{"id":20826820,"url":"https://github.com/arkaung/dropout_bayesian_nn","last_synced_at":"2026-04-29T03:04:00.025Z","repository":{"id":70135091,"uuid":"263217385","full_name":"ArkAung/dropout_bayesian_nn","owner":"ArkAung","description":"Demonstration for using dropout as a means of bayesian approximation in Deep Neural Network","archived":false,"fork":false,"pushed_at":"2020-05-13T07:28:09.000Z","size":11164,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-18T17:50:16.837Z","etag":null,"topics":["bayesian","deep-neural-networks"],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ArkAung.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2020-05-12T02:58:35.000Z","updated_at":"2022-05-31T02:41:29.000Z","dependencies_parsed_at":"2023-02-21T20:15:26.403Z","dependency_job_id":null,"html_url":"https://github.com/ArkAung/dropout_bayesian_nn","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/ArkAung%2Fdropout_bayesian_nn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArkAung%2Fdropout_bayesian_nn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArkAung%2Fdropout_bayesian_nn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ArkAung%2Fdropout_bayesian_nn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ArkAung","download_url":"https://codeload.github.com/ArkAung/dropout_bayesian_nn/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243174162,"owners_count":20248252,"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","deep-neural-networks"],"created_at":"2024-11-17T23:10:10.232Z","updated_at":"2025-12-28T06:23:45.715Z","avatar_url":"https://github.com/ArkAung.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Dropout as Bayesian Approximation for Deep Neural Network\n\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ArkAung/dropout_bayesian_nn)\n\nYou can run the whole notebook in Colab without issue. \nGetting helper scripts from Github repo, downloading datasets,\n and install required packages are all handled. \n\n### Running on local machine\n\n* Clone repository and change directory to local copy\n* Create a conda environment `conda create --name bayesian_nn`\n* Activate conda environment `conda activate bayesian_nn`\n* Install required libraries `pip install -r requirements.txt`\n* Run jupyter lab `jupyter lab`\n* Open `Dropout as Bayesian Approximation.ipynb`\n\n## Visualizing Model Uncertainty\n\nData is passed through the model with `Dropout` turned on \nduring the inference step for multiple times. The resulting \nprobability distributions are what the model produce over \nmultiple passes.\n\nWhen the model is uncertain:\n![Uncertain](assets/uncertain.png)\n\nWhen the model is certain:\n![Certain](assets/certain.png)\n\nHigh certainty:\n![High_Certain](assets/high_certainty.png)\n\nExtremely high certainty:\n![Ext_Certain](assets/extremely_high_certainty.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farkaung%2Fdropout_bayesian_nn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Farkaung%2Fdropout_bayesian_nn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farkaung%2Fdropout_bayesian_nn/lists"}