Skip to content

Latest commit

 

History

History
11 lines (9 loc) · 409 Bytes

README.md

File metadata and controls

11 lines (9 loc) · 409 Bytes

This is the code source of the master dissertation: "Sequence to sequence learning with the Variational Information Bottleneck".

Usage Example

  • python3 run_s2l_image_digit.py --length=5

Architecture

Main components:

  • Networks: the computational graphs
  • Learners: uses batches to train or test a network
  • Batcher: generate batches from a dataset
  • Layers: re-usable layer for different networks