search

danieldeutsch / sacrerouge

SacreROUGE is a library dedicated to the use and development of text generation evaluation metrics with an emphasis on summarization.
Apache License 2.0
134 stars 11 forks source link

qaeval setup issue #120

Closed amberhuang01 closed 3 years ago

amberhuang01 commented 3 years ago

Hi Daniel,

I notice this happens occasionally when setting up qaeval. Any idea what might be the issue? Capture

Cheers, Amber

danieldeutsch commented 3 years ago

Hi,

I've occasionally had problems with Google Drive when I download multiple files one after the other. Could you try manually downloading the file from here? It is also stored here, which shouldn't have download issues.

If that fixes the problem, I'll change the Google Drive pointers to the ones hosted on Penn's servers.

saiprabhakar commented 2 years ago

I can confirm that this issue is happening again, I can't find any solution to getting around the "too large to do virus scan" warning from google. I am able to get to the file manually though. Solutions can be:

  1. We can point to your univ server as you mentioned, or
  2. We can display which link to download the files from manually (from the drive) in the error message.

Btw this happens to all the model files that gets downloaded in the qaeval.py. All the zip files are 2.2k containing this:

<!DOCTYPE html><html><head><title>Google Drive - Virus scan warning</title><meta http-equiv="content-type" content="text/html; charset=utf-8"/><style nonce="SiHkFFFhyLik9OfGfbxPNw">/* Copyright 2022 Google Inc. All Rights Reserved. */ .goog-inline-block{position:relative;display:-moz-inline-box;display:inline-block}* html .goog-inline-block,*:first-child+html .goog-inline-block{display:inline}.goog-link-button{position:relative;color:#15c;text-decoration:underline;cursor:pointer}.goog-link-button-disabled{color:#ccc;text-decoration:none;cursor:default}body{color:#222;font:normal 13px/1.4 arial,sans-serif;margin:0}.grecaptcha-badge{visibility:hidden}.uc-main{padding-top:50px;text-align:center}#uc-dl-icon{display:inline-block;margin-top:16px;padding-right:1em;vertical-align:top}#uc-text{display:inline-block;max-width:68ex;text-align:left}.uc-error-caption,.uc-warning-caption{color:#222;font-size:16px}#uc-download-link{text-decoration:none}.uc-name-size a{color:#15c;text-decoration:none}.uc-name-size a:visited{color:#61c;text-decoration:none}.uc-name-size a:active{color:#d14836;text-decoration:none}.uc-footer{color:#777;font-size:11px;padding-bottom:5ex;padding-top:5ex;text-align:center}.uc-footer a{color:#15c}.uc-footer a:visited{color:#61c}.uc-footer a:active{color:#d14836}.uc-footer-divider{color:#ccc;width:100%}</style><link rel="icon" href="null"/></head><body><div class="uc-main"><div id="uc-dl-icon" class="image-container"><div class="drive-sprite-aux-download-file"></div></div><div id="uc-text"><p class="uc-warning-caption">Google Drive can't scan this file for viruses.</p><p class="uc-warning-subcaption"><span class="uc-name-size"><a href="/open?id=193K7v6pjOtuXdlMenQW-RzF6ft-xY2qd">model.tar.gz</a> (387M)</span> is too large for Google to scan for viruses. Would you still like to download this file?</p><form id="downloadForm" action="https://docs.google.com/uc?export=download&amp;id=193K7v6pjOtuXdlMenQW-RzF6ft-xY2qd&amp;confirm=t" method="post"><input type="submit" id="uc-download-link" class="goog-inline-block jfk-button jfk-button-action" value="Download anyway"/></form></div></div><div cl

danieldeutsch commented 2 years ago

Very frustrating! Thanks for letting me know. I wish there was a more reliable way to download files from Google Drive. I will move the models to a different location and update the links.

danieldeutsch commented 2 years ago

I merged the fix. Also, if you have Docker installed or can install it on the machine where the code is running, this implementation of the metric is likely far easier to use since all of the dependencies are isolated within the Docker container.