{"id":13869966,"url":"https://github.com/ludwigwinkler/pytorch_ProbabilisticLayers","last_synced_at":"2025-07-15T20:30:59.873Z","repository":{"id":53459983,"uuid":"267649581","full_name":"ludwigwinkler/pytorch_ProbabilisticLayers","owner":"ludwigwinkler","description":"Bayesian Neural Networks with Parallelized Sampling of LogLikelihood","archived":false,"fork":false,"pushed_at":"2021-03-30T08:54:56.000Z","size":11499,"stargazers_count":5,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-08-06T21:22:49.556Z","etag":null,"topics":["bayesianneuralnetwork","bnn","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ludwigwinkler.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-05-28T17:11:18.000Z","updated_at":"2024-05-15T20:35:19.000Z","dependencies_parsed_at":"2022-09-01T00:52:38.109Z","dependency_job_id":null,"html_url":"https://github.com/ludwigwinkler/pytorch_ProbabilisticLayers","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ludwigwinkler%2Fpytorch_ProbabilisticLayers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ludwigwinkler%2Fpytorch_ProbabilisticLayers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ludwigwinkler%2Fpytorch_ProbabilisticLayers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ludwigwinkler%2Fpytorch_ProbabilisticLayers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ludwigwinkler","download_url":"https://codeload.github.com/ludwigwinkler/pytorch_ProbabilisticLayers/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226068121,"owners_count":17568701,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bayesianneuralnetwork","bnn","pytorch"],"created_at":"2024-08-05T20:01:23.655Z","updated_at":"2024-11-23T16:30:55.244Z","avatar_url":"https://github.com/ludwigwinkler.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# torch-ProbabilisticLayers\n\n\u003cimg src=\"data/plots/BNN.gif\" width=\"500\"\u003e\n\nThis repository implements **parallelized** Bayesian Neural Networks in PyTorch via Variational Inference.\n\nBayesian neural networks require the evaluation of the evidence lower bound as the cost function of choice which includes the expectation over the data log-likelihood.\n\\\nThe sampling of the data log-likelihood evidence is implemented in a parallel fashion to circumvent slow Python loops like in other repositories.\n\nIn order to achieve this, the most common layers are implemented from scratch to process the samples of the expectation of the data log-likelihood in parallel.\n\\\nThe data tensors fed into the Bayesian neural network are extended with an additional first dimension `input.shape=(MonteCarloSamples, BatchSize, Features...)` which is referred to as MC (Monte Carlo) dimension.\n\nCaveat Emptor: The memory footprint increases linearly with the number of chosen Monte Carlo samples but the gradients are greatly stabilized even with \u003e 5 MC samples.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fludwigwinkler%2Fpytorch_ProbabilisticLayers","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fludwigwinkler%2Fpytorch_ProbabilisticLayers","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fludwigwinkler%2Fpytorch_ProbabilisticLayers/lists"}