Programming challenge by Kopernikus Automotive GmBH
Table of Contents
-
About The Project
-
Getting Started
- Usage
- License
- Contact
### About
Programming challenge by Kopernikus Automotive GmBH.
## Structure
The directory is structured as follows:
1. util folder includes the module for plotting plot.py, as well as parsing, file validity and camera information (common.py);
2. preprocess folder contains the module (preprocess.py) for the image similarity classification task;
3. parameter_search.ipynb shows the parameter tuning process along with the dataset analysis;
4. main.py launches the program;
5. report_challenge_dimasi.pdf contains a brief overview on the code structure and the answers of the questions provided by the assignment.
### Built With
[![Python][Python.js]][Python-url]
(back to top)
## Getting Started
This is an example of how you may give instructions on setting up your project locally.
### Installation
1. Install anaconda: https://docs.anaconda.com/free/anaconda/install/index.html
2. Create a python enviroment called kopernikus_perception
```sh
conda create kopernikus_perception python=3.10
```
3. Install the requirements
```sh
python -m pip install -r requirements.txt
```
WARNING:
In case of Windows operative system it is highly suggested to download an anaconda version including python 3.10 and create the environmnt without the 'python' option:
```sh
conda create kopernikus_perception
```
(back to top)
## Usage
To run the fast version (option --fast) you need a PC with at least 8GB of RAM.
1. Activate the environment
```sh
conda activate kopernikus_perception
```
2. Clean the dataset with default value
```sh
python main.py --fast
```
3. Clean the dataset with custom value
```sh
python main.py --fast --min_contour_area
--diss_threshold --height --width
```
4. Clean the dataset with non concurrent version
```sh
python main.py --min_contour_area --diss_threshold --height --width
```
5. Info about all the command line arguments
```sh
python main.py --help
```
(back to top)
## License
Distributed under the MIT License. See `LICENSE` for more information.
(back to top)
## Contact
Paolo Dimasi - paolo.dimasi@outlook.com
Project Link: [https://github.com/Pamasi/kopernikus_perception](https://github.com/Pamasi/kopernikus_perception)
(back to top)
[contributors-shield]: https://img.shields.io/github/contributors/Pamasi/kopernikus_perception.svg?style=for-the-badge
[contributors-url]: https://github.com/Pamasi/kopernikus_perception/graphs/contributors
[forks-shield]: https://img.shields.io/github/forks/Pamasi/kopernikus_perception.svg?style=for-the-badge
[forks-url]: https://github.com/Pamasi/kopernikus_perception/network/members
[stars-shield]: https://img.shields.io/github/stars/Pamasi/kopernikus_perception.svg?style=for-the-badge
[stars-url]: https://github.com/Pamasi/kopernikus_perception/stargazers
[issues-shield]: https://img.shields.io/github/issues/Pamasi/repo_name.svg?style=for-the-badge
[issues-url]: https://github.com/Pamasi/kopernikus_perception/issues
[license-shield]: https://img.shields.io/github/license/Pamasi/kopernikus_perception.svg?style=for-the-badge
[license-url]: https://github.com/Pamasi/kopernikus_perception/blob/master/LICENSE
[linkedin-shield]: https://img.shields.io/badge/-LinkedIn-black.svg?style=for-the-badge&logo=linkedin&colorB=555
[linkedin-url]: https://linkedin.com/in/paolo-dimasi
[Python-url]: https://www.Python-lang.org/
[Python.js]: https://img.shields.io/badge/Python-20232A?style=for-the-badge&logo=Python&logoColor=61DAFB