jayparks transformer issues

jayparks / transformer

A Pytorch Implementation of "Attention is All You Need" and "Weighted Transformer Network for Machine Translation"

543 stars 122 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

This is a piece of junk code don't look at it anymore！

#18 Ant0082 opened 1 year ago
0
Can't run the whole project

#17 MsTao-68 opened 2 years ago
0
**difference** between paper and your code

#16 yuanyihan opened 3 years ago
0
I don`t want to debug...

#15 laichengen opened 3 years ago
0
how to generate train, src, tgt,or how to run the code

#14 wangyy161 opened 3 years ago
2
Some error in position encoding

#13 HN123-123 opened 3 years ago
0
why dose this repo use the earlier labels as the input of Decoder?

#12 qq563902455 opened 3 years ago
0
improved transformer modules

#11 Sa-asus opened 3 years ago
0
error in Linear

#10 baoxin1100 opened 4 years ago
3
Thanks for your sharing, but I have a question that how to use it ?

#9 zhhhzhang opened 4 years ago
2
Thanks for your sharing, but I have a question that how to use it ?

#8 hellokevin96 opened 5 years ago
0
How to keep constrains of sum(k)=1 and sum(α)=1?

#7 sunzewei2715 opened 5 years ago
0
How to add some functionalities to this code?

#6 liperrino opened 5 years ago
1
TypeError: on __init()__ missing require positional argument: out_features

#5 liperrino opened 5 years ago
3
only integer tensors of a single element can be converted to an index

#4 ShangYuming opened 5 years ago
0
Usage of this repository

#3 liperrino opened 5 years ago
0
RuntimeError: Expected object of type torch.cuda.LongTensor but found type torch.LongTensor for argument #3 'index'

#2 GITJolly opened 5 years ago
2
ModuleNotFoundError: No module named 'torchtext'

#1 pemywei opened 5 years ago
1

jayparks / transformer

issues

This is a piece of junk code don't look at it anymore！

Can't run the whole project

difference between paper and your code

I don`t want to debug...

how to generate train, src, tgt,or how to run the code

Some error in position encoding

why dose this repo use the earlier labels as the input of Decoder?

improved transformer modules

error in Linear

Thanks for your sharing, but I have a question that how to use it ?

Thanks for your sharing, but I have a question that how to use it ?

How to keep constrains of sum(k)=1 and sum(α)=1?

How to add some functionalities to this code?

TypeError: on init() missing require positional argument: out_features

only integer tensors of a single element can be converted to an index

Usage of this repository

RuntimeError: Expected object of type torch.cuda.LongTensor but found type torch.LongTensor for argument #3 'index'

ModuleNotFoundError: No module named 'torchtext'