Pay20Y/SEED

Issues

• Error in beam search

  #52 opened 2 years ago by JamesYang568
  2

• Pretrained model link in onedrive is not working

  #48 opened 2 years ago by gjh8760
  0

• No checkpoint found at 'logs/se_aster/model_best.pth.tar'

  #46 opened 2 years ago by ajoymondal
  0

• Training on other script like Hindi

  #45 opened 2 years ago by ajoymondal
  0

• ASTER has the Bidirectional Decoder, it seems that the code hasn't implement。

  #42 opened 2 years ago by Agiroy4712
  0

• 为什么evaluation时候显存会一直增加

  #35 opened 3 years ago by ZHEGG
  3

• How can I get the training dataset?

  #19 opened 4 years ago by arufuss
  1

• why accuracy, similarity, best is zero?

  #26 opened 3 years ago by vince2003
  4

• word embeddding in an online way

  #36 opened 3 years ago by Bonnie-gift
  0

• If I want to recognize a picture, how can I do it? Do I still want to generate LMDB format? Can you provide a predict interface? Thank you

  #15 opened 4 years ago by DYF-AI
  8

• Training Chinese?

  #27 opened 3 years ago by WeihongM
  1

• initial the hidden layer for decoder input

  #31 opened 3 years ago by chengjackjelly
  0

• can not load checkpoints to evaluate model metrics

  #29 opened 3 years ago by tink2123
  0

• Can the framework adapt to textline recognition?

  #20 opened 4 years ago by AndiezPham
  0

• 解压se_aster.tar 显示文件已经损坏

  #9 opened 4 years ago by wyc2015fq
  6

• pretrain

  #10 opened 4 years ago by nightfuryyy
  2

• I can't decompress the checkpoint you uploaded

  #12 opened 4 years ago by trevor-field
  3

• 你好，请问可以提供一个更简单的测试demo吗

  #5 opened 4 years ago by yyr6661
  6

• attention_recognition_head.py sample y_prev = predicted

  #16 opened 4 years ago by DYF-AI
  0

• Does anyone implement the predict function inference module

  #14 opened 4 years ago by DYF-AI
  0

• Why the results on the readme.md are different from the one shown on the paper?

  #13 opened 4 years ago by thcheung
  0

• evaluate_with_lexicon

  #11 opened 4 years ago by DYF-AI
  2

• How to directly use word embedding from the pre-trained LM during training and inference?

  #7 opened 4 years ago by Fishersponge
  4

• Is it possible to recognize two or more languages using SEED?

  #8 opened 4 years ago by Amagong
  2

• 你好，请问可以提供一个更简单的测试demo吗

  #6 opened 4 years ago by yyr6661
  0

• Have you ever tried to use CTC Loss and replicate the FastText embedding with BERT embedding?

  #4 opened 4 years ago by Shenzheji
  1

• When the code will be released?

  #1 opened 4 years ago by zobeirraisi
  3