{"id":18568884,"url":"https://github.com/lucianopalmeida/mnist-number-classification","last_synced_at":"2026-05-03T22:32:22.127Z","repository":{"id":98356132,"uuid":"135939758","full_name":"LucianoPAlmeida/mnist-number-classification","owner":"LucianoPAlmeida","description":"A simple classification of mnist handwritten digits","archived":false,"fork":false,"pushed_at":"2018-07-29T00:20:01.000Z","size":257027,"stargazers_count":2,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-10-06T15:33:40.620Z","etag":null,"topics":["coreml-models","jupyter-notebook","mnist-classification","mnist-handwriting-recognition","python3","tensorflow"],"latest_commit_sha":null,"homepage":"","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/LucianoPAlmeida.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":"2018-06-03T20:52:41.000Z","updated_at":"2019-08-26T07:55:56.000Z","dependencies_parsed_at":null,"dependency_job_id":"9fd2b87a-a70d-4029-8d11-69a68a99cb04","html_url":"https://github.com/LucianoPAlmeida/mnist-number-classification","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/LucianoPAlmeida/mnist-number-classification","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LucianoPAlmeida%2Fmnist-number-classification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LucianoPAlmeida%2Fmnist-number-classification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LucianoPAlmeida%2Fmnist-number-classification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LucianoPAlmeida%2Fmnist-number-classification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/LucianoPAlmeida","download_url":"https://codeload.github.com/LucianoPAlmeida/mnist-number-classification/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LucianoPAlmeida%2Fmnist-number-classification/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32587817,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-03T22:12:39.696Z","status":"ssl_error","status_checked_at":"2026-05-03T22:09:10.534Z","response_time":103,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["coreml-models","jupyter-notebook","mnist-classification","mnist-handwriting-recognition","python3","tensorflow"],"created_at":"2024-11-06T22:30:56.909Z","updated_at":"2026-05-03T22:32:22.110Z","avatar_url":"https://github.com/LucianoPAlmeida.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# mnist-number-classification\n\n[![license](https://img.shields.io/github/license/mashape/apistatus.svg)](https://opensource.org/licenses/MIT)\n\nThis is a Convolutional Neural Network model trained with the [MNIST Dataset](https://en.wikipedia.org/wiki/MNIST_database) of handwritten digits and \nthis model was implemented to support the [CoreML-MNIST](https://github.com/LucianoPAlmeida/CoreML-MNIST) Demo Application.\n\n## Tools\n* [Tensorflow 1.8](https://www.tensorflow.org/)\n* [tf-coreml](https://github.com/tf-coreml/tf-coreml) \n* [coremltools](https://github.com/apple/coremltools)\n* [Jupyter Notebook](http://jupyter.org/)\n* [Python 3.6](https://www.python.org/)\n* [matplotlib](https://matplotlib.org/)\n\n## The Model \nThe model was trainned with 70 epochs with a batch size of 512. Achieving 0.984400 of validation accuracy and 0.9861225328947368 of test accuracy.\nThe [AdamOptimizer](https://www.tensorflow.org/api_docs/python/tf/train/AdamOptimizer) was used to train this network with a learning rate of 0.00001.\n\n### Architecture \n * conv2d with filter size 32, strides 5, padding same and relu activation\n * max_pooling2d with pool size of 2 and strides 2\n * conv2d with filter size 64, strides 5, padding same and relu activation\n * max_pooling2d with pool size of 2 and strides 2\n * fully_connected with number of outputs 1024 and relu activation\n * fully_connected with number of outputs 10 and no activation function\n * softmax activation layer\n\n## The CoreML Model\n\nWith a trained model and saved .pb file, tf-coreml was used generate a CoreML model. \nThe code is available on [coreml_converter.py](https://github.com/LucianoPAlmeida/mnist-number-classification/blob/master/coreml_converter.py)\n\n## Credits and Thanks\n\n- [Udacity](https://www.udacity.com) for their awesome [Deep Learning Nanodegree Foundation](https://www.udacity.com/course/deep-learning-nanodegree--nd101) course.\n\n\n## Licence \n\nmnist-number-classification is released under the [MIT License](https://opensource.org/licenses/MIT).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucianopalmeida%2Fmnist-number-classification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flucianopalmeida%2Fmnist-number-classification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucianopalmeida%2Fmnist-number-classification/lists"}