da03/Attention-OCR

Issues

• DVAN

  #115 opened 8 months ago by GenieVailfort
  0

• OSS License compatibility question

  #114 opened 2 years ago by Ashley123456789
  0

• training and testing as README introduced, but got a bad accuracy on provided evaluation dataset. What may cause that?

  #113 opened 3 years ago by SharonJin422
  1

• module 'tensorflow.contrib.rnn.python.ops.rnn_cell' has no attribute '_linear'

  #71 opened 7 years ago by dongdql
  15

• when i running the testing code. i am getting the below error

  #79 opened 6 years ago by balajiwix
  7

• generating attention mask based on the SavedModel output

  #112 opened 3 years ago by abucka
  0

• printed mathematical expression recognition

  #111 opened 3 years ago by StephenKyung
  0

• Does it support special ascii characters ?

  #82 opened 6 years ago by hskzlj
  2

• I don't understand the meaning of the code: ord(c) - 97 + 13 if ord(c) > 96 else ord(c) - 48 + 3)

  #102 opened 5 years ago by vinsofts-trientt
  1

• Training is not starting.

  #108 opened 4 years ago by R1234A
  2

• Which loss function is used?

  #110 opened 4 years ago by mrgloom
  0

• Stop writing of events.out.tf.events file during test phase

  #109 opened 5 years ago by pranshu19chester
  1

• Does it support special asscii charater?

  #107 opened 5 years ago by rahuladream
  1

• using multi gpu

  #74 opened 7 years ago by stupiding
  1

• About the running requirement

  #101 opened 5 years ago by EriCongMa
  2

• Output Node

  #78 opened 7 years ago by richeekawasthi
  5

• How to test a model that I choose

  #104 opened 5 years ago by 5thwin
  2

• Cant find sample.txt file.

  #106 opened 5 years ago by hiqmatNisa
  0

• Testing trained images with bad accuracy.

  #105 opened 5 years ago by DLH06
  0

• What dependencies' versions to run this?

  #103 opened 5 years ago by gabrielziegler3
  1

• toy跑不起来

  #97 opened 6 years ago by wyfSunflower
  1

• difference result in difference running test

  #100 opened 5 years ago by hamhochoi
  1

• I want to know where can i get the paper of this code????

  #72 opened 7 years ago by CXY573
  2

• bucket_specs

  #77 opened 7 years ago by cltdevelop
  2

• fine-tune model, train my data

  #87 opened 6 years ago by dongdql
  1

• What is the upper limit of the number of characters recognized by this model?

  #90 opened 6 years ago by XuXuanhui
  1

• testing the result in a single image

  #94 opened 6 years ago by anish9
  1

• which paper is implementd by this repository?"what you get"..or "coarse to fine"

  #99 opened 5 years ago by ganliqiang
  1

• output_node_names

  #95 opened 6 years ago by zmxheart
  1

• cub segmented reduce error invalid configuration argument

  #98 opened 6 years ago by xiaohujecky
  0

• icdar 2003 lexicon

  #96 opened 6 years ago by dpengwen
  1

• Can widechar be supported? Such as chinese and japanese characters.

  #81 opened 6 years ago by hskzlj
  1

• Problem when training on the ICDAR2013 dataset

  #91 opened 6 years ago by jianxiangm
  0

• 100% incorrect

  #89 opened 6 years ago by kspook
  2

• train my data

  #93 opened 6 years ago by kspook
  0

• How to train the model on coco-dataset :D

  #92 opened 6 years ago by DiaaEsmail
  0

• During the execution of "Test and visualize attention results" i am getting error:

  #65 opened 7 years ago by arsalan993
  4

• I switched to tensorflow 0.12.1 and Keras 1.1.1 but now i am getting this error

  #66 opened 7 years ago by arsalan993
  6

• Hi Can I use this code for English letter recognition in an image for different fonts and different font sizes. Can you plz help me. Thanks

  #86 opened 6 years ago by SANDAFERNANDO
  0

• ImportError: cannot import name ContextualZipFile

  #85 opened 6 years ago by famunir
  1

• Issue with GPU training (Windows)

  #84 opened 6 years ago by gagan144
  0

• Uppcase Letter

  #68 opened 7 years ago by MustakMU
  1

• Which paper does it be refered to?

  #83 opened 6 years ago by hskzlj
  1

• How to improve the accuracy?

  #80 opened 6 years ago
  0

• 麻烦问个问题，这个输出的字符个数是怎么对应的呢？

  #76 opened 7 years ago by zhangtao22
  0

• could not create cudnn handle: CUDNN_STATUS_NOT_INITIALIZED

  #75 opened 7 years ago by xiaohujecky
  0

• why do you set TARGET_EMBEDDING_SIZE=10？how do you represent TARGET_VOCAB_SIZE=39 with TARGET_EMBEDDING_SIZE=10？

  #73 opened 7 years ago by zhangtao22
  0

• fixed already

  #70 opened 7 years ago by fengxinjie
  0

• Magic line for visualising attention

  #69 opened 7 years ago by cipri-tom
  0

• Why are there not bias terms in the CNN model?

  #67 opened 7 years ago by MBleeker
  3