Overview

This directory is designed for training a SD classifier. Below is the directories structure and how to run

---

Directory Structure

code/
├── AutoEncoder/       # Files for our autoencoder architecture and training 
├── Data/              # Where to place data
├── Helper/            # Where helper functions and data prossessing code lives
├── report_assets/     # Figures and data from training
├── SignDistanceModel/ # Files for our sign distance model architecture and training 
└── README.md          # Repository overview (this file)

Running the Project

1. Create a Data folder in the root of the code directory

2. Download the ModelNet40 dataset and place in Data folder

3. Run the repair script on the data

   python3 Helpers/repair_dataset.py

4. Train the autoencoder model

   python3 AutoEncoder/train.py

5. Download the SDF dataset from our google drive and place it in the Data folder

6. Train the SDF classification model

   python3 SignDistanceModel/train.py