search

alinealinealine / GPT-Pilot

Fine-tune GPT model
0 stars 0 forks source link

FIG:16 PDF files that are not read in yet: need to convert to word and find the relevant sections (tagging if needed) #6

Open alinealinealine opened 1 year ago

alinealinealine commented 1 year ago

@gauravrpjain I managed to use python converting successfully, hopefully, to identify and convert all of them to docx tonight. will keep you posted.

alinealinealine commented 1 year ago

The projects with only pdf board paper are identified using script: https://github.com/alinealinealine/GPT-Pilot/blob/main/src/pdf_docx_fig.R and these pdf board papers are converted to docx using the script: https://github.com/alinealinealine/GPT-Pilot/blob/main/src/pdf_docx_fig.py

Overall: 349 projects scripted for FIG using the latest code.