{"id":18605504,"url":"https://github.com/manohara-ai/tinyvgg_inspired_binary_classifier","last_synced_at":"2025-05-06T20:43:37.772Z","repository":{"id":256624819,"uuid":"855959040","full_name":"Manohara-Ai/TinyVGG_Inspired_Binary_Classifier","owner":"Manohara-Ai","description":"This project implements a Convolutional Neural Network (CNN) binary classifier inspired by the TinyVGG architecture.","archived":false,"fork":false,"pushed_at":"2024-12-08T10:40:44.000Z","size":24,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-31T02:41:19.269Z","etag":null,"topics":["binary-classifier","cnn-classification","machine-learning","tinyvgg"],"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/Manohara-Ai.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":"2024-09-11T18:33:43.000Z","updated_at":"2024-12-08T10:40:47.000Z","dependencies_parsed_at":null,"dependency_job_id":"940071c1-c77a-4512-b66d-1cd4535fdce5","html_url":"https://github.com/Manohara-Ai/TinyVGG_Inspired_Binary_Classifier","commit_stats":null,"previous_names":["manohara-ai/tinyvgg_inspired_binary_classifier"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Manohara-Ai%2FTinyVGG_Inspired_Binary_Classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Manohara-Ai%2FTinyVGG_Inspired_Binary_Classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Manohara-Ai%2FTinyVGG_Inspired_Binary_Classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Manohara-Ai%2FTinyVGG_Inspired_Binary_Classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Manohara-Ai","download_url":"https://codeload.github.com/Manohara-Ai/TinyVGG_Inspired_Binary_Classifier/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252768988,"owners_count":21801373,"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":["binary-classifier","cnn-classification","machine-learning","tinyvgg"],"created_at":"2024-11-07T02:21:43.359Z","updated_at":"2025-05-06T20:43:37.732Z","avatar_url":"https://github.com/Manohara-Ai.png","language":"Python","readme":"# TinyVGG-inspired CNN Binary Classifier\n\nThis project implements a Convolutional Neural Network (CNN) binary classifier inspired by the TinyVGG architecture. The model is designed for binary classification tasks where the goal is to categorize input images into two classes.\n\n## Table of Contents\n- [Model Architecture](#model-architecture)\n- [Requirements](#requirements)\n- [Usage](#usage)\n- [Training and Evaluation](#training-and-evaluation)\n- [Contributor](#contributor)\n\n## Model Architecture\n\nThe CNN model is based on the TinyVGG architecture with modifications for binary classification. The architecture consists of:\n- Multiple convolutional layers followed by max-pooling.\n- ReLU activation functions after each convolution.\n- Fully connected layers at the end to output a binary classification decision.\n\n**Key Features:**\n- Lightweight model, suitable for small datasets.\n- Two output nodes using softmax activation for binary classification.\n\n### Architecture Overview:\n```\nConv2D -\u003e ReLU -\u003e MaxPooling\nConv2D -\u003e ReLU -\u003e MaxPooling\nFlatten -\u003e Fully Connected -\u003e ReLU\nFully Connected -\u003e Output (Softmax for binary classification)\n```\n\n## Requirements\n\nTo run this project, the following packages are required:\n- Python 3.x\n- PyTorch\n- OpenCV (for image preprocessing)\n- NumPy\n- Matplotlib (for visualizations)\n- tqdm (for progress tracking)\n\nYou can install the required packages using `pip`:\n\n```bash\npip install torch torchvision opencv-python numpy matplotlib tqdm\n```\n\n## Usage\n\n1. **Data Preparation:**\n   - Place your training and validation images in respective folders: `datasets/train/` and `datasets/val/`, with subfolders for each class (e.g., `class0/`, `class1/`).\n\n2. **Dataset:**\n   - For this project, you can use the dataset from Kaggle: [Binary Image Classification Dataset](https://www.kaggle.com/datasets/hasnainkhan0123/binary-image-classification)\n\n## Training and Evaluation\n\nTo the train, evaluate and test the model, make necessary changes and run the main script.\n\n   - The script will output accuracy, loss, and other metrics for evaluation.\n\n## Contributor\n\nThis project is developed by B M Manohara @Manohara-Ai\n\n---\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanohara-ai%2Ftinyvgg_inspired_binary_classifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmanohara-ai%2Ftinyvgg_inspired_binary_classifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanohara-ai%2Ftinyvgg_inspired_binary_classifier/lists"}