Home

Awesome

Hierarchical Layout-Aware Graph Convolutional Network for Unified Aesthetics Assessment

[Paper] [Supplementary Material] [Jittor Code] [Pytorch Code(coming soon)]

This repository contains a <a href="https://github.com/Jittor/Jittor" target="_blank">Jittor</a> implementation of the paper "Hierarchical Layout-Aware Graph Convolutional Network for Unified Aesthetics Assessment" (CVPR 2021)

pipeline

Contents

Requirements

Jittor environment requirements:

Install

Dataset

Training

Traning scripts for two datasets can be found in scripts/. The dataroot argument should be modified to path_to_<dataset_name>. Run the follwing command for training:

# Training on AVA
sh script/train_jittor_aadb.sh

# Training on AABD
sh script/train_jittor_aadb.sh

Our code will process the dataset information and save file in preprocess/, which needs few minutes for the first time.

Testing

Testing model by runing the scripts or the follwing command:

python -m utils_jittor.eval \
    --dataset <dataset_name> \
    --dataroot path_to_<dataset_name> \
    --eval_model path_to_model

Citation

If you found this code useful please cite our work as:

@InProceedings{She_2021_CVPR,
    author    = {She, Dongyu and Lai, Yu-Kun and Yi, Gaoxiong and Xu, Kun},
    title     = {Hierarchical Layout-Aware Graph Convolutional Network for Unified Aesthetics Assessment},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {8475-8484}
}