zhuannianyixiang
Follow
Stars
All Algorithms implemented in Python
Flexible and transparent Python Boruta implementation
Python implementations of the Boruta all-relevant feature selection method.
Code release for "Multi-Adversarial Domain Adaptation" (AAAI 2018)
Pytorch Code release for our NeurIPS paper "Multi-source Domain Adaptation for Semantic Segmentation"
Pytorch implementation of four neural network based domain adaptation techniques: DeepCORAL, DDC, CDAN and CDAN+E. Evaluated on benchmark dataset Office31.
Code release for "Conditional Adversarial Domain Adaptation" (NIPS 2018)
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
A collection of 85 minority oversampling techniques (SMOTE) for imbalanced learning with multi-class oversampling and model selection features
Reimplementation of paper "Variational Graph Auto-Encoders", adapted from https://github.com/limaosen0/Variational-Graph-Auto-Encoders/, simplified and error-corrected.
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
A Collection of Variational Autoencoders (VAE) in PyTorch.
Dual LSTM Encoder for Dialog Response Generation
Implementation of handwriting generation with use of recurrent neural networks in tensorflow. Based on Alex Graves paper (https://arxiv.org/abs/1308.0850).
In this repository you will find an end-to-end model for text generation by implementing a Bi-LSTM-LSTM based model with PyTorch's LSTMCells.
Text Generation using Bidirectional LSTM and Doc2Vec models
Oversampling for imbalanced learning based on k-means and SMOTE
Pytorch implementation of "DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data".
使用AIC准则进行参数选择，之后采用ARIMA模型进行时间序列预测，最后给出残差图。The AIC criterion is used to select the parameters, and then ARIMA model is used to predict the time series. Finally, the residual diagram is given.
Undergradute final project with ARIMA,LSTM,GRU,Xgboost and DeepTTE.毕业论文代码库合集，包括基于ARIMA,LSTM,GRU进行时间序列预测，基于DeepTTE解决ETA(estimated time of arrival)问题计算运输完成时长，基于特征工程和xgboost的运力预测
ARIMA时间序列分析：预测餐厅销量