Sahp_repo
| Project Name | Stars | Downloads | Repos Using This | Packages Using This | Most Recent Commit | Total Releases | Latest Release | Open Issues | License | Language |
|---|---|---|---|---|---|---|---|---|---|---|
| Danet | 1,556 | 3 years ago | 33 | mit | Python | |||||
| Dual Attention Network for Scene Segmentation (CVPR2019) | ||||||||||
| Deepvoice3_pytorch | 1,449 | 2 years ago | 29 | other | Python | |||||
| PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models | ||||||||||
| Image_segmentation | 880 | 3 years ago | 20 | Python | ||||||
| Pytorch implementation of U-Net, R2U-Net, Attention U-Net, and Attention R2U-Net. | ||||||||||
| Transformer | 644 | 2 months ago | 3 | Python | ||||||
| PyTorch Implementation of "Attention Is All You Need" | ||||||||||
| Vad | 632 | 2 years ago | 32 | MATLAB | ||||||
| Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD. We also provide our directly recorded dataset. | ||||||||||
| Moran_v2 | 593 | 4 months ago | 24 | mit | Python | |||||
| MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition | ||||||||||
| Transformer | 583 | 6 months ago | 7 | gpl-3.0 | Jupyter Notebook | |||||
| Implementation of Transformer model (originally from Attention is All You Need) applied to Time Series. | ||||||||||
| Attention Networks For Classification | 477 | 3 years ago | 8 | Jupyter Notebook | ||||||
| Hierarchical Attention Networks for Document Classification in PyTorch | ||||||||||
| Long Range Arena | 456 | 6 months ago | 18 | apache-2.0 | Python | |||||
| Long Range Arena for Benchmarking Efficient Transformers | ||||||||||
| Mac Network | 445 | 2 years ago | 9 | apache-2.0 | Python | |||||
| Implementation for the paper "Compositional Attention Networks for Machine Reasoning" (Hudson and Manning, ICLR 2018) | ||||||||||
SAHP
This is the repository for the Self-Attentive Hawkes Processes paper where self-attention is used to adapt the intensity function of Hawkes process.
Dataset
The realword datasets are available on this [Google drive] (https://drive.google.com/drive/folders/0BwqmV0EcoUc8UklIR1BKV25YR1U) while the synthetic dataset is at this [link] (https://drive.google.com/file/d/1lRUIJx5UIPMx4TMwKy6GiAiP-k2vwvDc/view?usp=sharing). To run the model, you should download them to
the parent directory of the source code, with the folder name data.
To make the data format consistent, it is necessary to run the script convert_realdata_syntheform.py first.
Package
The Python version should be at least 3.5 and the torch version can be 0.4.1
Scripts
models defines the self-attentive Hawkes model, multi-head attention and the related.
main_func.py is the main function to run the experiments, hyper-parameters are provided here.
utils contains utility functions
To run the model: python main_func.py
Citation
@article{zhang2019self,
title={Self-attentive Hawkes processes},
author={Zhang, Qiang and Lipani, Aldo and Kirnap, Omer and Yilmaz, Emine},
journal={arXiv preprint arXiv:1907.07561},
year={2019}
}
