Welcome to the AI for Visual Arts Challenges repository! This repository contains the resources you need to participate in the challenge, including example notebooks, baseline models, and instructions.
We have three challenge tracks: segmentation, depth and saliency estimation. Each track has the following structure:
data/
: Contains training and validation images and ground truth data.notebooks/
: Contains Jupyter notebooks for data exploration.scripts/
: Contains Python scripts for evaluation and metrics.models/
: A folder to place your models.results/
: Contains your models' predictions.requirements.txt
: Lists Python dependencies.README.md
: This file, provides a task-specific overview and instructions.
-
Clone the repository:
git clone https://github.com/IVRL/AI4VA.git cd AI4VA
-
Install the dependencies:
pip install -r requirements.txt
-
Download and organize the data: We provide the data for each task in this Google Drive folder : https://drive.google.com/drive/folders/1wkZrOFQx3LZnG_rEc_js1WvNf5HHcGtn?usp=sharing Follow the instructions on the task page for more details.
-
Explore the data: Open and run
show_annotations.ipynb
. -
Run the baseline model: Open and run
notebooks/baseline_model.ipynb
.
Please read the instructions in the respective challenge folders for more details.
This project is licensed under the MIT License.