{"id":29638239,"url":"https://github.com/celestialtaha/convnext-tf-keras","last_synced_at":"2026-05-10T16:38:15.725Z","repository":{"id":115624678,"uuid":"450462389","full_name":"celestialtaha/ConvNeXt-tf-keras","owner":"celestialtaha","description":"tf-keras re-implementation of ConvNeXt (https://arxiv.org/abs/2201.03545) from Facebook Research.","archived":false,"fork":false,"pushed_at":"2022-01-22T01:22:12.000Z","size":48,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-21T19:26:59.009Z","etag":null,"topics":["2020s-convnets","classification","convnext","deep-learning","facebook-research","image-net","keras","modernized-conv","tensorflow2"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/celestialtaha.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,"zenodo":null}},"created_at":"2022-01-21T11:17:50.000Z","updated_at":"2025-01-07T23:12:49.000Z","dependencies_parsed_at":null,"dependency_job_id":"412da1c2-48c7-4b0a-a073-278fe86b89d7","html_url":"https://github.com/celestialtaha/ConvNeXt-tf-keras","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/celestialtaha/ConvNeXt-tf-keras","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/celestialtaha%2FConvNeXt-tf-keras","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/celestialtaha%2FConvNeXt-tf-keras/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/celestialtaha%2FConvNeXt-tf-keras/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/celestialtaha%2FConvNeXt-tf-keras/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/celestialtaha","download_url":"https://codeload.github.com/celestialtaha/ConvNeXt-tf-keras/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/celestialtaha%2FConvNeXt-tf-keras/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32864082,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-10T13:40:02.631Z","status":"ssl_error","status_checked_at":"2026-05-10T13:40:02.145Z","response_time":54,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["2020s-convnets","classification","convnext","deep-learning","facebook-research","image-net","keras","modernized-conv","tensorflow2"],"created_at":"2025-07-21T19:07:11.253Z","updated_at":"2026-05-10T16:38:15.714Z","avatar_url":"https://github.com/celestialtaha.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ConvNeXt-tf-keras\ntf-keras re-implementation of ConvNeXt [1] from Facebook Research.\n\n\n![image](ResNet_vs_ConvNeXt.png)\n\n# Usage\nThere are two ways one can use this implementation:\n  * Notebook (.ipynb)\n    - Simply run the cells\n  * .py file\n\n## Example of using .py version\n```python\nfrom main import create_convnext_model\n\nmodel = create_convnext_model(input_shape=(224, 224, 3), depths=[3, 3, 9, 3], dims=[96, 192, 384, 768], num_classes=1000)\nprint(model.summary())\n\nmodel = create_convnext_model(depths=[3, 3, 9, 3], dims=[96, 192, 384, 768], num_classes=1000, drop_path=2., layer_scale_init_value=1e-6)\nprint(model.summary())\n```\n\n# References\nPaper:\n\n[1] [A ConvNet for the 2020s](https://arxiv.org/abs/2201.03545)\n\nCode:\n\n[2] https://github.com/facebookresearch/ConvNeXt\n\n[3] https://github.com/rishigami/Swin-Transformer-TF\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcelestialtaha%2Fconvnext-tf-keras","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcelestialtaha%2Fconvnext-tf-keras","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcelestialtaha%2Fconvnext-tf-keras/lists"}