Large-Scale Gravitational Lens Modeling with Bayesian Neural Networks for Accurate and Precise Inference of the Hubble Constant - Datasets, Trained Models, BNN Samples, and MCMC Chains

We publish the training/validation/test datasets, trained model weights, configuration files, Bayesian neural network samples, and MCMC chains used to produce the figures in the LSST DESC paper, "Large-Scale Gravitational Lens Modeling with Bayesian Neural Networks for Accurate and Precise Inference of the Hubble Constant." They are formatted to be used with the DESC package "H0rton" (https://github.com/jiwoncpark/h0rton). Additional descriptions can be found in the README. Please contact Ji Won Park (@jiwoncpark) on GitHub or make an issue for any questions.

我们发布了LSST暗能量科学合作组（LSST DESC）论文《基于贝叶斯神经网络的大规模引力透镜建模以准确且精准推断哈勃常数》（Large-Scale Gravitational Lens Modeling with Bayesian Neural Networks for Accurate and Precise Inference of the Hubble Constant）中用于生成图表的训练/验证/测试数据集、训练好的模型权重、配置文件、贝叶斯神经网络（Bayesian Neural Network）采样样本以及马尔可夫链蒙特卡洛（Markov Chain Monte Carlo, MCMC）链。本数据集的格式适配DESC工具包“H0rton”（https://github.com/jiwoncpark/h0rton）。更多详细说明可参见README文件。如有任何疑问，请在GitHub上联系Ji Won Park（用户名@jiwoncpark）或提交Issue。