issues
search
jadore801120
/
attention-is-all-you-need-pytorch
A PyTorch implementation of the Transformer model in "Attention is All You Need".
MIT License
8.78k
stars
1.97k
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
python preprocess.py -lang_src de -lang_trg en -save_data multi30k_de_en.pkl -share_vocab have problem
#222
yyydfff
opened
2 months ago
1
Create app.py
#221
Esmail-ibraheem
opened
5 months ago
0
Create Embedding.py
#220
Esmail-ibraheem
opened
5 months ago
0
Create transformer.py
#219
Esmail-ibraheem
opened
5 months ago
0
when I run the `python preprocess.py -lang_src de -lang_trg en -share_vocab -save_data m30k_deen_shr.pkl`.I have faced a problem
#218
dapaolufuduizhang
opened
8 months ago
1
About target mask
#217
KimRass
opened
8 months ago
0
Error time to execute 'python preprocess.py -lang_src de -lang_trg en -share_vocab -save_data m30k_deen_shr.pkl' command
#216
evilczy
opened
10 months ago
3
根据requirements.txt安装出错
#215
kmphuang
opened
12 months ago
4
[feat] 添加了一些阅读代码的注释
#214
SS4G
opened
1 year ago
0
why is masking performed again during the inference decoder stage?
#213
Akshay1-6180
opened
1 year ago
0
e
#212
Anton293
closed
1 year ago
0
Possible mistakes in d_k, d_v of MultiheadAttention
#211
SARIHUST
opened
1 year ago
0
May I ask you a question about the "scale_emb_or_prj" parameter?
#210
aitch25
opened
1 year ago
0
Performance Confusion
#209
Zarca
opened
1 year ago
0
Is there some way to convert .chkpt to other form model such as onnx?
#208
warren-wzw
opened
1 year ago
0
Replace NumPy with PyTorch in PositionalEncoding
#207
ZYM66
opened
1 year ago
0
Bump tensorflow from 1.14.0 to 2.11.1
#206
dependabot[bot]
opened
1 year ago
0
In patch_trg, i cant understand why do you change the data shape like that
#205
kwanhoP
opened
1 year ago
3
ValueError: Cell is empty
#204
Kznnd
opened
1 year ago
4
Bump tensorflow from 1.14.0 to 2.9.3
#203
dependabot[bot]
closed
1 year ago
1
preprocess error
#202
zhoup150344
opened
1 year ago
6
what's the intuition behind getting q, k and v from embedding
#201
ShouravBR
closed
2 years ago
1
Bump tensorflow from 1.14.0 to 2.7.2
#200
dependabot[bot]
closed
1 year ago
1
Bump tensorflow from 1.14.0 to 2.6.4
#199
dependabot[bot]
closed
2 years ago
1
OverflowError
#198
Daming-TF
opened
2 years ago
0
download dataset error
#197
qimg412
opened
2 years ago
4
Update requirements.txt
#196
yunhuang1241
closed
2 years ago
0
My question
#195
Messiz
opened
2 years ago
2
TranslationDataset is now deprecated in torchtext
#194
imkzh
opened
2 years ago
2
CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)`
#193
lisp2047
opened
2 years ago
1
Bump tensorflow from 1.14.0 to 2.5.3
#192
dependabot[bot]
closed
2 years ago
1
Beam search torch.log
#191
actforjason
opened
2 years ago
0
@SeoroMin
#190
SeoroMin
opened
2 years ago
1
removed a singleton-comparison pitfall
#189
NaelsonDouglas
opened
2 years ago
0
learning rate update before optimizer.step()
#188
AlbertiPot
closed
3 years ago
1
why PEpos+k can be represented as a linear function of PEpos?
#187
myrainbowandsky
opened
3 years ago
0
Confusion regarding embedding space
#186
IamAdiSri
opened
3 years ago
2
some problem
#185
zhLia
opened
3 years ago
3
Bump tensorflow from 1.14.0 to 2.5.1
#184
dependabot[bot]
closed
2 years ago
1
变量名能不能起得好读一点?
#183
Xelawk
closed
2 years ago
0
Attention value is strange
#182
YPatrickW
opened
3 years ago
1
test error
#181
LonelyPlanetIoT
opened
3 years ago
2
[fix]: remove-extra-arg
#180
yinchimaoliang
opened
3 years ago
0
MultiHeadAttention input shape
#179
Superklez
opened
3 years ago
0
Input sequence dimensions of MultiHeadAttention
#178
Superklez
closed
3 years ago
1
Incorrect implementation?
#177
weilueluo
closed
3 years ago
2
The results of the translate function.
#176
zshyang
opened
3 years ago
4
If we change the code in Model.py like this, the convergence speed would be faster.
#175
Sry2016
opened
3 years ago
1
why dropping last example with patch_src&patch_trg function @train.py
#174
pluspluswu
opened
3 years ago
1
How to deal with the UNK_TOKEN?
#173
lhy2749
opened
3 years ago
0
Next