Comments (1)
You are right about my current implementation, and I agree it will increase diversity. Iām bit afraid that adding randomness in latent space may delude the latent trajectory, one has to carefully choose random samples by checking its distance to its Gaussian mean.
from optimus.
Related Issues (20)
- Question: why this choice of BERT and GPT2? HOT 2
- DailyDialogue dataset HOT 4
- demo website
- how about using gpt2 as encoder and decoder? HOT 1
- Demo webset is dead HOT 2
- One question about the decoder of vae
- Missing requirements file HOT 1
- About Pre-training on the Wikipedia dataset HOT 2
- GPT2ForLatentConnector HOT 2
- Hyper-parameters to reproduce language modelling results
- Chinese Pretrained Model
- Format of input files split by NLTK used as input for preprocessing: "wikipedia.segmented.nltk.split.seq64.0.json"
- issue about reproducing results on SNLI dataset HOT 1
- Question about mutual information
- How to run the Label-Conditional Text Generation experiment on YELP dataset
- Seems like checkpoints for {beta=0, beta=0.5} latent size=32 are the same checkpoints
- How about the reconstruction BLEU of AE and VAE?
- Dataset access denied HOT 1
- Pre-trained model download is not available. HOT 4
- The loss_encoder and loss_lsc in cara.py cancel each other
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
š 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. ššš
-
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 ā¤ļø Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from optimus.