Awesome

🚘 The easiest implementation of fully convolutional networks

• Task: semantic segmentation, it's a very important task for automated driving

• The model is based on CVPR '15 best paper honorable mentioned Fully Convolutional Networks for Semantic Segmentation

Results

Trials

<img align='center' style="border-color:gray;border-width:2px;border-style:dashed" src='result/trials.png' padding='5px' height="150px"></img>

Training Procedures

<img align='center' style="border-color:gray;border-width:2px;border-style:dashed" src='result/result.gif' padding='5px' height="150px"></img>

Performance

I train with two popular benchmark dataset: CamVid and Cityscapes

Training

Install packages

pip3 install -r requirements.txt

and download pytorch 0.2.0 from pytorch.org

and download CamVid dataset (recommended) or Cityscapes dataset

Run the code

• default dataset is CamVid

create a directory named "CamVid", and put data into it, then run python codes:

python3 python/CamVid_utils.py 
python3 python/train.py CamVid

• or train with CityScapes

create a directory named "CityScapes", and put data into it, then run python codes:

python3 python/CityScapes_utils.py 
python3 python/train.py CityScapes

Author

Po-Chih Huang / @pochih