Mask Architecture for Road Scenes

This is the starting repository for two projects:

• Mask Architecture Anomaly Segmentation for Road Scenes [Project Description]
• Comprehensive Road Scene Understanding for Autonomous Driving [Project Description]

This repository 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. Some of this code may be unnecessary for your project.

Folders

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

• eval contains tools for evaluating/visualizing 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.