{"id":13499026,"url":"https://github.com/titu1994/Inception-v4","last_synced_at":"2025-03-29T03:32:18.173Z","repository":{"id":150946785,"uuid":"61495087","full_name":"titu1994/Inception-v4","owner":"titu1994","description":"Inception-v4, Inception - Resnet-v1 and v2 Architectures in Keras","archived":false,"fork":false,"pushed_at":"2017-09-07T23:05:54.000Z","size":17136,"stargazers_count":385,"open_issues_count":5,"forks_count":171,"subscribers_count":19,"default_branch":"master","last_synced_at":"2025-03-22T10:42:39.250Z","etag":null,"topics":["deep-learning","inception-resnet","keras","paper"],"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/titu1994.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}},"created_at":"2016-06-19T18:50:15.000Z","updated_at":"2025-02-16T20:44:14.000Z","dependencies_parsed_at":"2023-08-01T09:01:20.044Z","dependency_job_id":null,"html_url":"https://github.com/titu1994/Inception-v4","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/titu1994%2FInception-v4","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/titu1994%2FInception-v4/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/titu1994%2FInception-v4/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/titu1994%2FInception-v4/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/titu1994","download_url":"https://codeload.github.com/titu1994/Inception-v4/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":["deep-learning","inception-resnet","keras","paper"],"created_at":"2024-07-31T22:00:26.535Z","updated_at":"2025-03-29T03:32:17.567Z","avatar_url":"https://github.com/titu1994.png","language":"Python","funding_links":[],"categories":["Papers\u0026Codes"],"sub_categories":["Inceptionv4 \u0026\u0026 Inception-ResNetv2"],"readme":"# Inception v4 in Keras\nImplementations of the Inception-v4, Inception - Resnet-v1 and v2 Architectures in Keras using the Functional API. The paper on these architectures is available at \u003ca href=\"http://arxiv.org/pdf/1602.07261v1.pdf\"\u003e\u003cb\u003e\"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning\"\u003c/b\u003e\u003c/a\u003e. \n\nThe models are plotted and shown in the architecture sub folder. Due to lack of suitable training data (ILSVR 2015 dataset) and limited GPU processing power, the weights are not provided. \n\n## Inception v4\nThe python script '\u003cb\u003einception_v4.py\u003c/b\u003e' contains the methods necessary to create the Inception v4 network. \n\nUsage:\n```\nfrom inception_v4 import create_inception_v4\n\nmodel = create_inception_v4()\n\n```\n\n## Inception ResNet v1\nThe python script '\u003cb\u003einception_resnet_v1.py\u003c/b\u003e' contains the methods necessary to create the Inception ResNet v1 network. \nIt is to be noted that scaling of the residuals is turned \u003cb\u003eOFF\u003c/b\u003e by default. This can be rectified by supplying 'scale=True' in the create method.\n\nUsage:\n```\nfrom inception_resnet_v1 import create_inception_resnet_v1\n\nmodel = create_inception_resnet_v1()\n\n```\n\n## Inception ResNet v2\nThe python script '\u003cb\u003einception_resnet_v2.py\u003c/b\u003e' contains the methods necessary to create the Inception ResNet v2 network. \nIt is to be noted that scaling of the residuals is turned \u003cb\u003eON\u003c/b\u003e by default. \n\nThere are a few differences in the v2 network from the original paper:\u003cbr\u003e\n\u003cb\u003e[1]\u003c/b\u003e In the B blocks: 'ir_conv' nb of filters  is given as 1154 in the paper, however input size is 1152.\u003cbr\u003e\n    This causes inconsistencies in the merge-sum mode, therefore the 'ir_conv' filter size\n    is reduced to 1152 to match input size.\n    \u003cbr\u003e\n\u003cb\u003e[2]\u003c/b\u003e In the C blocks: 'ir_conv' nb of filter is given as 2048 in the paper, however input size is 2144.\u003cbr\u003e\n    This causes inconsistencies in the merge-sum mode, therefore the 'ir_conv' filter size\n    is increased to 2144 to match input size.\n    \nUsage:\n```\nfrom inception_resnet_v2 import create_inception_resnet_v2\n\nmodel = create_inception_resnet_v2(scale=True)\n```\n\n# Architectures\n## Inception v4\n\n\u003cimg src=\"https://github.com/titu1994/Inception-v4/blob/master/Architectures/Inception-v4.png?raw=true\"\u003e\n\n## Inception ResNet v1\n\n\u003cimg src=\"https://github.com/titu1994/Inception-v4/blob/master/Architectures/Inception%20ResNet-v1.png?raw=true\"\u003e\n\n## Inception ResNet v2\n\n\u003cimg src=\"https://github.com/titu1994/Inception-v4/blob/master/Architectures/Inception%20ResNet-v2.png?raw=true\"\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftitu1994%2FInception-v4","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftitu1994%2FInception-v4","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftitu1994%2FInception-v4/lists"}