy version 2.x. For other spAcy versions, the package benepar has the following recommendation:

import benepar, spacy nlp = spacy.load('en_core_web_md') if spacy.version.startswith('2'): nlp.add_pipe(benepar.BeneparComponent("benepar_en3")) else: nlp.add_pipe("benepar", config={"model": "benepar_en3"})

See more here.

AhmedEwis commented 2 years ago

Hello Ady.

Thanks for your reply.

I have read the instructions and I am stuck in this step:

To extract parses for PororoSV: python parse.py --dataset pororo --data_dir

what do you mean by the required arguments for parse.py script? is there anything I have to change?

adymaharana commented 2 years ago

The parser.py script has been written to read captions for the PororoSV dataset. It needs two arguments: the dataset name and the path to data directory. Are you using this script for PororoSV or some other dataset? If using for Pororo, you need to download the zipped directory available here, unzip it, and add the path to the directory as a command line argument. If you're using the script for a different dataset, you will need to make some changes. If you have already made some changes and are facing error there, I can be of more help if you could share the modified script. Thank you.