Skip to content

Latest commit

 

History

History
21 lines (18 loc) · 912 Bytes

File metadata and controls

21 lines (18 loc) · 912 Bytes

Lipreading With Machine Learning In PyTorch

A PyTorch implementation of the models described in Combining Residual Networks with LSTMs for Lipreading by T. Stafylakis and G. Tzimiropoulos. Adapted from the Torch7 code.

Usage

  • Install Python 3.
  • Clone the repository.
  • Run pip3 install -r requirements.txt to install project dependencies.
  • to use, run python3 main.py.

Dependencies

  • Python 3 to run the program
  • PyTorch for tensors, network definition and backprop
  • ImageIO to load video clips
  • NumPy to visualize individual layers