Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

PCA/TSNE for embedding visualisation #252

Closed
alexcoca opened this issue Oct 17, 2018 · 1 comment
Closed

PCA/TSNE for embedding visualisation #252

alexcoca opened this issue Oct 17, 2018 · 1 comment

Comments

@alexcoca
Copy link

Hey,

I was wondering how to use the SummaryWriter().add_embedding method to visualise neural network representations. I read the docs and saw that all that is necessary to do is to pass a N x D tensor to the function and optionally a list of N labels. Assuming, D>> 3, how can I control which dimensionality reduction method is used to display the plots and its hyperparameters? There seems to be no obvious way to control these through the interface. I was hoping to find out more about this here but the link to the website appears to be broken.

Alex

@lanpa
Copy link
Owner

lanpa commented Oct 17, 2018

That is moved to: https://github.com/lanpa/tensorboardX/blob/master/examples/demo_embedding.py

You have to control the reduction method on the web interface.

@lanpa lanpa closed this as completed in 2a11efa Oct 17, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants