{"id":13499024,"url":"https://github.com/kentsommer/keras-inceptionV4","last_synced_at":"2025-03-29T03:32:17.361Z","repository":{"id":59643479,"uuid":"79427137","full_name":"kentsommer/keras-inceptionV4","owner":"kentsommer","description":"Keras Implementation of Google's Inception-V4 Architecture (includes Keras compatible pre-trained weights)","archived":false,"fork":false,"pushed_at":"2017-09-10T05:47:38.000Z","size":1712,"stargazers_count":472,"open_issues_count":2,"forks_count":176,"subscribers_count":21,"default_branch":"master","last_synced_at":"2024-10-31T17:39:06.522Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kentsommer.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}},"created_at":"2017-01-19T07:25:31.000Z","updated_at":"2024-10-27T15:18:54.000Z","dependencies_parsed_at":"2022-09-19T18:41:25.513Z","dependency_job_id":null,"html_url":"https://github.com/kentsommer/keras-inceptionV4","commit_stats":null,"previous_names":[],"tags_count":4,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kentsommer%2Fkeras-inceptionV4","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kentsommer%2Fkeras-inceptionV4/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kentsommer%2Fkeras-inceptionV4/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kentsommer%2Fkeras-inceptionV4/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kentsommer","download_url":"https://codeload.github.com/kentsommer/keras-inceptionV4/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246135766,"owners_count":20729056,"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":[],"created_at":"2024-07-31T22:00:26.408Z","updated_at":"2025-03-29T03:32:16.487Z","avatar_url":"https://github.com/kentsommer.png","language":"Python","funding_links":[],"categories":["Papers\u0026Codes"],"sub_categories":["Inceptionv4 \u0026\u0026 Inception-ResNetv2"],"readme":"# Keras Inception-V4\nKeras implementation of Google's inception v4 model with ported weights!\n\nAs described in:\n[Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi)](https://arxiv.org/abs/1602.07261)\n\nNote this Keras implementation tries to follow the [tf.slim definition](https://github.com/tensorflow/models/blob/master/slim/nets/inception_v4.py) as closely as possible.\n\nPre-Trained weights for this Keras model can be found here (ported from the tf.slim ckpt): https://github.com/kentsommer/keras-inceptionV4/releases\n\nYou can evaluate a sample image by performing the following (weights are downloaded automatically):\n* ```$ python evaluate_image.py```\n```\nLoaded Model Weights!\nClass is: African elephant, Loxodonta africana\nCertainty is: 0.868498\n```\n\n# News\n5/23/2017:\n\n* Enabled support for both Theano and Tensorflow (again... :neckbeard:)\n* Added useful training parameters \n  * l2 regularization added to conv layers\n  * Variance Scaling initialization added to conv layers\n  * Momentum value updated for batch_norm layers\n* Updated pre-processing to match paper (subtracts 0.5 instead of 1.0 :fire:)\n* Minor code changes and cleanup is also included in the recent changes\n\n\n\n\n# Performance Metrics (@Top5, @Top1)\n\nError rate on non-blacklisted subset of ILSVRC2012 Validation Dataset (Single Crop):\n* Top@1 Error: 19.54%\n* Top@5 Error: 4.88%\n\nThese error rates are actually slightly lower than the listed error rates in the paper:\n* Top@1 Error: 20.0%\n* Top@5 Error: 5.0%\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkentsommer%2Fkeras-inceptionV4","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkentsommer%2Fkeras-inceptionV4","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkentsommer%2Fkeras-inceptionV4/lists"}