joanrod/ocr-vqgan

Issues

• Una pregunta sobre la Sección 4.2

  #12 opened 3 months ago by qiqigit
  0

• `resolution` and `size` in train config

  #11 opened 4 months ago by sakemin
  0

• Inference mode

  #10 opened 10 months ago by Serzhanov
  0

• `paper2fig_train.json` and `paper2fig_test.json` not included in `Paper2Fig100k.tar.gz`

  #9 opened a year ago by potamides
  3

• about text to image

  #7 opened a year ago by canghao
  6

• Stuck on Downloading ocr_craft Model During Training

  #8 opened a year ago by qingpowuwu
  1

• Questions about test phase~

  #1 opened 2 years ago by wujiekd
  1

• vqgan result

  #6 opened 2 years ago by Winnie202
  2

• paper2figure dataset can‘t download

  #5 opened 2 years ago by songge25
  1

• Assertion error in losses/vqperceptual.py

  #4 opened 2 years ago by Wonder1905
  2

• Transferring ocr-vqgan to an image super-resolution task for text within images?

  #3 opened 2 years ago by songkq
  3

• Questions about the pre-training model

  #2 opened 2 years ago by wujiekd
  2