Skip to content

CS 6140 Machine Learning Project on creating a Multi-Layer Capsule Network for better Facial Recognition.

Notifications You must be signed in to change notification settings

VikramShenoy97/Multi-Layer-Capsule-Network

Repository files navigation

Multi-Layer Capsule Network

Multi-Layer Capsule Network and its evaluation implemented by Vikram Shenoy, Alexander Chowdhury, and Harry Hartenstine.

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

Baseline Multi-Layer Capsule Network

This model was trained on Google Colab. To reproduce the results, follow the following instructions

1) Go to CapsNet_AT&T/MLCN
2) Copy the main.py file onto a Google Colab Cell
3) Upload the make_graph.py, att_MLCN.py, and utils.py file onto Google Colab
4) Change the mode from "Train" to "Test", "VPA" (Capsule Vector Perturbation Analysis), and "LVG" (Latent Vector Generation)

The above instructions apply to the other codes as well with some minor changes.

Results

Results can be found in the Network Comparisons folder. One such result is displayed below.

Encoding_37_2

More details can be found in the Results section of our paper.

Built With

Authors

About

CS 6140 Machine Learning Project on creating a Multi-Layer Capsule Network for better Facial Recognition.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages