{"id":15708012,"url":"https://github.com/abdulfatir/iwae-tensorflow","last_synced_at":"2025-05-12T20:57:20.990Z","repository":{"id":82220142,"uuid":"148983052","full_name":"abdulfatir/IWAE-tensorflow","owner":"abdulfatir","description":"Tensorflow implementation of Importance Weighted Auto Encoder","archived":false,"fork":false,"pushed_at":"2018-09-21T12:44:11.000Z","size":130,"stargazers_count":5,"open_issues_count":2,"forks_count":3,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-01T03:35:13.962Z","etag":null,"topics":["autoencoder","deep-learning","generative-model","paper-implementations","variational-autoencoder"],"latest_commit_sha":null,"homepage":null,"language":"Python","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/abdulfatir.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":"2018-09-16T09:58:16.000Z","updated_at":"2023-09-29T03:28:26.000Z","dependencies_parsed_at":null,"dependency_job_id":"1d7ecf02-fc78-4e8f-85bc-c88ac983ff07","html_url":"https://github.com/abdulfatir/IWAE-tensorflow","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/abdulfatir%2FIWAE-tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abdulfatir%2FIWAE-tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abdulfatir%2FIWAE-tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abdulfatir%2FIWAE-tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/abdulfatir","download_url":"https://codeload.github.com/abdulfatir/IWAE-tensorflow/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253823352,"owners_count":21969844,"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":["autoencoder","deep-learning","generative-model","paper-implementations","variational-autoencoder"],"created_at":"2024-10-03T20:43:34.280Z","updated_at":"2025-05-12T20:57:20.960Z","avatar_url":"https://github.com/abdulfatir.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Importance Weighted Auto Encoder\nA tensorflow implementation of _Importance Weighted Auto Encoder_ \u003csup\u003e[1]\u003c/sup\u003e\n\n## Requirements\n\n* tensorflow\n* numpy\n* matplotlib\n\n## Usage\n```\npython main.py  --dataset {mnist,omniglot} \\\n                --k \u003c# of particles for training\u003e \\\n                --test_k \u003c# number of particles for testing\u003e \\\n                --n_steps \u003c# of steps\u003e \\\n                --batch_size \u003cbatch size\u003e\n```\n\n### Datasets\n\n* MNIST - automatically downloaded by tensorflow\n* OMNIGLOT - run `download_omniglot.sh`\n\n## Results\nThe following are the log-likelihood values after training for 400,000 steps with a batch size of 100 for different number of particles (`k`) and `test_k = 5000`.\n\n|k| NLL (MNIST) | NLL (OMNIGLOT) |\n|:----:|:----:|:----:|\n| 1  | 90.26 | 114.68 |\n| 5  | 88.49 | 112.25 |\n| 50 | 87.34 | 110.31 |\n\n### References\n[1] Burda, Y., Grosse, R. and Salakhutdinov, R., 2015. Importance Weighted Autoencoders. arXiv preprint arXiv:1509.00519.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabdulfatir%2Fiwae-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fabdulfatir%2Fiwae-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabdulfatir%2Fiwae-tensorflow/lists"}