{"id":20262403,"url":"https://github.com/imvision12/convnext-tf","last_synced_at":"2025-09-22T10:33:06.628Z","repository":{"id":148880207,"uuid":"600452859","full_name":"IMvision12/ConvNeXt-tf","owner":"IMvision12","description":"A Tensorflow Implementation of \"A ConvNet for the 2020s\" and \"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders\" (ConvNeXt and ConvNeXtV2)","archived":false,"fork":false,"pushed_at":"2023-02-11T22:22:44.000Z","size":340,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-11-14T11:37:56.356Z","etag":null,"topics":["cnn","convnext","convnextv2","tensorflow"],"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/IMvision12.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":"2023-02-11T14:44:44.000Z","updated_at":"2024-09-09T14:16:40.000Z","dependencies_parsed_at":"2023-07-15T14:25:48.060Z","dependency_job_id":null,"html_url":"https://github.com/IMvision12/ConvNeXt-tf","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IMvision12%2FConvNeXt-tf","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IMvision12%2FConvNeXt-tf/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IMvision12%2FConvNeXt-tf/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IMvision12%2FConvNeXt-tf/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/IMvision12","download_url":"https://codeload.github.com/IMvision12/ConvNeXt-tf/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":233843150,"owners_count":18738935,"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":["cnn","convnext","convnextv2","tensorflow"],"created_at":"2024-11-14T11:29:39.068Z","updated_at":"2025-09-22T10:33:01.278Z","avatar_url":"https://github.com/IMvision12.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"### To-do\r\n- [x] Add convnextv1 and v2 pytorch\r\n- [x] convert pytorch to tensorflow\r\n- [ ] weight conversion\r\n\r\n# ConvNeXt and ConvNeXtV2\r\n\r\nThis repository is about an implementation of the research paper \"A ConvNet of the 2020s\" and \"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders\" using `Tensorflow`.\r\n\r\nConvNeXtV1 : ConvNeXt, a pure ConvNet model constructed entirely from standard ConvNet modules. ConvNeXts compete favorably with Transformers in terms of accuracy and scalability, achieving 87.8% ImageNet top-1 accuracy and outperforming Swin Transformers on COCO detection and ADE20K segmentation, while maintaining the simplicity and efficiency of standard ConvNets.\r\n\r\nConvNeXtV2: The paper proposed a fully convolutional masked autoencoder framework (FCMAE) and a new Global Response Normalization (GRN) layer to original ConvNeXtV1 model to enhance inter-channel feature competition. This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets on various recognition benchmarks.\r\n\r\n\u003cp align=\"center\"\u003e\r\n\u003cimg src=\"https://github.com/IMvision12/ConvNeXt-tf/blob/main/img/model_scaling.png\" width=50% height=50%\r\nclass=\"right\"\u003e\r\n\u003c/p\u003e\r\n\r\n### ConvNeXtV1 and ConvNeXtV2 block design:\r\n\r\n\u003cp align=\"center\"\u003e\r\n\u003cimg src=\"https://github.com/IMvision12/ConvNeXt-tf/blob/main/img/Capture.PNG\" width=40% height=40%\r\nclass=\"right\"\u003e\r\n\u003c/p\u003e\r\n\r\n# References\r\n\r\n[1] ConvNeXt paper: https://arxiv.org/abs/2201.03545\r\n\r\n[2] ConvNeXtV2 paper: https://arxiv.org/abs/2301.00808\r\n\r\n[3] Official ConvNeXt code: https://github.com/facebookresearch/ConvNeXt\r\n\r\n[4] Official ConvNeXtV2 code: https://github.com/facebookresearch/ConvNeXt-V2\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fimvision12%2Fconvnext-tf","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fimvision12%2Fconvnext-tf","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fimvision12%2Fconvnext-tf/lists"}