GithubHelp home page GithubHelp logo

zishansami102 / first-impression Goto Github PK

View Code? Open in Web Editor NEW
29.0 4.0 25.0 16.95 MB

Human Personality Traits Recognition from short introduction videos of users from Youtube (ECCV16 Challenge)

License: MIT License

Python 100.00%

first-impression's Introduction

First-Impression

This is the solution to the problem "First Impressions" given in CVPR'17, ECCV '16 & ICPR '16 and this piece of code is the partial implementation(Video Modality) of the paper Deep Bimodal Regression for Apparent Personality Analysis which is the winner of ECCV 2016

This problem is a challenge on “first impressions”, in which participants will develop solutions for recognizing personality traits of users in short video sequences. They have made available a large newly collected data set sponsored by Microsoft of at least 10,000 15-second videos collected from YouTube, annotated with personality traits by AMT workers.

The traits to be recognized will correspond to the “big five” personality traits used in psychology and well known of hiring managers using standardized personality profiling:

  • Extroversion
  • Agreeableness
  • Conscientiousness
  • Neuroticism
  • Openness to experience.

As is known, the first impression made is highly important in many contexts, such as human resourcing or job interviews. This work could become very relevant to training young people to present themselves better by changing their behavior in simple ways.

The model used is called Descriptor Aggregation Network called DAN in short.

Model Archi

What distinguishes DAN from the traditional CNN is: the fully connected layers are discarded, and replaced by both average- and max-pooling following the last convolutional layers (Pool5). Meanwhile, each pooling operation is followed by the standard L2-normalization. After that, the obtained two 512-d feature vectors are concatenated as the final image representation. Thus, in DAN, the deep descriptors of the last convolutional layers are aggregated as a single visual feature. Finally, a regression (fc+sigmoid) layer is added for end-to-end training.

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

Prerequisites

Installing

Clone the repository

git clone https://github.com/THEFASHIONGEEK/First-Impression.git

Downlad the training dataset and extract it into a new /data directory with all 75 training zip files and 25 validation zip files as it is, we will extract them through the script.

Download Pretrained Vgg-face model and move it to the root directory

Run the Video_to_Image.py file to scrape the images from the videos and save it to a new ImageData directory

python Video_to_Image.py

Run the vid_to_wav.py file to extract audio(.wav) files from the videos and save it to a new VoiceData directory

python vid_to_wav.py

If succesfully completed then run the Write_Into_TFRecords.py file to form a data pipeline by saving the all the train images into train_full.tfrecords file , all the validation images into val_full.tfrecords to load it later during training

python Write_Into_TFRecords.py

Start the training by running the following command

python train.py

Other Proud Works: An AI Powered Website Builder

Makeweb.ai - Build websites with AI, publish in seconds EazySEO.co - Automate your SEO start to end

Acknowledgments

first-impression's People

Contributors

thefashiongeek avatar zishansami102 avatar

Stargazers

Xiao SUN avatar  avatar Kevin Saltarelli avatar He Jiazhi avatar 陈旭 avatar  avatar  avatar  avatar angus9077 avatar Jongho Kim avatar moe somatsu avatar OoCCloud avatar  avatar Vijay Narsing Chakole avatar  avatar  avatar  avatar  avatar  avatar SID avatar Shanay Ghag avatar Priscilla  avatar Jamal Dahbur avatar  avatar Ruitian Gao avatar fodorad avatar  avatar 李泽宇 avatar Prakhar Choudhary avatar

Watchers

James Cloos avatar  avatar Boostys avatar SID avatar

first-impression's Issues

Got Input/output error....

my training is started......But i got this error

UnknownError: 2 root error(s) found.
(0) Unknown: train_full.tfrecords; Input/output error
[[{{node ReaderReadV2_6}}]]
[[DecodeRaw_12/_97]]
(1) Unknown: train_full.tfrecords; Input/output error
[[{{node ReaderReadV2_6}}]]
0 successful operations.
0 derived errors ignored.

Please help

trained model

Hi, many thanks for your contribution.
Can you share the trained model?

slow train

Hi,

many thanks for your contribution.
I'm training on AWS's instance and the time remaining according to your code is:

Epoch:0.33% Of 1/2, Batch loss:0.0181
Time remaining : 417Hrs 33Secs

  • what am I doing wrong that it's so slow?

  • where is the audio features extraction code (I didn't find it in dan.py) ?

IN TRIAN.PY

File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/common_shapes.py", line 691, in _call_cpp_shape_fn_impl
raise ValueError(err.message)
ValueError: Shapes must be equal rank, but are 1 and 2 for 'Assign_1' (op: 'Assign') with input shapes: [64], [64,1].
getting this error when i run train.py

please help me to resolve this error

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.