{"id":15907947,"url":"https://github.com/nathanielsimard/numpy-mnist-classifier","last_synced_at":"2026-04-29T17:34:31.418Z","repository":{"id":93803005,"uuid":"165151093","full_name":"nathanielsimard/numpy-mnist-classifier","owner":"nathanielsimard","description":"Feed forward neural network using Numpy for MNIST classification.","archived":false,"fork":false,"pushed_at":"2019-02-01T01:14:14.000Z","size":502,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-08T14:11:17.159Z","etag":null,"topics":["deep-learning","machine-learning","mnist","mnist-classification","mnist-classifier","numpy"],"latest_commit_sha":null,"homepage":"","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/nathanielsimard.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":"2019-01-11T00:20:49.000Z","updated_at":"2019-04-02T08:41:49.000Z","dependencies_parsed_at":"2023-03-13T05:45:31.920Z","dependency_job_id":null,"html_url":"https://github.com/nathanielsimard/numpy-mnist-classifier","commit_stats":{"total_commits":8,"total_committers":1,"mean_commits":8.0,"dds":0.0,"last_synced_commit":"aa27c8e689bf6b98a5dabafa576f51020e1b6d96"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nathanielsimard%2Fnumpy-mnist-classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nathanielsimard%2Fnumpy-mnist-classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nathanielsimard%2Fnumpy-mnist-classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nathanielsimard%2Fnumpy-mnist-classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nathanielsimard","download_url":"https://codeload.github.com/nathanielsimard/numpy-mnist-classifier/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246911489,"owners_count":20853654,"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":["deep-learning","machine-learning","mnist","mnist-classification","mnist-classifier","numpy"],"created_at":"2024-10-06T14:06:59.191Z","updated_at":"2026-04-29T17:34:26.382Z","avatar_url":"https://github.com/nathanielsimard.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Numpy Mnist Classifier\n\nThis project was done for learning purpose.\nThe goal was to implement a deep neural network to do supervised learning.\nThe MNIST data set was used due to its small size, making the learning process fast enough on a personal laptop.\n\nTo try the project you first need to install the dependencies, note that `python3` is required.\n\n```bash\npip install -r requirements/basic.txt\n```\n\n## Usage\n\nIt only takes a small amount of code to test some models :\n\n```python\n    from classifier import nn, training\n    from data import mnist\n\n    # The MNIST data set will be automatically downloaded and cached.\n    training_data, validation_data, test_data = mnist.load()\n\n    # Create a Neural Network with one hidden layer.\n    model = nn.NeuralNetwork([784, 30, 10], learning_rate=0.02, batch_size=50)\n\n    # Train the model with early stopping regularization.\n    model_training = training.EarlyStoppingRegularization(model,\n                                                          training_data,\n                                                          validation_data,\n                                                          test_data,\n                                                          max_steps_without_progression=2)\n    model_training.train()\n\n    # It is possible to save the result which serializes the model and create a report.\n    result.save('models/mnist-example')\n\n    # It is possible to load the trained model for futur uses.\n    model_trained = nn.load('models/mnist-example/model.pkl)\n```\n\n## Report Example\n\n## Model\n\n- Layers : [784, 30, 10]\n- Activation : sigmoid\n- Learning Rate : 0.02\n- Batch Size : 50\n\n## Training\n\n- Method : early stopping regularization\n- Epochs : 69\n\n## Data\n\nSize :\n\n- Training : 50000\n- Test : 10000\n- Validation : 10000\n\n### Sample\n\n![graph](./assets/sample.png)\n\n## Accuracy and Loss\n\n|   | Training | Test |\n|---|---|---|\n| Accuracy | 97.392% | 95.430%  |\n| Loss | 0.046 | 0.081 |\n\n![graph](./assets/result.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnathanielsimard%2Fnumpy-mnist-classifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnathanielsimard%2Fnumpy-mnist-classifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnathanielsimard%2Fnumpy-mnist-classifier/lists"}