Git Product home page Git Product logo

lipreading-in-the-wild-experiments's Introduction

lipreading-in-the-wild-experiments

This repository contains my experiments with lip reading using deep learning in Keras. I train and test on the LRW dataset.

process-lrw/

Codes to convert the videos in LRW Dataset to: - frames pertaining to words - mouth area of those frames - audio

Instructions are provided in README file in directory.

shape-predictor/

Directory to place the "shape_predictor_68_face_landmarks.dat" file, required by process-lrw and head-pose

image-retrieval/

Codes and files --- considering the lipreader as an image retrieval system

head-pose/

Codes and files --- to compute head pose in all frames in LRW dataset (extracted using process-lrw)

Head pose is determined using voletiv/deepgaze (my fork of deepgaze).

Instructions are provided in README file in directory.

lipreading-in-the-wild-experiments's People

Contributors

shiweijin avatar voletiv 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 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

Forkers

liviust cmplumtju gzjas fitrialif willqucd violivei xiaokeai18 ronakmehta21 pingyufeng newtusst sf308 robinttt333 warhammer0 lpsunny ltl7155

lipreading-in-the-wild-experiments's Issues

lipnet

hello, i am a Chinese student weiwei. i also study this direction. and now i run the lipnet with grid dataset ,your code is in the wild dataset, can you realize the lip recognation with that dataset?and did you have reported relative papers?

It can only extract fixed frames from each video?

Thanks for your contribution!

I found it can only extract fixed frames from each video? right?
VIDEO_FRAMES_PER_WORD = 30
Does this mean I can only extract 30 frames from each video even though the durations of each video are different?
Thanks!

Need lrw_word_set_num_txt_file_names_*.txt files.

Hi, I tried to run this assessor but I got an error message:

FileNotFoundError: [Errno 2] No such file or directory: '/home/user/lip_reading/src/assessor/lrw_word_set_num_txt_file_names_train.txt'

I didn't find the 'lrw_word_set_num_txt_file_names_train.txt' or other 'lrw_word_set_num_txt_file_names_X.txt'.
Could you give us an example of these *.txt?
Thanks~

Absense of syncnet_functions.py

Hi, Vikram. Thanks for your implementation. I'm digging into your code and found that there lack of syncnet_functions.py

Could you check it please.

dataset

Hi，I'm also studying this recently. Is it convenient to share the account and password applied by LRW lip data set [email protected]

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.