Comments (1)
Generally, you should set the sizes so that the output size for the encoder would be as close to 10x10 as possible, this is mentioned in "Implementation Details" under our Experiments section:
"For all datasets, we consider two convolutional layers followed by a fully connected layer in encoder and decoder pathways. While for all convolutional layers, the feature map size is 50 and the kernel
size is about 5×5, the dimension of the embedding subspace is set equal to the number of clusters in each dataset. the dimension of the embedding subspace is set equal to the number of clusters in each dataset. We also pick the proper stride, padding and crop to have an output size of about 10x10 in the second convolutional layer."
Hope this would work for your dataset as well. If there is any other question please let me know :)
from depict.
Related Issues (11)
- about loss function HOT 4
- question about clustering performance on YTF dataset HOT 1
- DEPICT for text classification? HOT 2
- TenorFlow version HOT 1
- Error on update HOT 1
- where is datasets? HOT 1
- Code HOT 1
- some question
- Closed form solution for Q
- how to get the closed solution of Q from fomular (6) to formular (7) in the paper?
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 depict.