{"id":23623587,"url":"https://github.com/freedisch/ml-protocol","last_synced_at":"2025-11-07T08:30:29.434Z","repository":{"id":239690210,"uuid":"799643155","full_name":"Freedisch/ml-protocol","owner":"Freedisch","description":null,"archived":false,"fork":false,"pushed_at":"2024-11-12T15:30:33.000Z","size":7429,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-12-27T20:49:57.337Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/Freedisch.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":"2024-05-12T18:40:06.000Z","updated_at":"2024-11-12T15:30:37.000Z","dependencies_parsed_at":"2024-05-14T03:45:36.476Z","dependency_job_id":"b9c31a2a-8401-4929-b337-934c5afdef6a","html_url":"https://github.com/Freedisch/ml-protocol","commit_stats":null,"previous_names":["freedisch/ml-protocol"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Freedisch%2Fml-protocol","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Freedisch%2Fml-protocol/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Freedisch%2Fml-protocol/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Freedisch%2Fml-protocol/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Freedisch","download_url":"https://codeload.github.com/Freedisch/ml-protocol/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239523839,"owners_count":19653018,"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":"2024-12-27T20:49:41.757Z","updated_at":"2025-11-07T08:30:29.394Z","avatar_url":"https://github.com/Freedisch.png","language":"Jupyter Notebook","readme":"# Breast Cancer Image Classification using Transfer Learning\n\n## Dataset\n\nThe dataset contains images related to bread cancer. Each image has a corresponding mask image.\n\n## Pre-trained Models\n\nWe selected the following pre-trained models:\n\n- **VGG16**: Known for its simplicity and effectiveness in image classification tasks.\n- **ResNet50**: Utilizes residual learning, which allows training of very deep networks.\n- **InceptionV3**: Combines multiple filter sizes and network-in-network architectures, providing high accuracy.\n\n## Fine-Tuning\n\nWe fine-tuned the models by modifying the top layers and training them on the dataset. The following layers were modified:\n\n- **GlobalAveragePooling2D**: To reduce the feature maps.\n- **Dense (1024 units)**: Added for high-level features.\n- **Dense (1 unit)**: Output layer for binary classification with sigmoid activation.\n\n## Usage\n\nTo use this project:\n\n1. Clone the repository to your local machine.\n2. Ensure that the dataset is stored at the correct path, as specified in the notebook.\n3. Open the `Transfer_Learning_Assignment.ipynb` notebook in Jupyter or another IPython notebook viewer.\n4. Run the cells sequentially to perform the data preprocessing, model training, and evaluation.\n\n## Evaluation Metrics\n\nThe models are evaluated based on the following metrics:\n\n- Accuracy\n- Loss\n- Precision\n- Recall\n- F1 Score\n\nThese metrics are crucial for assessing the performance of the models, particularly in a medical context where accuracy and reliability are paramount.\n\n## Results\n\nThe results section will contain tables and charts generated from the notebook, providing a visual and quantitative comparison of the performance of the different models.\n\n## Contributions\n\nContributions to this project are welcome. You can contribute by improving the model training pipeline, introducing new models, or enhancing the data preprocessing steps.\n\n## License\n\nThis project is licensed under the MIT License - see the LICENSE file for details.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffreedisch%2Fml-protocol","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffreedisch%2Fml-protocol","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffreedisch%2Fml-protocol/lists"}