Giter Club home page Giter Club logo

mica-race-from-face's Introduction

Predicting race from faces for movie data

NOTE: Race is a social construct. We understand that our objective here of attempting to classify race, regardless of the definitional distinction between race and ethnicity, is an extremely culturally sensitive issue. Any approach we use to classify race will be done with as much respect as this problem deserves to be treated with and as delicately as possible -- in the ultimate interest of understanding diversity of representation of people on screen. This is a work in progress and has plenty of scope for improvement.

Please see the details of the definitions of race, taxonomy of race recognition, database details, neural network models and performance evaluation details in the wiki page here

Contents:

race labels

actor_race.txt: labels for IMDB faces obtained as described in Ramakrishna et. al., 2017, ACL
lfw_race_dict.json: mapping of race for identities in the LFW dataset

aligning faces

average_face.ppm: average face used for in-plane face alignment
average_face.json: landmark information for the average face for alignment
faceswap.py: utilities for face alignment

average_faces: directory with average faces for the different classes in our data

Convolution neural networks (CNN) training scripts and pretrained models

pretrained_models: Directory containing 5-class pretrained models
train_multiclass_vgg16_5class_subsample.py: Keras training script and CNN architecture details
test_race_models.py: performance evaluation scripts (ROC, accuracy, confusion matrix, etc.,)
utils.py: miscellaneous handy utility functions

mica-race-from-face's People

Contributors

krsna6 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar

mica-race-from-face's Issues

Predict race for an image in 10k US Adult Faces Database

Thanks for sharing the code to run a race prediction model.

I've been trying to apply your pre-trained model on a sample of the 10k faces dataset without much success. In particular, most faces are predicted to be "black race".

One of the issues, I think, is that your code is missing (maybe?) how you preprocess an arbitrary face image before you input it into the network.

Any help would be highly appreciated!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.