Datasets: density estimation using deep generative neural network

Datasets used in Roundtrip paper. Source code can be found at https://github.com/kimmo1019/Roundtrip UCI datasets: AReM/data.npy: Activity Recognition data collected from Multi sensors. Data size (42239, 6) CASP/data.npy: Protein Tertiary Structure data. Data size (45730, 9) BANK/data.npy: Financial data collected from clients. Data size (45211, 17) YPMSD/data.npy: Audio data of various songs. Data size (515345,90) HEPMASS/train.csv and HEPMASS/test.csv: Data of high-energy particles. ODDS contains three outlier detection datasets Shuttle, Mammography and ForestCover. mnist.tar.gz: MNIST datasets cifar10.tar.gz: CIFAR-10 datasets Pretrained models:uncompress pre_trained_models.tar.gz under the Roundtrip model.

本数据集为Roundtrip论文所使用的数据集，源代码可于https://github.com/kimmo1019/Roundtrip 获取。UCI数据集详情如下：AReM/data.npy：多传感器采集的活动识别数据，数据规模为(42239, 6)；CASP/data.npy：蛋白质三级结构数据，数据规模为(45730, 9)；BANK/data.npy：面向客户的金融数据，数据规模为(45211, 17)；YPMSD/data.npy：各类歌曲的音频数据，数据规模为(515345, 90)。HEPMASS/train.csv与HEPMASS/test.csv：高能粒子数据集。ODDS数据集包含三类异常检测数据集：Shuttle、Mammography与ForestCover。mnist.tar.gz：MNIST数据集；cifar10.tar.gz：CIFAR-10数据集。预训练模型：请将pre_trained_models.tar.gz解压至Roundtrip模型所在目录下。