Comments (4)
Is there any chance that you could explain the parameters? I'm having a bit of trouble using them properly. An example would be really helpful.
from etm.
Could this be related to isotropic Gaussian prior over theta logits (as in typical VAEs)?
from etm.
guess as the log-normal's natural, smaller sigma on the Gaussian prior would give your smoother topic proportions.
However this implement seems do not allow for a configurable sigma——it is hard-coded the Gaussian prior to (mu=0,sigma=1) in the encoder.
Could you change that and report here later?
from etm.
@WalterKung you metioned you are using get_theta(normalized_data_batch)
as the way to get the topic dist - is this the correct way?
There are quite a few questions in this repo on how to predict on new data: #4
Thanks in advance!
from etm.
Related Issues (20)
- perform bad on classifiction task HOT 3
- FileNotFoundError: [Errno 2] No such file or directory: 'data/20ng_embeddings.txt'
- How to get the topic vector? HOT 3
- rising KL_theta values
- 代码运行 HOT 1
- Is that true that a lot of repeated topics appear? HOT 7
- Topic Coherence Computation: Division by 45? HOT 2
- How to modify the code to number of topics other than 50? HOT 1
- Validation set loss is being calculated on the Test set.
- Negative coherence on short texts HOT 1
- Run ETM on my own dataset HOT 3
- How to obtain document-topic proportions (the thetas) for each document HOT 3
- a bug in test dataset splitting HOT 1
- evaluate
- Add predictive measure to utils.py
- dataset
- embedding HOT 3
- Confuse about the data loader function HOT 6
- read embedding matrix when not using trained embeddings HOT 1
- args.clip
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 etm.