SwiftNet

Source code to reproduce results from

In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images
Marin Oršić*, Ivan Krešo*, Siniša Šegvić, Petra Bevandić (* denotes equal contribution)
CVPR, 2019.

Steps to reproduce

Install requirements

• Python 3.7+

pip install -r requirements.txt

Download pre-trained models

wget http://elbereth.zemris.fer.hr/swiftnet/swiftnet_ss_cs.pt -P weights/
wget http://elbereth.zemris.fer.hr/swiftnet/swiftnet_pyr_cs.pt -P weights/

Download Cityscapes

From https://www.cityscapes-dataset.com/downloads/ download:

• leftImg8bit_trainvaltest.zip (11GB)
• gtFine_trainvaltest.zip (241MB)

Either download and extract to datasets/ or create a symbolic link datasets/Cityscapes

Evaluate

python eval.py configs/single_scale.py
python eval.py configs/pyramid.py