{"id":15645079,"url":"https://github.com/philipperemy/tensorflow-maxout","last_synced_at":"2025-08-12T22:38:32.743Z","repository":{"id":70249854,"uuid":"77984796","full_name":"philipperemy/tensorflow-maxout","owner":"philipperemy","description":"Maxout Networks TensorFlow implementation presented in https://arxiv.org/abs/1302.4389","archived":false,"fork":false,"pushed_at":"2018-12-19T07:31:57.000Z","size":78,"stargazers_count":56,"open_issues_count":0,"forks_count":17,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-30T12:06:01.347Z","etag":null,"topics":["maxout","maxout-networks","tensorflow","tensorflow-maxout"],"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/philipperemy.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":"2017-01-04T05:42:12.000Z","updated_at":"2024-08-12T19:26:56.000Z","dependencies_parsed_at":"2023-03-04T00:00:57.976Z","dependency_job_id":null,"html_url":"https://github.com/philipperemy/tensorflow-maxout","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/philipperemy/tensorflow-maxout","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/philipperemy%2Ftensorflow-maxout","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/philipperemy%2Ftensorflow-maxout/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/philipperemy%2Ftensorflow-maxout/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/philipperemy%2Ftensorflow-maxout/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/philipperemy","download_url":"https://codeload.github.com/philipperemy/tensorflow-maxout/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/philipperemy%2Ftensorflow-maxout/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270148215,"owners_count":24535696,"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","status":"online","status_checked_at":"2025-08-12T02:00:09.011Z","response_time":80,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["maxout","maxout-networks","tensorflow","tensorflow-maxout"],"created_at":"2024-10-03T12:04:23.506Z","updated_at":"2025-08-12T22:38:32.713Z","avatar_url":"https://github.com/philipperemy.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Maxout Networks (Ian Goodfellow, Yoshua Bengio - 2013)\nMaxout Networks TensorFlow implementation presented in https://arxiv.org/abs/1302.4389\n\n## How to run the MNIST experiment?\n\n```bash\n# make sure Tensorflow is installed.\ngit clone git@github.com:philipperemy/tensorflow-maxout.git maxout \u0026\u0026 cd maxout\npython mnist_maxout_example.py MAXOUT # Can pick up from one of those values: LINEAR, RELU, MAXOUT.\n```\n\n## How to integrate it in your code\n\nIt's two lines of code. Sorry I can't make it shorter.\n\n```python\nfrom maxout import max_out\ny = tf.matmul(x, W1) + b1\nt = max_out(y, num_units=50)\n```\n\n# Some Results on MNIST dataset\n\nThose results are not meant to reproduce the results of the paper. It's more about showing on how to use the maxout non linearity in the Tensorflow graphs.\n\n## Loss\n\nAs expected, Maxout strictly outperforms Sigmoid and ReLU. Having one hidden layer + non linearity helps to have a smaller loss.\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"fig/mnist.png\" width=\"400\"\u003e\u003cbr\u003e\u003cbr\u003e\n\u003c/div\u003e\n\n## Accuracy\n\n| Model      | Accuracy (100 epochs) | \n| ------------- |:-------------:|\n| MLP Hidden MaxOut      | 0.9730 |\n| MLP Hidden ReLU       |  0.9704      |\n| MLP Hidden Sigmoid | 0.9353      |\n| MLP Linear | 0.9214      |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fphilipperemy%2Ftensorflow-maxout","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fphilipperemy%2Ftensorflow-maxout","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fphilipperemy%2Ftensorflow-maxout/lists"}