lsdefine/attention-is-all-you-need-keras

Issues

• Licence

  #38 opened 2 years ago by BDUG
  0

• startup error

  #35 opened 5 years ago by rafaleo
  8

• reshape may not match

  #36 opened 5 years ago by pengxingang
  0

• why get same output with different input?

  #29 opened 5 years ago by maozezhong
  4

• after embedding layer

  #37 opened 5 years ago by lidongxing
  1

• Time series forecasting?

  #32 opened 5 years ago by salihgunduz
  0

• layer norm end of the encoder?

  #33 opened 5 years ago by salihgunduz
  0

• Difference between decode_sequence_fast and decode_sequence_readout?

  #31 opened 5 years ago by renjithamadeus
  0

• Transformer encoder layer instead of Bidirectional LSTM

  #19 opened 6 years ago by Eugen2525
  1

• Using the approach for video encoding.

  #30 opened 5 years ago by kristosh
  0

• Save model to json

  #8 opened 6 years ago by jingyuanz
  2

• the mask of attention

  #28 opened 6 years ago by zjjzyl
  0

• 'nan' loss function when using layer normalization

  #13 opened 6 years ago by McKracken
  1

• Skip-connection in Transformer

  #17 opened 6 years ago by hoangcuong2011
  1

• Using the transformer instead of a simple LSTM layer

  #22 opened 6 years ago by basma-b
  2

• seq2seq confused with shape

  #26 opened 6 years ago by thomasyue
  1

• ScaledDotProductAttention

  #25 opened 6 years ago by t-kong
  0

• the test demo

  #24 opened 6 years ago by chenjun2hao
  0

• dimension in GetSubMask

  #23 opened 6 years ago by ichenjia
  0

• Why wasn't K and V weren't passed from the top encoder to bottom decoder model?

  #21 opened 6 years ago by ichenjia
  0

• K.mean() in computing loss doesn't make any sense.

  #20 opened 6 years ago by mayurnewase
  0

• when i run the pinyin_main.py, get UserWarning like below

  #11 opened 6 years ago by alphanlp
  2

• after run your demo i get a error result like this.why?

  #18 opened 6 years ago by flyboyer
  0

• Issue with attention mask

  #16 opened 6 years ago by LorrinWWW
  2

• Reshape : Dimension mismatch

  #15 opened 6 years ago by shashwattrivedi
  1

• Decoding a sentence give same translation

  #14 opened 6 years ago by mayurnewase
  0

• maybe i find a point should be change

  #12 opened 6 years ago by alphanlp
  2

• How to perform translation?

  #4 opened 6 years ago by lchunleo
  4

• Keras and Tensorflow Versions

  #9 opened 6 years ago by amirveyseh
  1

• pure language model

  #7 opened 6 years ago by XiaoLiuAI
  1

• mask for decoder

  #6 opened 6 years ago by XiaoLiuAI
  6

• Issues with Keras Lambda Layers

  #3 opened 6 years ago by wfmonster
  3

• Is the LayerNormalization class is the transformer needed?

  #5 opened 7 years ago by chaitjo
  2

• MultiHeadAttention

  #2 opened 7 years ago by AMSakhnov
  1

• LayerNormalization

  #1 opened 7 years ago by AMSakhnov
  1