{"id":17053956,"url":"https://github.com/vertexclique/evren","last_synced_at":"2026-04-13T20:01:51.347Z","repository":{"id":145767559,"uuid":"120447449","full_name":"vertexclique/evren","owner":"vertexclique","description":"Machine Learning model optimizer and exporter for embedded systems and mobile platforms","archived":false,"fork":false,"pushed_at":"2018-02-07T17:31:45.000Z","size":17,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-23T05:44:17.308Z","etag":null,"topics":["android","android-ndk","core-ml","ios","machine-learning","mlkit","model-export"],"latest_commit_sha":null,"homepage":null,"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/vertexclique.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","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":"2018-02-06T11:45:49.000Z","updated_at":"2024-10-20T22:42:04.000Z","dependencies_parsed_at":null,"dependency_job_id":"f67a1ada-8fbc-4cdb-8f37-cdba4e05dce1","html_url":"https://github.com/vertexclique/evren","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/vertexclique/evren","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vertexclique%2Fevren","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vertexclique%2Fevren/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vertexclique%2Fevren/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vertexclique%2Fevren/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vertexclique","download_url":"https://codeload.github.com/vertexclique/evren/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vertexclique%2Fevren/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31768649,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T15:25:13.801Z","status":"ssl_error","status_checked_at":"2026-04-13T15:25:09.162Z","response_time":93,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["android","android-ndk","core-ml","ios","machine-learning","mlkit","model-export"],"created_at":"2024-10-14T10:13:42.526Z","updated_at":"2026-04-13T20:01:51.320Z","avatar_url":"https://github.com/vertexclique.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Evren\n\n![Evren](https://i.imgur.com/ZHrX1l3.png)\n\n[![Build Status](https://travis-ci.org/vertexclique/evren.svg?branch=master)](https://travis-ci.org/vertexclique/evren)\n[![codecov.io](https://codecov.io/gitlab/hbetts/orbitalpy/coverage.svg?branch=master)](https://codecov.io/gitlab/vertexclique/evren?branch=master)\n\n**NOTE:** Project is in experimental phase.\n\n**Evren** is pre-optimizer and exporter for machine learning models to embedded systems, android and iOS platforms.\nCurrently Android and iOS supported, for iOS it can export `caffe` and `keras` models, for Android it exports `keras` models.\nKeras models should use Tensorflow backend.\n\n## Installation\n\nAfter cloning use `tox` to setup environment.\n```bash\n$ tox\n```\n\n## Usage\n\nYou can find examples in `examples` directory. Documentation will be made available soon.\n\nMinimal export code can be:\n\n```python\nMODEL_NAME = \"dense_android_test\"\n\n# Define Keras model\nmodel = Sequential()\nmodel.add(Dense(10, input_shape=(10, 1)))\nmodel.add(Dense(10))\nmodel.add(Dense(10))\nmodel.add(Dense(10))\nmodel.add(Dense(10))\nmodel.add(Dense(10))\nmodel.add(Dense(1, activation='sigmoid'))\n\n# Train it in here, just because it is demonstration we ignore that\n# . . . . . . TRAINING . . . . . .\n\n# If you know the output nodes you\n# don't need to call underlying output nodes list\n\noutput_nodes = get_output_node_names()\n\n# Write Keras model with weights as protobuf file\n# for use with Tensorflow Lite and Android NDK\n# It will produce `dense_android_test.pb` with weights embedded in.\nexport_keras_to_file(model_name=MODEL_NAME,\n                     input_names=map(str, range(1, 10)),\n                     output_names=output_nodes,\n                     out_file_name=MODEL_NAME)\n```\n\n## TODO\n\n* Caffee export for Android\n* Extra optimization techniques for Android and iOS.\n* Travis setup with Tox.\n\n## Contributing\n\nRead [CONTRIBUTING](CONTRIBUTING.md).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvertexclique%2Fevren","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvertexclique%2Fevren","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvertexclique%2Fevren/lists"}