{"id":21069529,"url":"https://github.com/wolny/keras-image-net","last_synced_at":"2026-05-03T17:34:58.464Z","repository":{"id":140897134,"uuid":"96344537","full_name":"wolny/keras-image-net","owner":"wolny","description":"Simple REST app for image classification using Keras pre-trained deep learning models","archived":false,"fork":false,"pushed_at":"2017-07-06T10:34:01.000Z","size":53,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-01-15T21:38:26.343Z","etag":null,"topics":["flask","image-classification","keras-neural-networks","keras-tensorflow","tensorflow"],"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/wolny.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":"2017-07-05T17:28:19.000Z","updated_at":"2024-06-19T23:18:25.000Z","dependencies_parsed_at":"2024-06-14T09:15:36.965Z","dependency_job_id":null,"html_url":"https://github.com/wolny/keras-image-net","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/wolny/keras-image-net","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wolny%2Fkeras-image-net","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wolny%2Fkeras-image-net/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wolny%2Fkeras-image-net/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wolny%2Fkeras-image-net/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wolny","download_url":"https://codeload.github.com/wolny/keras-image-net/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wolny%2Fkeras-image-net/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32578854,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-03T06:36:36.687Z","status":"ssl_error","status_checked_at":"2026-05-03T06:36:09.306Z","response_time":103,"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":["flask","image-classification","keras-neural-networks","keras-tensorflow","tensorflow"],"created_at":"2024-11-19T18:35:59.698Z","updated_at":"2026-05-03T17:34:58.442Z","avatar_url":"https://github.com/wolny.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# keras-image-net\nSimple REST app for image classification using [Keras pre-trained deep learning models](https://keras.io/applications/).\nBy default the app uses [pre-trained ResNet-50 model](https://github.com/KaimingHe/deep-residual-networks) described in the paper \"Deep Residual Learning for Image Recognition\"\n```\n@article{He2015,\n\tauthor = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},\n\ttitle = {Deep Residual Learning for Image Recognition},\n\tjournal = {arXiv preprint arXiv:1512.03385},\n\tyear = {2015}\n}\n```\n\n## Run (Docker)\n```\ndocker build -t keras-image-net .\ndocker run -p 5000:5000 keras-image-net\n# wait for models to be loaded\n# test with: curl -v http://localhost:5000/detect?imageUrl=\u003cimageUrl\u003e, e.g.\ncurl -v http://localhost:5000/detect?imageUrl=http://expressioncoffins.com.au/wp-content/uploads/2012/06/RED-TRACTOR1.jpg\n```\nYou should get the following response:\n```\n{\n\"imageUrl\": \"http://expressioncoffins.com.au/wp-content/uploads/2012/06/RED-TRACTOR1.jpg\",\n\"results\": [\n  {\n    \"score\": 0.6732403039932251,\n    \"label\": \"tractor\"\n  },\n  {\n    \"score\": 0.3161275088787079,\n    \"label\": \"plow\"\n  },\n  {\n    \"score\": 0.010076208040118217,\n    \"label\": \"harvester\"\n  },\n  {\n    \"score\": 0.00041331720422022045,\n    \"label\": \"thresher\"\n  },\n  {\n    \"score\": 0.00006622869841521606,\n    \"label\": \"hay\"\n  }]\n}\n```\n\n## Run (command line)\nMake sure you have Keras installed, then just\n```\npython src/res-net-50.py\n```\nYou should see:\n```\n('Predicted:', [(u'n02106662', u'German_shepherd', 0.99324906), (u'n02096051', u'Airedale', 0.0033434019), (u'n02105162', u'malinois', 0.0015451796), (u'n03803284', u'muzzle', 0.0005292811), (u'n02091635', u'otterhound', 0.00021379442)])\n```\n\n## Run (GCP)\n\n```\ndocker build -t eu.gcr.io/$PROJECT_NAME/keras-res-net .\ngcloud docker -- push eu.gcr.io/$PROJECT_NAME/keras-res-net\nkubectl run keras-res-net --image=eu.gcr.io/$PROJECT_NAME/keras-res-net --port=5000 --replicas=2\nkubectl expose deployment keras-res-net --type=LoadBalancer --name=keras-res-net\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwolny%2Fkeras-image-net","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwolny%2Fkeras-image-net","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwolny%2Fkeras-image-net/lists"}