This repository contains the demo code for the CVPR'17 paper Network Dissection: Quantifying Interpretability of Deep Visual Representations. You can use this code with naive Caffe, with matcaffe and pycaffe compiled. We also provide a PyTorch wrapper to apply NetDissect to probe networks in PyTorch format.

GAN Dissection is a way to inspect the internal representations of a generative adversarial network (GAN) to understand how internal units align with human-interpretable concepts. It is part of NetDissect.

Given a grayscale photograph as input, this paper attacks the problem of hallucinating a plausible color version of the photograph. This problem is clearly underconstrained, so previous approaches have either relied on significant user interaction or resulted in desaturated colorizations. We propose a fully automatic approach that produces vibrant and realistic colorizations. We embrace the underlying uncertainty of the problem by posing it as a classification task and use class-rebalancing at training time to increase the diversity of colors in the result.

Lyra is an interactive environment that enables custom visualization design without writing any code. Graphical “marks” can be bound to data fields using property drop zones; dynamically positioned using connectors; and directly moved, rotated, and resized using handles. Lyra also provides a data pipeline interface for iterative visual specification of data transformations and layout algorithms. Lyra is more expressive than interactive systems like Tableau, allowing designers to create custom visualizations comparable to hand-coded visualizations built with D3 or Processing.