{"id":18605513,"url":"https://github.com/manohara-ai/hand_written_digit_recognizer","last_synced_at":"2025-06-16T23:34:10.182Z","repository":{"id":253513055,"uuid":"843735143","full_name":"Manohara-Ai/Hand_Written_Digit_Recognizer","owner":"Manohara-Ai","description":"Building a CNN to identify hand written digits","archived":false,"fork":false,"pushed_at":"2024-12-08T10:37:38.000Z","size":103,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-31T02:41:44.570Z","etag":null,"topics":["cnn","machine-learning","multiclass-image-classification","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":"2024-08-17T09:00:57.000Z","updated_at":"2024-12-08T10:37:42.000Z","dependencies_parsed_at":null,"dependency_job_id":"e7931719-166f-467b-baf5-cb93e5fd0eb8","html_url":"https://github.com/Manohara-Ai/Hand_Written_Digit_Recognizer","commit_stats":null,"previous_names":["manohara-ai/hand_written_digit_recognizer"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Manohara-Ai%2FHand_Written_Digit_Recognizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Manohara-Ai%2FHand_Written_Digit_Recognizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Manohara-Ai%2FHand_Written_Digit_Recognizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Manohara-Ai%2FHand_Written_Digit_Recognizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Manohara-Ai","download_url":"https://codeload.github.com/Manohara-Ai/Hand_Written_Digit_Recognizer/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252769128,"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":["cnn","machine-learning","multiclass-image-classification","tinyvgg"],"created_at":"2024-11-07T02:21:47.083Z","updated_at":"2025-05-06T20:45:32.679Z","avatar_url":"https://github.com/Manohara-Ai.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Handwritten Digit Recognition using CNN\n\nThis project implements a Convolutional Neural Network (CNN) similar to the TinyVGG architecture to recognize handwritten digits. The model was trained on the MNIST dataset and tested on custom handwritten digits.\n\n## Model Overview\n\nThe CNN architecture is inspired by TinyVGG and consists of multiple convolutional layers followed by ReLU activation, max-pooling, and fully connected layers. The model achieved **98.12% accuracy (on random seed and accuracy can be better/ worse on other seeds)** on both the MNIST test data and custom handwritten digits created using GIMP.\n\n## Dataset\n\n- **Training Data:** MNIST dataset of handwritten digits (60,000 training images)\n- **Testing Data:** MNIST test set (10,000 images) and custom images created in GIMP\n\n## Results\n\nThe model achieved:\n- **98.12% accuracy (on random seed and accuracy can be better/ worse on other seeds)** on custom handwritten digits\n\n## Requirements\n\nTo run this project, you will need the following dependencies:\n\n- Python 3.x\n- PyTorch\n- OpenCV\n- NumPy\n- Matplotlib\n\nNOTE: The images in MNIST dataset, on which the model are greyscale and 28x28 pixels in size. So, ensure to test on images of same size and color channels.\n\n## Contributor\nB M Manohara @Manohara-Ai\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanohara-ai%2Fhand_written_digit_recognizer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmanohara-ai%2Fhand_written_digit_recognizer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmanohara-ai%2Fhand_written_digit_recognizer/lists"}