🚘 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

I train with two popular benchmark dataset: CamVid and Cityscapes

dataset	n_class	pixel accuracy
Cityscapes	20	96%
CamVid	32	93%

pip3 install -r requirements.txt

and download pytorch 0.2.0 from pytorch.org

and download CamVid dataset (recommended) or Cityscapes dataset

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

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

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

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

Po-Chih Huang / @pochih

Project Name	Stars	Most Recent Commit	Open Issues	License	Language
Pytorch Tutorial	7,263	2 months ago	28	mit	Jupyter Notebook
Build your neural network easy and fast, 莫烦Python中文教学
Gcn	6,621	15 days ago	121	mit	Python
Implementation of Graph Convolutional Networks in TensorFlow
Cnn Explainer	6,389	20 days ago		mit	JavaScript
Learning Convolutional Neural Networks with Interactive Visualization.
Cnn Text Classification Tf	5,256	3 years ago	110	apache-2.0	Python
Convolutional Neural Network for Text Classification in Tensorflow
T81_558_deep_learning	5,225	15 days ago	2	other	Jupyter Notebook
Washington University (in St. Louis) Course T81-558: Applications of Deep Neural Networks
Machine Learning Collection	4,989	a day ago	88	mit	Python
A resource for learning about Machine learning & Deep Learning
Deep Learning V2 Pytorch	4,865	18 days ago	11	mit	Jupyter Notebook
Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101
Unet	4,040	4 months ago	199	mit	Jupyter Notebook
unet for image segmentation
Image Super Resolution	3,376	a year ago	85	apache-2.0	Python
🔎 Super-scale your images and run experiments with Residual Dense and Adversarial Networks.
Pygcn	2,952	3 years ago	42	mit	Python
Graph Convolutional Networks in PyTorch