Kyubyong / transformer

Watch 103
Star 3.1k
Fork 1.1k

Code
Issues 112
Pull requests 9
Actions
Projects
Security
Insights

Code
Issues
Pull requests
Actions
Projects
Security
Insights

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Pick a username

Email Address

Password

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

112 Open 30 Closed

Author

Filter by author

Label

Filter by label

Use alt + click/return to exclude labels.

Projects

Filter by project

Milestones

Filter by milestone

Assignee

Filter by who’s assigned

Sort

Sort by

Newest Oldest Most commented Least commented Recently updated Least recently updated

Most reactions

Can anyone improve the code to reproduce WMT2014 results?

#161 opened Jul 20, 2020 by whl5902601

How do you connect Convolutional layers to Transformers?

#160 opened Jul 10, 2020 by leersaam

I found a small mistake in the Transformer model.

#158 opened Jul 3, 2020 by rhksgud92

Will there be a TF2.0 version of this project?

#156 opened Jun 12, 2020 by Chinshann

The reason why removed keys masking and query masking?

#155 opened May 25, 2020 by user683

why use dropout in function scaled_dot_product_attention?

#154 opened May 8, 2020 by asmartsnail

what's difference between key masks and query masks?

#153 opened May 2, 2020 by superhg2012

run test error

#152 opened Apr 28, 2020 by anpingbo

Is there a version tf2.0 of this project

#149 opened Jan 14, 2020 by ZhichaoOuyang

Why do you only one vocab? nmt has two languages

#148 opened Dec 29, 2019 by AiCake

'gbk' codec can't decode byte 0x93 in position 978: illegal multibyte sequence and then a bytes-like object is required, not 'str'

#146 opened Dec 10, 2019 by Ailing-Zou

ImportError: DLL load failed: The specified module could not be found. Please help me!

#145 opened Nov 18, 2019 by git31

if tf.reduce_sum(y_hat, 1) == self.token2idx["<pad>"]: break

#144 opened Nov 6, 2019 by gaoxuezhao

train.py, small logic problems

#143 opened Nov 6, 2019 by 915288938lx

for _ in tqdm(range(self.hp.maxlen2))

#142 opened Nov 5, 2019 by tyongguang

key_mask是什么 what is key_mask in modules's mask????

#140 opened Oct 29, 2019 by letmeheard

在moudules中的multi-head attention的实现

#139 opened Oct 28, 2019 by letmeheard

Best performance on iwslt2016 de->en?

#138 opened Oct 23, 2019 by LibertFan

positional_encoding , sin cos has the same input ??

#137 opened Oct 23, 2019 by bsll

Debugging, errore

#136 opened Oct 22, 2019 by kevinwei1975

How to get the output without decoder -input?

#134 opened Oct 14, 2019 by Yuui-Asuka

enc *= self.d_model**0.5 # scale

#132 opened Sep 15, 2019 by qwaiz

Encoding issue

#131 opened Sep 5, 2019 by skumyol

while the code "enc *= self.hp.d_model**0.5 # scale" in model.py

#130 opened Aug 9, 2019 by a982385200

Why 6 blocks of multi-head attention in the encoder and decoder?

#129 opened Jul 31, 2019 by sdxu8888

Previous 1 2 3 4 5 Next

Previous Next

ProTip! Add no:assignee to see everything that’s not assigned.