m-wz
Follow
Stars
Official code of "Towards Multi-Grained Explainability for Graph Neural Networks" (NeurIPS 2021) + Pytorch Implementation of recent attribution methods for GNNs
A simple package to allow users to run Monte Carlo Tree Search on any perfect information domain
Paper:Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting . Implementation of spatio-temporal graph convolutional network with PyTorch
[IJCAI'18] Spatio-Temporal Graph Convolutional Networks
Graph Neural Network Library for PyTorch
[CIKM'2023] "STExplainer: Explainable Spatio-Temporal Graph Neural Networks"
Official Implementation of "TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery"
Official implementation for Paper: PAGE: Parametric Generative Explainer for Graph Neural Network
Parameterized Explainer for Graph Neural Network
Implementation fo Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks
A data-driven deep learning based fault diagnosis application for radial, active distribution grids
MATLAB Unbalanced Power System Fault Analysis
Open-source Windows and Office activator featuring HWID, Ohook, KMS38, and Online KMS activation methods, along with advanced troubleshooting.
MATPOWER – steady state power flow simulation and optimization for MATLAB and Octave
使用torch整合两种经典的指针NER抽取范式，分别是SpanBert和苏神的GlobalPointer，简单加了些tricks，配置后一键运行
这是我ehr-journey项目的一个命名实体识别的子项目，主要实现基于中文预训练字向量finetune的Bert与BiLSTM模型的网络。演示使用了CCKS2019task1数据集，并实现了django接口。
基于pytorch的bert_bilstm_crf中文命名实体识别
Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)
Keras solution of Chinese NER task using BiLSTM-CRF/BiGRU-CRF/IDCNN-CRF/single-CRF model with BERTs (Google's Pretrained Language Model: supporting BERT/RoBERTa/ALBERT).
中文命名实体识别NER。用keras实现BILSTM+CRF、IDCNN+CRF、BERT+BILSTM+CRF进行实体识别。结果当然是BERT+BILSTM+CRF最好啦。
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
基于Pytorch的BERT-IDCNN-BILSTM-CRF中文实体识别实现
基于Tensorflow2.3开发的NER模型，都是CRF范式，包含Bilstm(IDCNN)-CRF、Bert-Bilstm(IDCNN)-CRF、Bert-CRF，可微调预训练模型，可对抗学习，用于命名实体识别，配置后可直接运行。
达观ner比赛的代码，主要是elmo pretrain + cnn/lstm + attention + crf 结构。成绩一般，一百以内，前几名全为各种bert集成的模型。
Named Entity Recognition (NER) with different combinations of BiGRU, Self-Attention and CRF