ruthcfong

perturb_explanations

Code for Fong and Vedaldi 2017, "Interpretable Explanations of Black Boxes by Meaningful Perturbation"

pointing_game

pytorch_models

interactive_overlay

TorchRay

Understanding Deep Networks via Extremal Perturbations and Smooth Masks

imagenet_localization

ruthcfong.github.io

pytorch_cifar

95.16% on CIFAR10 with PyTorch

pytorch_workflow

amplifyapp

Amplify Console CI / CD Demo

bag-of-local-features-models

Pretrained bag-of-local-features neural networks

bam

chineseinflow-javascript

Practice Chinese characters

CUB200-2011

The collection of 80*80-pixels bird-images from cub200-2011 dataset.

cutout

2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552

dropblock

Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.

excitationbp

Visualizing how deep networks make decisions

hydra

Hydra is a framework for elegantly configuring complex applications

lucid

A collection of infrastructure and tools for research in neural network interpretability.

mAP

mean Average Precision - This code evaluates the performance of your neural net for object recognition.

MichiGAN

MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing (SIGGRAPH 2020)

NetDissect-Lite

Light version of Network Dissection for Quantifying Interpretability of Networks

nifty-web-apps

Build a web app for any programming assignment.

partialconv

A New Padding Scheme: Partial Convolution based Padding

perturb_improvements

post--example

Example Distill article repository—clone, rename, start writing!

ProtoPNet

This code package implements the prototypical part network (ProtoPNet) from the paper "This Looks Like That: Deep Learning for Interpretable Image Recognition" (to appear at NeurIPS 2019), by Chaofan Chen* (Duke University), Oscar Li* (Duke University), Chaofan Tao (Duke University), Alina Jade Barnett (Duke University), Jonathan Su (MIT Lincoln Laboratory), and Cynthia Rudin (Duke University) (* denotes equal contribution).

revisiting-self-supervised

saliency_sampler

The saliency-based is a distortion layer for convolutional neural networks that helps to improve the spatial sampling of input data for a given task.

starter-hugo-academic

🎓 Hugo Academic Theme 创建一个学术网站. Easily create a beautiful academic résumé or educational website using Hugo, GitHub, and Netlify.