Vision

This repository will host implementations of computer vision algorithms, this repository hosts a general toolbox in library format under neodroidvision, while also comprising a range of sample usages in samples, many of them utilising the Neodroid platform.

Neodroid is developed with support from Research Council of Norway Grant #262900. (https://www.forskningsradet.no/prosjektbanken/#/project/NFR/262900)

Contents Of This Readme

• Algorithms
• Requirements
• Usage
• Results
  • Segmentation
• Contributing
• Other Components

Computer Vision Algorithms

Classification

Segmentation

• UNET - Segmentation model
• AUX-UNET - Instance Segmentation model + Auxilary ouputs

Detection

• SSD - Object Detection Model
• MASK-RCNN - Object Detection Model

Regression

Generative

• SAGAN - Generative model
• VAE - Generative model

Requirements

• pytorch
• tqdm
• Pillow
• numpy
• matplotlib
• torchvision
• torch
• Neodroid
• pynput

To install these use the command:

pip3 install -r requirements.txt

Usage

Export python path to the repo root so we can use the utilities module

export PYTHONPATH=/path-to-repo/

For training a agent use:

python3 procedures/train_agent.py

For testing a trained agent use:

python3 procedures/test_agent.py

Results

Segmentation

Code

Screenshots

Contributing

See guidelines for contributing here.

Citation

For citation you may use the following bibtex entry:

@misc{neodroid-vision,
  author = {Heider, Christian},
  title = {Neodroid Vision},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/aivclab/vision}},
}

Authors

• Christian Heider Nielsen - cnheider
• Other contributors