{"id":16518124,"url":"https://github.com/ferrine/gelato","last_synced_at":"2025-03-21T08:31:54.984Z","repository":{"id":83546240,"uuid":"74837175","full_name":"ferrine/gelato","owner":"ferrine","description":"Bayesian dessert for Lasagne","archived":false,"fork":false,"pushed_at":"2017-06-25T11:38:46.000Z","size":354,"stargazers_count":84,"open_issues_count":2,"forks_count":4,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-03-17T23:14:39.155Z","etag":null,"topics":["bayesian-inference","deep-learning","gelato","lasagne","neural-network","theano","uncertainty","variational-inference"],"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/ferrine.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2016-11-26T16:28:59.000Z","updated_at":"2024-01-04T16:09:21.000Z","dependencies_parsed_at":"2023-07-07T17:45:50.988Z","dependency_job_id":null,"html_url":"https://github.com/ferrine/gelato","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ferrine%2Fgelato","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ferrine%2Fgelato/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ferrine%2Fgelato/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ferrine%2Fgelato/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ferrine","download_url":"https://codeload.github.com/ferrine/gelato/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244765508,"owners_count":20506825,"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":["bayesian-inference","deep-learning","gelato","lasagne","neural-network","theano","uncertainty","variational-inference"],"created_at":"2024-10-11T16:34:56.946Z","updated_at":"2025-03-21T08:31:54.965Z","avatar_url":"https://github.com/ferrine.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Gelato\n[![](https://travis-ci.org/ferrine/gelato.svg?branch=master)](https://travis-ci.org/ferrine/gelato)\n[![Coverage Status](https://coveralls.io/repos/github/ferrine/gelato/badge.svg?branch=master)](https://coveralls.io/github/ferrine/gelato?branch=master)\n## Bayesian dessert for Lasagne\n\n![](img/gelato.jpg)\n\nRecent results in Bayesian statistics for constructing robust neural networks have proved that it is one of the best ways to deal with uncertainty, overfitting but still having good performance. Gelato will help to use bayes for neural networks.\nLibrary heavily relies on [Theano](https://github.com/Theano/Theano), [Lasagne](https://github.com/Lasagne/Lasagne) and [PyMC3](https://github.com/pymc-devs/pymc3).\n\nInstallation\n------------\n\n* from github (assumes bleeding edge pymc3 installed)\n    ```bash\n    # pip install git+git://github.com/pymc-devs/pymc3.git\n    pip install git+https://github.com/ferrine/gelato.git\n    ```\n* from source\n    ```bash\n    git clone https://github.com/ferrine/gelato\n    pip install -r gelato/requirements.txt\n    pip install -e gelato\n    ```\n\nUsage\n-----\nI use generic approach for decorating all Lasagne at once. Thus, for using Gelato you need to replace import statements for layers only. For constructing a network you need to be the in pm.Model context environment.\n\n**Warning**\n-  `lasagne.layers.noise` is not supported\n-  `lasagne.layers.normalization` is not supported (theano problems with default updates)\n-  functions from `lasagne.layers` are hidden in `gelato` as they use Lasagne classes. Some exceptions are done for `lasagne.layers.helpers`. I'll try to solve the problem generically in future.\n\nExamples\n--------\nFor comprehensive example of using `Gelato` you can reference [this](https://github.com/ferrine/gelato/blob/master/examples/mnist.ipynb) notebook \n\nLife Hack\n---------\nAny `spec` class can be used standalone so feel free to use it everywhere\n\nReferences\n----------\nCharles Blundell et al: \"Weight Uncertainty in Neural Networks\" ([arXiv preprint arXiv:1505.05424](https://arxiv.org/abs/1505.05424))\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fferrine%2Fgelato","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fferrine%2Fgelato","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fferrine%2Fgelato/lists"}