Skip to content

Latest commit

 

History

History
18 lines (15 loc) · 895 Bytes

README.md

File metadata and controls

18 lines (15 loc) · 895 Bytes

Rotational Invariance in Convolutional Neural Networks

The purpose of this project is to explore rotational invariance in Convolutional Neural Networks using Max-Pooling.

Setup

Install the following Python packages to run the code in the project:

  1. Theano, bleeding edge.
  2. Keras: pip install keras
  3. iPython: pip install ipython
  4. [Optional] Hualos, for live visualization of loss function.
  5. [Optional] h5py, for saving trained models:
  • Install HDF5: sudo apt-get install libhdf5-serial-dev
  • Then, pip install h5py

Team Members