CyberZHG/keras-self-attention

Issues

• "tuple index out of range" when using self attention layer in imdb dataset

  #24 opened 5 years ago by Larry955
  7

• Which paper does Local Attention refer to？

  #62 opened 3 years ago by Fatigerrr
  1

• Issue with tensorflow-gpu

  #65 opened 2 years ago by kerighan
  1

• Self-attention before BiLSTM

  #64 opened 3 years ago by katekats
  0

• Question about the SeqSelfAttention.

  #63 opened 3 years ago by katekats
  0

• load attention model

  #55 opened 4 years ago by jalalmzh
  2

• How to add `keras-self-attention` to a seq2seq model

  #60 opened 3 years ago by uttamdhakal
  1

• Issue with importing SeqSelfAttention

  #61 opened 3 years ago by katekats
  4

• Error with flatten

  #58 opened 3 years ago by sandeepbhutani304
  6

• Error when loading model (.h5 file) in Java (deeplearning 4j)

  #53 opened 3 years ago by cuongnguyengit
  3

• TestResidualScaledDotProductAttention错误

  #59 opened 3 years ago by Yesgo1220
  1

• Visualize attention results

  #57 opened 3 years ago by sandeepbhutani304
  3

• Getting Error :Invalid argument: Incompatible shapes

  #51 opened 3 years ago by jasmeet12
  2

• local attention parameter

  #54 opened 3 years ago by farhantandia
  1

• Error when load model

  #52 opened 3 years ago by raspatiocan
  1

• visualizing attention weights

  #50 opened 3 years ago by henokDES
  1

• module 'keras' has no attribute 'applications'

  #56 opened 3 years ago by zlindaz2411
  3

• ValueError: Shapes (None, 3) and (None, 50, 3) are incompatible

  #46 opened 4 years ago by Keramatfar
  2

• what's the difference between SeqWeightedAttention and SeqSelfAttention?

  #49 opened 4 years ago by qianwang102
  1

• Which paper does Multiplicative Attention refer to?

  #48 opened 4 years ago by hongjianyuan
  0

• Which paper does Multiplicative Attention refer to?

  #47 opened 4 years ago by hongjianyuan
  0

• Attention to 2D input

  #45 opened 4 years ago by raghavgurbaxani
  1

• keras-self-attention Paper ?

  #44 opened 4 years ago by mohamedScikitLearn
  1

• reference for multiplicative attention

  #43 opened 4 years ago by indi297
  1

• Compatibility with Tensorflow 2.0

  #38 opened 5 years ago by mohamedScikitLearn
  10

• Masking implementation

  #41 opened 4 years ago by tomasmenezes
  1

• Supporting convolutional LSTM?

  #40 opened 5 years ago by adanacademic
  1

• tf.keras.layers.Attention？

  #39 opened 5 years ago by yuanjie-ai
  1

• Tensorflow 2.0 Compatibility

  #31 opened 5 years ago by SamanehSaadat
  2

• ScaledDotProductAttention not returning attention properly.

  #37 opened 5 years ago by dioptx
  1

• AttributeError: module 'tensorflow' has no attribute 'get_default_graph' while using 'SeqSelfAttention'

  #33 opened 5 years ago by octolis
  3

• IndexError, tuple index out of range

  #36 opened 5 years ago by elsheikh21
  1

• "Tuple index out of range" when using SeqWeightedAttention

  #25 opened 5 years ago by Hellisotherpeople
  4

• Attention Weights

  #32 opened 5 years ago by BigMasonFang
  1

• Examples for a basic NMT model?

  #35 opened 5 years ago by user06039
  1

• Is it only for sequential data?

  #34 opened 5 years ago by xuzhang5788
  1

• error in building my bi-lstm with attention, help

  #22 opened 5 years ago by denglizong
  3

• keras-self-attention for time series forecasting

  #30 opened 5 years ago by rahimikia
  0

• __init__() missing 3 required positional arguments: 'node_def', 'op', and 'message'

  #29 opened 5 years ago by dingtine
  1

• 在加法模式和乘法模式里，一个加 ba,一个加ba[0]

  #28 opened 5 years ago by xugaoliang
  1

• 初始化器写成了正则化器

  #27 opened 5 years ago by xugaoliang
  2

• results[2]应该改为results[0]

  #26 opened 5 years ago by xugaoliang
  2

• 您好请问您这个对应的论文是那一篇。

  #23 opened 5 years ago by dashujuzha
  2

• The gradient is missing sometimes

  #20 opened 5 years ago by SUNBERG010
  2

• how to apply Attention between two LSTM layers?

  #21 opened 5 years ago by shreeeyash
  0

• T

  #19 opened 5 years ago by SUNBERG010
  0

• Compatibility with `tf.keras`

  #18 opened 6 years ago by nshaud
  2

• Error (with multiplication?)

  #16 opened 6 years ago by GadL
  1

• Scaled Dot Product attention error

  #14 opened 6 years ago by AliOsm
  3

• can this be used in a seq 2 seq task?

  #15 opened 6 years ago by cristianmtr
  2