https://github.com/johnsmithm/lipsreadertensorflow

Tensorflow implementation of lips reader neural network
https://github.com/johnsmithm/lipsreadertensorflow

Last synced: 11 months ago
JSON representation

Tensorflow implementation of lips reader neural network

• Host: GitHub
• URL: https://github.com/johnsmithm/lipsreadertensorflow
• Owner: johnsmithm
• Created: 2017-01-18T14:03:38.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2017-01-18T14:39:10.000Z (over 9 years ago)
• Last Synced: 2025-03-20T14:04:32.355Z (about 1 year ago)
• Language: Jupyter Notebook
• Homepage:
• Size: 11.6 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

          
This is a implementation of lips reader neural networks using tensorflow.

The dataset is made using the GridCorpus database.

the database.ipynb download the database and make the batches

-it uses opencv haarcascade_frontalface_default.xml to detect the face of the speacker

the ctc-images-bidirectional.ipynb make the graph and run simulation

-bidirectional rnn, 3d convolution layers, dropout