blitz-bayesian-deep-learning:一个简单且可扩展的库,可在PyTorch上创建贝叶斯神经网络层

上传者: 42097450 | 上传时间: 2024-04-24 16:41:44 | 文件大小: 136KB | 文件类型: ZIP
闪电战-火炬动物园中的贝叶斯层 BLiTZ是一个简单且可扩展的库,用于在PyTorch上创建贝叶斯神经网络层(基于“)。 通过使用BLiTZ图层和utils,您可以以不影响图层之间的交互的简单方式(例如,就像使用标准PyTorch一样)添加非证书并收集模型的复杂性成本。 通过使用我们的核心权重采样器类,您可以扩展和改进此库,从而以与PyTorch良好集成的方式为更大范围的图层添加不确定性。 也欢迎拉取请求。 我们的目标是使人们能够通过专注于他们的想法而不是硬编码部分来应用贝叶斯深度学习。 Rodamap: 为不同于正态的后验分布启用重新参数化。 指数 贝叶斯层的目的 贝叶斯层上的权重采样 有可能优化我们的可训练重量 的确,存在复杂度成本函数随其变量可微分的情况。 在第n个样本处获得整个成本函数 一些笔记和总结 引用 参考 安装 要安装BLiTZ,可以使用pip命令: pip

文件下载

资源详情

[{"title":"( 47 个子文件 136KB ) blitz-bayesian-deep-learning:一个简单且可扩展的库,可在PyTorch上创建贝叶斯神经网络层","children":[{"title":"blitz-bayesian-deep-learning-master","children":[{"title":".github","children":[{"title":"workflows","children":[{"title":"pythonpublish.yml <span style='color:#111;'> 865B </span>","children":null,"spread":false},{"title":"pythonapp.yml <span style='color:#111;'> 783B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 34.33KB </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 71B </span>","children":null,"spread":false},{"title":"doc","children":[{"title":"layers.md <span style='color:#111;'> 17.39KB </span>","children":null,"spread":false},{"title":"utils.md <span style='color:#111;'> 2.55KB </span>","children":null,"spread":false},{"title":"losses.md <span style='color:#111;'> 282B </span>","children":null,"spread":false},{"title":"samplers.md <span style='color:#111;'> 2.39KB </span>","children":null,"spread":false}],"spread":true},{"title":"setup.py <span style='color:#111;'> 1.03KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 1.86KB </span>","children":null,"spread":false},{"title":"blitz","children":[{"title":"models","children":[{"title":"b_vgg.py <span style='color:#111;'> 3.00KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 20B </span>","children":null,"spread":false}],"spread":true},{"title":"losses","children":[{"title":"tests","children":[{"title":"kl_divergence_test.py <span style='color:#111;'> 1.53KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 28B </span>","children":null,"spread":false},{"title":"kl_divergence.py <span style='color:#111;'> 557B </span>","children":null,"spread":false}],"spread":true},{"title":"run_tests.sh <span style='color:#111;'> 122B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"examples","children":[{"title":"stocks-blstm.ipynb <span style='color:#111;'> 106.53KB </span>","children":null,"spread":false},{"title":"requirements_stocks_example.txt <span style='color:#111;'> 31B </span>","children":null,"spread":false},{"title":"cifar10_bvgg.py <span style='color:#111;'> 9.92KB </span>","children":null,"spread":false},{"title":"bayesian_regression_boston.py <span style='color:#111;'> 3.45KB </span>","children":null,"spread":false},{"title":"bayesian_LeNet_mnist.py <span style='color:#111;'> 3.03KB </span>","children":null,"spread":false}],"spread":true},{"title":"utils","children":[{"title":"tests","children":[{"title":"layer_wrappers_test.py <span style='color:#111;'> 1.54KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"variational_estimator_test.py <span style='color:#111;'> 6.59KB </span>","children":null,"spread":false}],"spread":false},{"title":"__init__.py <span style='color:#111;'> 101B </span>","children":null,"spread":false},{"title":"minibatch_weighting.py <span style='color:#111;'> 629B </span>","children":null,"spread":false},{"title":"layer_wrappers.py <span style='color:#111;'> 3.68KB </span>","children":null,"spread":false},{"title":"variational_estimator.py <span style='color:#111;'> 6.26KB </span>","children":null,"spread":false}],"spread":true},{"title":"modules","children":[{"title":"gru_bayesian_layer.py <span style='color:#111;'> 8.78KB </span>","children":null,"spread":false},{"title":"base_bayesian_module.py <span style='color:#111;'> 4.20KB </span>","children":null,"spread":false},{"title":"embedding_bayesian_layer.py <span style='color:#111;'> 4.58KB </span>","children":null,"spread":false},{"title":"conv_bayesian_layer.py <span style='color:#111;'> 16.51KB </span>","children":null,"spread":false},{"title":"tests","children":[{"title":"conv_bayesian_layer_test.py <span style='color:#111;'> 10.61KB </span>","children":null,"spread":false},{"title":"base_bayesian_module_test.py <span style='color:#111;'> 1.91KB </span>","children":null,"spread":false},{"title":"embadding_bayesian_test.py <span style='color:#111;'> 3.31KB </span>","children":null,"spread":false},{"title":"gru_bayesian_layer_test.py <span style='color:#111;'> 2.57KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"linear_bayesian_layer_test.py <span style='color:#111;'> 3.38KB </span>","children":null,"spread":false},{"title":"weight_sampler_test.py <span style='color:#111;'> 2.57KB </span>","children":null,"spread":false},{"title":"lstm_bayesian_layer_test.py <span style='color:#111;'> 2.81KB </span>","children":null,"spread":false}],"spread":false},{"title":"linear_bayesian_layer.py <span style='color:#111;'> 4.21KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 210B </span>","children":null,"spread":false},{"title":"lstm_bayesian_layer.py <span style='color:#111;'> 9.77KB </span>","children":null,"spread":false},{"title":"weight_sampler.py <span style='color:#111;'> 2.94KB </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 18.20KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明