chennwpu/Fast-SCNN-pytorch

A PyTorch Implementation of Fast-SCNN: Fast Semantic Segmentation Network

Fast-SCNN: Fast Semantic Segmentation Network

A PyTorch implementation of Fast-SCNN: Fast Semantic Segmentation Network from the paper by Rudra PK Poudel, Stephan Liwicki.

Table of Contents

• Installation
• Datasets
• Train
• Evaluate
• Demo
• Results
• TO DO
• Reference

Installation

• Python 3.x. Recommended using Anaconda3
• PyTorch 1.0. Install PyTorch by selecting your environment on the website and running the appropriate command. Such as:

  conda install pytorch torchvision cudatoolkit=9.0 -c pytorch
  

• Clone this repository.
• Download the dataset by following the instructions below.
• Note: For training, we currently support cityscapes, and aim to add VOC and ADE20K.

Datasets

• You can download cityscapes from here. Note: please download leftImg8bit_trainvaltest.zip(11GB) and gtFine_trainvaltest(241MB).

Training-Fast-SCNN

• By default, we assume you have downloaded the cityscapes dataset in the ./datasets/citys dir.
• To train Fast-SCNN using the train script the parameters listed in train.py as a flag or manually change them.

python train.py --model fast_scnn --dataset citys

Evaluation

To evaluate a trained network:

python eval.py

Demo

Running a demo:

python demo.py --model fast_scnn --input-pic './png/berlin_000000_000019_leftImg8bit.png'

Results

Method	Dataset	crop_size	mIoU	pixAcc
Fast-SCNN(paper)	cityscapes
Fast-SCNN(ours)	cityscapes	768	54.84%	92.37%

Note: The result based on crop_size=768, which is different with paper.

      (a) test image            (b) ground truth           (c) predicted result

TODO

• add distributed training
• Support for the VOC, ADE20K dataset
• Support TensorBoard
• save the best model
• add Ohem Loss

Authors

• Tramac

References

• Rudra PK Poudel. et al. "Fast-SCNN: Fast Semantic Segmentation Network".