AT-GCN
Pytorch implementation of the paper : Modeling Label Dependencies for Audio Tagging with Graph Convolutional Network
To start
This code is based on https://github.com/MaigoAkisame/cmu-thesis.
You can run it by replacing the files in https://github.com/MaigoAkisame/cmu-thesis/tree/master/code/audioset by the files we provide.
Also, you can follow another code https://github.com/qiuqiangkong/audioset_tagging_cnn.
Simply add the model in net.py to https://github.com/qiuqiangkong/audioset_tagging_cnn/blob/master/pytorch/models.py.
Citation
If this code is helpful, please feel free to cite the following papers:
@article{wang2020modeling,
title={Modeling Label Dependencies for Audio Tagging with Graph Convolutional Network},
author={Wang, Helin and Zou, Yuexian and Chong, Dading and Wang, Wenwu},
journal={IEEE Signal Processing Letters},
year={2020},
publisher={IEEE}
}
References
-
Yun Wang, Juncheng Li and Florian Metze, "A comparison of five multiple instance learning pooling functions for sound event detection with weak labeling," arXiv e-prints, Oct. 2018. [Online]. Available: http://arxiv.org/abs/1810.09050. https://github.com/MaigoAkisame/cmu-thesis
-
Qiuqiang Kong, Yin Cao, Turab Iqbal, Yuxuan Wang, Wenwu Wang, Mark D. Plumbley. "PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition." arXiv preprint arXiv:1912.10211 (2019). https://github.com/qiuqiangkong/audioset_tagging_cnn
Contact
If you have any problem about our code, feel free to contact
or describe your problem in Issues.