Mask Architecture Anomaly Segmentation for Road Scenes [Course Project]

This repository provides a starter-code setup for the Real-Time Anomaly Segmentation project of the Machine Learning Course. It consists of the code base for training/testing ERFNet on the Cityscapes dataset and perform anomaly segmentation. It also contains some code referring to EoMT.

Packages

For instructions, please refer to the README in each folder:

• eval contains tools for evaluating/visualizing the an ERFNet model's output and performing anomaly segmentation.
• trained_models Contains the ERFNet trained models for the baseline eval.
• eomt It is almost the original folder of the EoMT project. Inside it you will find code to train and pretrained checkpoints for EoMT.