CyberZHG/keras-bert

Issues

• 'adamwarmup' object has no attribute '_set_hyper'

  #226 opened a year ago by jianlianggao
  0

• load_trained_model_from_checkpoint(config_path,checkpoint_file=checkpoint_path) AttributeError: 'tuple' object has no attribute 'layer'

  #224 opened a year ago by dshwei
  0

• load_trained_model_from_checkpoint(config_path,checkpoint_file=checkpoint_path)

  #225 opened a year ago by dshwei
  0

• module 'tensorflow.compat.v2' has no attribute '__internal__'

  #221 opened 3 years ago by TerryTT2
  1

• Error in getting attention map

  #218 opened 3 years ago by suyashh94
  3

• Concatenate BERT and CNN

  #184 opened 5 years ago by efabb95
  7

• List index out of range for example code

  #210 opened 4 years ago by tama-biro
  2

• AttributeError: module 'keras' has no attribute 'applications'

  #220 opened 3 years ago by vngrv
  5

• Masked LM pre-training

  #219 opened 3 years ago by Khedesh
  1

• Improve Tokenizer for uppercase text

  #217 opened 3 years ago by HariWu1995
  1

• 关于显存巨量占用的疑惑

  #216 opened 3 years ago by Creling
  1

• API reference list

  #214 opened 3 years ago by UCRajkumar
  0

• which version of keras-bert is compatible for tensorflow 1.13?

  #215 opened 4 years ago by vikotse
  2

• The method get_model to get the bert model is right?

  #213 opened 4 years ago by lwyeah
  4

• Keras Bert with character embeddings

  #212 opened 4 years ago by shenron9155
  1

• 在哪里可以找到之前的版本呢？

  #211 opened 4 years ago by Ignoranceemperor
  2

• fine-tuning

  #173 opened 5 years ago by OKtang
  3

• Input sentence for extract_embeddings

  #209 opened 4 years ago by bigredbug47
  1

• 如何提取长度一致的bert词向量？

  #208 opened 4 years ago by 1535966643
  1

• 如何实现在自己的数据上很少的预训练？

  #207 opened 4 years ago by 1535966643
  1

• could you provide an albert loader ?

  #206 opened 4 years ago
  1

• 如何提取fine tune之后模型的字（词）向量？

  #204 opened 4 years ago by JackiyWu
  1

• how can do ner task in keras-bert ? anyone has applied the crf in keras-bert?

  #203 opened 4 years ago
  0

• keras-bert load pre model failed in keras 2.2.4, maybe it is a bug

  #205 opened 4 years ago
  0

• How to transfer character vector into word vector for Chinese texts

  #202 opened 4 years ago by JackiyWu
  1

• How to use bert encoder for continuous values directly? [ No pre-trained model ]

  #201 opened 4 years ago by monk1337
  1

• keras-bert怎么使用多个gpu进行训练？

  #200 opened 4 years ago by jane96
  1

• keras-bert relies on features removed in keras-transformer 0.34.0

  #190 opened 4 years ago by joseph-wakeling-frequenz
  7

• Is this model available to be converted to a .tflite?

  #199 opened 4 years ago by charlie-guan
  1

• NoneType error when fine tuning BERT CLS embeddings directly

  #195 opened 4 years ago by radurevutchi
  2

• error on codec call, no file found

  #194 opened 4 years ago by troy109
  2

• Which version of keras-bert should I download? keras:2.2.4 tf:1.12.0

  #196 opened 4 years ago by AliveHH
  1

• How to save and load Python Keras BERT model to serialize it?

  #197 opened 4 years ago by lxykyle01
  1

• Warning: Don't upgrade to 0.85.0 if you Keras version is less than 2.4

  #193 opened 4 years ago by CyberZHG
  0

• Position embedding for relation extraction

  #192 opened 4 years ago by juanluis17
  1

• Attention maps

  #186 opened 4 years ago by jogonba2
  1

• Training a model from scratch?

  #189 opened 4 years ago by ddofer
  1

• Removed "adapter"

  #191 opened 4 years ago by CyberZHG
  1

• WARNING:tensorflow:Entity

  #187 opened 5 years ago by kulturevulture
  3

• The loss of MLM seems wrong

  #188 opened 5 years ago by showerage
  0

• fine-tuning without using NSP-Dense

  #185 opened 5 years ago by kuroshiba-Ginji
  1

• TypeError in gelu when using different float precision

  #183 opened 5 years ago by f-kretschmer
  1

• Does keras_bert support task with segment id greater than 1?. For example, I want to enter a text with five sentences. So , I want to set segment id in range [0, 4]

  #182 opened 5 years ago by zhongerqiandan
  1

• How to prepare the input of test data?

  #180 opened 5 years ago by houzeyu2683
  1

• Question about the ordering of LayerNorm and Dropout.

  #179 opened 5 years ago by Alkaiddd
  1

• Slow inference on TPU with Colaboratory

  #178 opened 5 years ago by alex4321
  1

• error happens in the next-sentence prediction case

  #177 opened 5 years ago by TiranoGreatLand
  1

• Add words to a pretrained model

  #176 opened 5 years ago by dberma15
  1

• POOL_NSP

  #175 opened 5 years ago by zhangxin9988
  1

• 请问这个包对tensorflow的版本没有要求吗

  #174 opened 5 years ago by duterscmy
  1