/YOLOv3-UDA-Master_Thesis

A minimal PyTorch implementation of YOLOv3, with support for training, inference and evaluation. An addtional implementation of two Unsupervised Domain Adaptation methods (Direct Entropy Minimization and Fourier Domain Adaptation) integrated in the architecture.

Primary LanguageJupyter NotebookGNU General Public License v3.0GPL-3.0

YOLOv3-UDA

A minimal PyTorch implementation of YOLOv3, with support for training, inference and evaluation. An addtional implementation of two Unsupervised Domain Adaptation methods (Direct Entropy Minimization and Fourier Domain Adaptation) integrated in the architecture.

Installation

Clone and install requirements
$ git clone https://github.com/saurabh-2905/YOLOv3-UDA.git
$ cd YOLOv3-UDA/
$ sudo pip3 install -r requirements_rotated.txt

[Paper] [Project Webpage] [Authors' Implementation]

@article{yolov3,
  title={YOLOv3: An Incremental Improvement},
  author={Redmon, Joseph and Farhadi, Ali},
  journal = {arXiv},
  year={2018}
}