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

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

A Keras+TensorFlow Implementation of the Transformer: Attention Is All You Need

702 stars 188 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Licence

#38 BDUG opened 1 year ago
0
after embedding layer

#37 lidongxing opened 4 years ago
1
reshape may not match

#36 pengxingang opened 4 years ago
0
startup error

#35 rafaleo opened 4 years ago
8
Update transformer.py

#34 zhanjunlang closed 2 years ago
0
layer norm end of the encoder?

#33 salihgunduz opened 4 years ago
0
Time series forecasting?

#32 salihgunduz closed 4 years ago
0
Difference between decode_sequence_fast and decode_sequence_readout?

#31 renjithamadeus opened 4 years ago
0
Using the approach for video encoding.

#30 kristosh opened 4 years ago
0
why get same output with different input?

#29 maozezhong opened 5 years ago
4
the mask of attention

#28 zjjzyl opened 5 years ago
0
seq2seq confused with shape

#26 thomasyue closed 5 years ago
1
ScaledDotProductAttention

#25 t-kong opened 5 years ago
0
the test demo

#24 chenjun2hao opened 5 years ago
0
dimension in GetSubMask

#23 ichenjia opened 5 years ago
0
Using the transformer instead of a simple LSTM layer

#22 basma-b opened 5 years ago
2
Why wasn't K and V weren't passed from the top encoder to bottom decoder model?

#21 ichenjia closed 5 years ago
0
K.mean() in computing loss doesn't make any sense.

#20 mayurnewase opened 5 years ago
0
Transformer encoder layer instead of Bidirectional LSTM

#19 Eugen2525 opened 5 years ago
1
after run your demo i get a error result like this.why?

#18 flyboyer opened 5 years ago
0
Skip-connection in Transformer

#17 hoangcuong2011 opened 5 years ago
1
Issue with attention mask

#16 LorrinWWW closed 5 years ago
2
Reshape : Dimension mismatch

#15 shashwattrivedi closed 5 years ago
1
Decoding a sentence give same translation

#14 mayurnewase opened 5 years ago
0
'nan' loss function when using layer normalization

#13 McKracken opened 5 years ago
1
maybe i find a point should be change

#12 alphanlp opened 5 years ago
2
when i run the pinyin_main.py, get UserWarning like below

#11 alphanlp opened 5 years ago
2
embedding dropout

#10 JulesGM closed 5 years ago
0
Keras and Tensorflow Versions

#9 amirveyseh opened 5 years ago
1
Save model to json

#8 jingyuanz opened 6 years ago
2
pure language model

#7 XiaoLiuAI opened 6 years ago
1
mask for decoder

#6 XiaoLiuAI closed 6 years ago
6
Is the LayerNormalization class is the transformer needed?

#5 chaitjo closed 6 years ago
2
How to perform translation?

#4 lchunleo closed 5 years ago
4
Issues with Keras Lambda Layers

#3 wfmonster closed 6 years ago
3
MultiHeadAttention

#2 AMSakhnov closed 6 years ago
1
LayerNormalization

#1 AMSakhnov closed 6 years ago
1