Eclipse Picasso - A free open-source visualizer for Convolutional Neural Networks

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.