Comments (4)
I think you need to change --word_embedding_length to the dimension of your new embeddings, as for the --hidden_units_num, you can set it to whatever you want to try. There's a fcn layer converting input embedding of size --word_embedding_length to the hidden states of size --hidden_units_num
from disan.
@aimiyu Thanks for your answering, and you are correct.
from disan.
Gotcha! Thanks for replying. I wonder if there any relation between these two parameters or not? I now understand it is independent parameter but is there any best practice i.e. if I have 50d do I still need to have 300 hidden layers or they should be less and Vice versa.
from disan.
Actually, I don’t know any dependence between them. I’m just accustomed to follow previous work’s settings
from disan.
Related Issues (20)
- Using tree structure not raw text in SNLI dataset HOT 3
- Perplexity HOT 6
- experiments on MSRP HOT 3
- Word Embedding tune HOT 6
- tensorboard graph did not show anything HOT 1
- report error in line94 snli_main.py
- How to process new data? What should be the format of input file HOT 3
- what to do about the var rep_mask in the disan.py? HOT 10
- Can you take examples for the Fast-Disa.py?
- input to fast-disan.py
- SICK dataset
- Excuse me, where is the code for visual attention weight?
- SST data process HOT 1
- question about config parameter "only_sentence" HOT 3
- Where is the trained model stored?
- How can I generate predictions for my non-SNLI dataset using SNLI-DiSAN model? HOT 1
- It seems that without a pretrained embedding input, the results become worse HOT 2
- The net seems use lstm HOT 2
- About the structure of the code 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 disan.