Eclipse Picasso - A Free Open-Source Visualizer for Convolutional Neural Networks

Warning

This projects has been archived!

The Picasso visualizer tool is an open-source deep neural network visualization tool. It can be used to understand neural nets' decisions in the field of computer vision.

The scope of Picasso is definded as per below:

Provide a web framework to connect DNNs trained in various frameworks (currently Tensorflow and Keras) to visualizations
Handle upload of inputs (images)
Provide some useful default visualizations, and a frontend for navigating them:
- Class probabilities
- Occlusion of parts of objects (Zeiler, 2014)
- Saliency maps (Simonyan, 2014)

Additionally, we strive for:

Ease of working with new models
Ease of adding new visualizations

This is not a program for monitoring evaluation metrics or visualizating the computational graph itself. Thus, functionality like that provided in Tensorboard is out-of-scope.

Basics

Repositories

Repo	Commits	Reviews	Issues

This project has no activity.

The EMO oversees the lifecycle of Eclipse projects, trademark and IP management, and provides a governance framework and recommendations on open source best practices.

See the project’s PMI page at https://projects.eclipse.org/projects/technology.picasso

Releases

IP Lab requests

Security related information is not yet available for this project. In order to gather such information automatically, Self Service of GitHub resources needs to be enabled for this project.