https://github.com/nazanin1369/semantic-segmentation
Fully Convolutional Network (FCN)
https://github.com/nazanin1369/semantic-segmentation
deep-learning fcn self-driving-car
Last synced: 8 months ago
JSON representation
Fully Convolutional Network (FCN)
- Host: GitHub
- URL: https://github.com/nazanin1369/semantic-segmentation
- Owner: Nazanin1369
- Created: 2018-01-11T09:05:47.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2018-01-11T09:07:48.000Z (almost 8 years ago)
- Last Synced: 2025-01-07T20:49:41.367Z (9 months ago)
- Topics: deep-learning, fcn, self-driving-car
- Language: Python
- Size: 2.3 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Semantic Segmentation
### Introduction
In this project the pixels of a road in images are labelled using a Fully Convolutional Network (FCN).
The network uses the architecture described in [Long et al.](https://people.eecs.berkeley.edu/~jonlong/long_shelhamer_fcn.pdf)
and is trained on the [Kitti Road dataset](http://www.cvlibs.net/datasets/kitti/eval_road.php).
[//]: # (Image References)
[image1]: ./images/um_000032.png
[image2]: ./images/um_000093.png
[image3]: ./images/umm_000032.png
[image4]: ./images/umm_000063.png
[image5]: ./images/uu_000082.png
[video1]: ./images/project_video.mp4
Some of the results are shown below:
![sample][image1]
![sample][image2]
![sample][image3]
![sample][image4]
The code performs a hyperparameter search using 200 epochs for training each network.
A test of the trained network on road conditions very different to the training data can be found here [project_video](./images/project_video.mp4)
### Setup
##### Frameworks and Packages
Make sure you have the following is installed:
- [Python 3](https://www.python.org/)
- [TensorFlow](https://www.tensorflow.org/)
- [NumPy](http://www.numpy.org/)
- [SciPy](https://www.scipy.org/)
##### Dataset
Download the [Kitti Road dataset](http://www.cvlibs.net/datasets/kitti/eval_road.php) from [here](http://www.cvlibs.net/download.php?file=data_road.zip). Extract the dataset in the `data` folder. This will create the folder `data_road` with all the training a test images.
### Start
##### How to Run
Run the following command to run the project:
```
python main.py
```
**Note** If running this in Jupyter Notebook system messages, such as those regarding test status, may appear in the terminal rather than the notebook.