{"id":21477786,"url":"https://github.com/perpendicularai/imageclassification","last_synced_at":"2025-03-17T08:22:20.691Z","repository":{"id":215238133,"uuid":"738440970","full_name":"perpendicularai/imageclassification","owner":"perpendicularai","description":"A deep-learning notebook to detect real or fake faces. Now comes with it's own PyPI module. ","archived":false,"fork":false,"pushed_at":"2024-02-13T01:59:05.000Z","size":907,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-25T05:17:00.669Z","etag":null,"topics":["convolutional-neural-networks","deep-learning","deep-neural-networks","image-classification"],"latest_commit_sha":null,"homepage":"https://perpendicular.web.za","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/perpendicularai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-01-03T08:30:45.000Z","updated_at":"2024-06-20T07:14:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"42c43aa4-b9ae-4700-875b-770cb6087ba7","html_url":"https://github.com/perpendicularai/imageclassification","commit_stats":{"total_commits":24,"total_committers":2,"mean_commits":12.0,"dds":0.04166666666666663,"last_synced_commit":"9fe259e6656cfc38882992deb819f31fbbf1bb4f"},"previous_names":["perpendicularai/imageclassification"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/perpendicularai%2Fimageclassification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/perpendicularai%2Fimageclassification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/perpendicularai%2Fimageclassification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/perpendicularai%2Fimageclassification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/perpendicularai","download_url":"https://codeload.github.com/perpendicularai/imageclassification/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243997170,"owners_count":20380981,"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":["convolutional-neural-networks","deep-learning","deep-neural-networks","image-classification"],"created_at":"2024-11-23T11:15:05.925Z","updated_at":"2025-03-17T08:22:20.670Z","avatar_url":"https://github.com/perpendicularai.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"![image](https://github.com/perpendicularai/imageclassification/assets/146530480/6938491a-8670-47a1-8cb8-aed6fcad5978)\n\n\n\n# Binary Classification\n\nThis repo his been put together to showcase the ability of using deep-learning to train a binary classification model. The model in particular has been trained to detect between real and fake faces. This is ideal for locations that require a high degree of security, whether it be banks, airports, government buildings, schools to name a few. The dataset used to train the model is 4GB's in size. A link is provided below. The model was trained for 100 epochs on an Intel i5 CPU with 8GB's of RAM, and thus can be deployed on most systems. \n\n## How to :\n* Download dataset - [fakeface_dataset](https://www.kaggle.com/datasets/xhlulu/140k-real-and-fake-faces)\n*  Set train and test data paths in the notebook provided\n* Once model has been trained, run the following command to save the model to be used for inference `model.save('MODEL_DIRECTORY_NAME')`. This will save all the model files to your current directory in the directory name you provided.\n* A test image has been provided of someone that does not exist. The image was generated using a popular GAN. See [test_image](https://github.com/perpendicularai/imageclassification/tree/main/test_image/) directory for more.\n\n## Alternatively :\nIf you would like to get started right away with inference on an image, see [PyPI_HOWTO.md](https://github.com/perpendicularai/imageclassification/blob/main/PyPI_HOWTO.md)\n\n## Training stats :\n* Accuracy -\n![image](https://github.com/perpendicularai/imageclassification/assets/146530480/df14fb83-568b-478b-8394-2022b3409818)\n\n* Loss -\n![image](https://github.com/perpendicularai/imageclassification/assets/146530480/743fbaf9-58a8-49e9-befe-9e3f32507597)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fperpendicularai%2Fimageclassification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fperpendicularai%2Fimageclassification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fperpendicularai%2Fimageclassification/lists"}