{"id":26901646,"url":"https://github.com/thatlinuxguyyouknow/mnist-digit-classifier","last_synced_at":"2025-04-01T08:54:55.083Z","repository":{"id":281491401,"uuid":"943841539","full_name":"ThatLinuxGuyYouKnow/MNIST-Digit-Classifier","owner":"ThatLinuxGuyYouKnow","description":"A simple KERAS based CNN trained on the MSINT Dataset","archived":false,"fork":false,"pushed_at":"2025-03-09T12:49:50.000Z","size":7535,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-09T13:34:23.868Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/ThatLinuxGuyYouKnow.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":"2025-03-06T10:59:41.000Z","updated_at":"2025-03-09T12:49:53.000Z","dependencies_parsed_at":"2025-03-09T13:34:25.266Z","dependency_job_id":"2e2f4a67-226f-415a-b0ca-be44e76a0005","html_url":"https://github.com/ThatLinuxGuyYouKnow/MNIST-Digit-Classifier","commit_stats":null,"previous_names":["thatlinuxguyyouknow/mnist-digit-classifier"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ThatLinuxGuyYouKnow%2FMNIST-Digit-Classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ThatLinuxGuyYouKnow%2FMNIST-Digit-Classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ThatLinuxGuyYouKnow%2FMNIST-Digit-Classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ThatLinuxGuyYouKnow%2FMNIST-Digit-Classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ThatLinuxGuyYouKnow","download_url":"https://codeload.github.com/ThatLinuxGuyYouKnow/MNIST-Digit-Classifier/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246612485,"owners_count":20805354,"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":"2025-04-01T08:54:54.476Z","updated_at":"2025-04-01T08:54:55.078Z","avatar_url":"https://github.com/ThatLinuxGuyYouKnow.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MNIST Digit Classifier\n\n[![Python](https://img.shields.io/badge/python-3.x-blue.svg)](https://www.python.org/)\n[![TensorFlow](https://img.shields.io/badge/TensorFlow-2.x-orange.svg)](https://www.tensorflow.org/)\n[![NumPy](https://img.shields.io/badge/NumPy-1.x-green.svg)](https://numpy.org/)\n[![Pillow](https://img.shields.io/badge/Pillow-x.x-purple.svg)](https://pillow.readthedocs.io/en/stable/)\n\n\nThis project is a backend-only Python application that trains, evaluates, and tests a Convolutional Neural Network (CNN) model for classifying handwritten digits from the MNIST dataset.  It uses TensorFlow/Keras for model building and training, NumPy for numerical operations, and Pillow for image manipulation.\n\n## Accessible Routes \u0026 Methods\n\nThe application is run from the command line and doesn't have traditional web routes.  Instead, it offers the following command-line actions:\n\n\n* **`python main.py train`**:  Trains the MNIST model using the MNIST dataset.  No parameters are required. This command saves the model to `mnist_model.h5`\n\n* **`python main.py evaluate`**: Loads the model from `mnist_model.h5` and evaluates its performance on the MNIST test dataset. Prints the test accuracy. No parameters are required.\n\n* **`python main.py test`**: Loads the model from `mnist_model.h5` and uses it to predict the digit in `test.png`.  Requires a `test.png` image in the same directory.  The image should be a 28x28 grayscale image of a handwritten digit.\n\n* **`python main.py easy`**: Loads the model from `mnist_model.h5` and uses it to predict the digit in `test_easy.png`. Requires a `test_easy.png` image in the same directory.  The image should be a 28x28 grayscale image of a handwritten digit.\n\n\nAll actions use the `GET` method implicitly through command-line arguments.  No parameters are passed directly as part of a request, but the presence or absence of specific files (e.g., `test.png`) indirectly influences the behavior.  Error handling is implemented to gracefully handle the absence of a trained model or required image files.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthatlinuxguyyouknow%2Fmnist-digit-classifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthatlinuxguyyouknow%2Fmnist-digit-classifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthatlinuxguyyouknow%2Fmnist-digit-classifier/lists"}