FudanVI/FudanOCR

Issues

• How to download pretrained model without Baidu account?

  #99 opened 14 days ago by abghaky
  2

• Could u release the code of EAFormer, thanks!

  #98 opened 14 days ago by NTUYWANG103
  1

• 是否有HWDB 1.0-1.2 的lmdb数据集

  #94 opened 6 months ago by Skywalker-Harrison
  1

• Any code about 'Towards Accurate Video Text Spotting with Text-wise Semantic Reasoning'?

  #97 opened 3 months ago by P1ng3609
  0

• 字典里面的字符是不是不够啊？除了没有逗号，有时候会出现字典里没有这个汉字。

  #93 opened 6 months ago by zhouyupeng973
  4

• Question about CCR-CLIP experiment and code

  #92 opened 6 months ago by ZZXF11
  4

• For text-focused-transforemer, which version of MMCV and MMSeg should i choose?

  #96 opened 4 months ago by Chiangsonw
  1

• train.py在计算loss有个小错误

  #76 opened 10 months ago by bad-meets-joke
  2

• Please guide, how to perform inference on a single image and get the improved output image?

  #95 opened 5 months ago by Arslan-Mehmood1
  0

• lmdb can not find my file.

  #90 opened 6 months ago by zhouyupeng973
  2

• 关于Chinese-CLIP复现中的几点疑惑，期待答复！

  #91 opened 6 months ago by kongyan66
  0

• train.py的坑：容易误删已训练模型

  #89 opened 7 months ago by YourSonnet18
  2

• Fix link for Baidu download in text-focused-Transformers/

  #88 opened 7 months ago by lramming
  0

• CCR-CLIP使用印刷字体进行增强

  #87 opened 7 months ago by AnatoleWang
  1

• inference of orientation-independent-CTR ?

  #86 opened 8 months ago by a01163125
  0

• About CCR-CLIP pretrained

  #85 opened 8 months ago by ra890927
  1

• CCR-CLIP pretraining

  #84 opened 9 months ago by gyao15
  2

• 请问在竖直文本识别那篇论文中，有没有提供预训练模型呢

  #81 opened 10 months ago by bucaiLi
  2

• How to extract only image after super resolution?

  #83 opened 10 months ago by dvhphuc
  0

• How to download VCTR dataset?

  #82 opened 10 months ago by qiaoliang6
  2

• 请问text-focused-Transformers model和datasets如何下载

  #79 opened 10 months ago by rzgbw
  1

• 关于CCR-CLIP

  #77 opened 10 months ago by wu-yz
  1

• VCTR dataset read error

  #80 opened 10 months ago by Apostatee
  0

• 数据集请求

  #78 opened a year ago by leez20
  2

• Question about CLIP-like pre-training in image-ids-CTR

  #75 opened a year ago by ZZXF11
  1

• transformer预训练模型是如何训练的？

  #61 opened 2 years ago by dzyanshan
  1

• 印刷艺术字有几张图片张量全是1

  #74 opened a year ago by handeben
  0

• Why can't I reproduce the results in stroke-level-decomposition?

  #63 opened 2 years ago by yeahQing
  7

• lmdb格式数据集转换代码可以提供一下嘛?

  #57 opened 2 years ago by yeahQing
  6

• 为什么images_hr的图片会比images_sr更加清晰？

  #73 opened a year ago by zhangqiqi1228
  0

• Test problems about Recognizer Aster/关于使用ASTER来测试的问题

  #70 opened 2 years ago by Uxasxie
  2

• MSELoss is used in code, but Cosine similarity metric is used in paper?

  #62 opened a year ago by yeahQing
  0

• An code error about acpm matching process in character-profile-matching.

  #69 opened a year ago by yeahQing
  0

• 训练过程中的 attention_loss和recognition_loss一直都是-1正常吗？

  #72 opened a year ago by Everythingismetaphor
  0

• 单张图像生成超分辨率图（help）

  #71 opened 2 years ago by qilong-zhang
  0

• 中文文本超分辨率

  #55 opened 2 years ago by Winnie202
  1

• STT中的transformer预训练问题？

  #68 opened 2 years ago by 1093586578
  0

• 关于stroke-level-decomposition代码的问题

  #67 opened 2 years ago by WangXuCh
  0

• What is the size of image?

  #66 opened 2 years ago by 3umin
  3

• How is the support sample generated in Stroke-level-decomposition?

  #65 opened 2 years ago by cptbtptp125
  1

• How is the.pkl file generated in print_font_template in Stroke-level-decomposition?

  #64 opened 2 years ago by cptbtptp125
  0

• information about license

  #60 opened 2 years ago by leocd91
  0

• same problem:why i cant load the pretrain model to continue training

  #59 opened 2 years ago by Uxasxie
  0

• Chinese dataset question

  #49 opened 2 years ago by Winnie202
  1

• 你好，请问scene-text-telescope的log文件能分享吗

  #56 opened 2 years ago by Uxasxie
  0

• How can I eveluate TBSRN on Aster and Moran?

  #54 opened 2 years ago by MinghaoFu
  0

• test 准确率一直为0

  #52 opened 2 years ago by Winnie202
  0

• test准确率一直为0

  #53 opened 2 years ago by Winnie202
  0

• stroke-level-decomposition dataset problem

  #51 opened 2 years ago by cptbtptp125
  0

• A question about the TextZoom Dataset

  #50 opened 2 years ago by MingyuLau
  0