Comments (3)
avati
commented on July 22, 2024
It's intentional. The "last state" is also a bit ambiguous since we have two of them (bidirectional) but the decoder is uni directional. Also, the attn paper has this architecture (I.e no other connections other than attn)
from nlc.
windweller
commented on July 22, 2024
Hmmmmmmm is it a standard practice? THANK YOU for answering so quickly!
from nlc.
avati
commented on July 22, 2024
I believe so, when you are using attention the decoder starts with 0 hidden state.
from nlc.
Related Issues (17)
- error at line ret_vars = tf.while_loop(cond=beam_cond, body=beam_step, loop_vars=loop_vars, back_prop=False) of function setup_beam HOT 5
- Is the original Theano code available as well? HOT 2
- beam search using DynamicAttentionWrapper
- data url invalid HOT 3
- Unaviable data HOT 4
- no method to create vocab.dat
- Which TF version to use? HOT 1
- The link in the Other Implementations is not working
- Is downscale still used?
- Support PyTorch
- Can't get the data HOT 2
- Meet "disturbing performance" when decode sentence HOT 10
- tar files can not download HOT 3
- how to use lang-8 and CoNLL data? HOT 5
- Exploding gradients for long running task HOT 1
- Inputs to forward/backward RNN are the same 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 nlc.