Comments (3)
LifangD
commented on May 18, 2024
1
Because of the parametric way, I think multiple projection to lower dimension is equivalent to "first project then split" , e.g: 100d ->100d->split(25d * 4), the number of parameters is 100 * 100; multiple projection(4times): 100d->25d, the number of parameters is 100*25 *4. And "split and concat " looks more elegant. By the way, I also tried such two methods in my own experiments and found no difference on final performance. @ty5491003
from transformer.
ty5491003
commented on May 18, 2024
I noted you closed this issue, do you have the answer? I have the same question.
@LifangD thx.
from transformer.
ty5491003
commented on May 18, 2024
I got it, thx /:laughing:/
from transformer.
Related Issues (20)
- how to understand decoder_inputs have ["<s>"] while y_hat, y or x don't have ["<s>"] HOT 1
- How do you connect Convolutional layers to Transformers?
- Can anyone improve the code to reproduce WMT2014 results?
- Why to remove query masking?
- something about Model.py , in which something wrong between encoder and decoder HOT 2
- 自己学习率没有调节好 HOT 4
- 无 HOT 1
- Error! excuting the train.py
- Question：multihead_attention()’s output and ff()‘s output need dropout？
- Is value must be linear transformed at multi-head attention?
- request for dataset HOT 1
- 请问下，有TF2.X有实现的代码吗
- There is a problem when I execute the command bash download.sh HOT 2
- train error
- 多头问题的实现推导不太理解
- 您好，我想请问论文里bleu和meteor的数据是怎么得到的？我运行test.py文件，出现的是很多句子。
- 数据集链接失效了 HOT 3
- tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[27,100] = 100 is not in [0, 100) HOT 2
- About the query_mask
- about spm.SentencePieceTrainer.Train(train) HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from transformer.