{"id":15698129,"url":"https://github.com/hereismari/mnist-tensorflow","last_synced_at":"2025-05-09T01:08:52.112Z","repository":{"id":88345704,"uuid":"88059007","full_name":"hereismari/mnist-tensorflow","owner":"hereismari","description":"Exploring mnist dataset with TensorFlow and getting 99% accuracy in tests","archived":false,"fork":false,"pushed_at":"2017-09-08T13:47:05.000Z","size":11362,"stargazers_count":6,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-05-09T01:08:49.553Z","etag":null,"topics":["classifying-handwritten-digits","convolutional-neural-networks","mnist","tensorflow","tutorial"],"latest_commit_sha":null,"homepage":null,"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/hereismari.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":"2017-04-12T14:08:07.000Z","updated_at":"2025-01-31T10:22:10.000Z","dependencies_parsed_at":null,"dependency_job_id":"358e02ff-544b-41ce-83ad-5560652994e8","html_url":"https://github.com/hereismari/mnist-tensorflow","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hereismari%2Fmnist-tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hereismari%2Fmnist-tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hereismari%2Fmnist-tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hereismari%2Fmnist-tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hereismari","download_url":"https://codeload.github.com/hereismari/mnist-tensorflow/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253171260,"owners_count":21865293,"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":["classifying-handwritten-digits","convolutional-neural-networks","mnist","tensorflow","tutorial"],"created_at":"2024-10-03T19:23:27.873Z","updated_at":"2025-05-09T01:08:52.084Z","avatar_url":"https://github.com/hereismari.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Exploring MNIST with TensorFlow\n\n![mnist](http://rodrigob.github.io/are_we_there_yet/build/images/mnist.png?1363085077)\n\nThere are a lot of awesome tutorials about how to classify handwritten\ndigits from [MNIST database](http://yann.lecun.com/exdb/mnist/),\nso my plan is to put some of these tutorials together,\nevolving from a very simple model to a nice model that achieves\n99% accuracy in the test data.  \n\n[Here](https://github.com/mari-linhares/mnist-android-tensorflow) is an\nandroid app that I did as a final result of this exercise :smile:!\n\nHave fun!\n\n\u003e Note: most of the code presented here is originally from the tutorials in the Reference\n  section, please follow those for more details\n\n## Getting started\n\nFor running the \"tutorials\" You'll need:\n\n* Python 2 or 3\n* Numpy\n* [TensorFlow](https://www.tensorflow.org/install/)\n* Jupyter Notebook\n\n### Getting the data\n\nThe MNIST databased used here was the one available at TensorFlow\n([read more about it](https://www.tensorflow.org/get_started/mnist/beginners)),\nso you don't have to do much.  \nYou can download the data [here](http://yann.lecun.com/exdb/mnist/), if\nyou want.\n\nFor the examples in this repository we'll use all the available\ndata and train the models with stochastic gradient descent (except 01-KNN).\n\n## Let's do it!\n\nTo follow the tutorial samples, run: `jupyter notebook`.  \nIf you want to check TensorBoard: run `tensorboard --logdir=/tmp/tensorflow_log`\n\n## References\n\nThank you!\n\n0. [TF and DL without a Phd by Martin Gorner, Google](https://codelabs.developers.google.com/codelabs/cloud-tensorflow-mnist/#0)  \n1. [Classifying Handwritten Digits with TF.Learn, by Josh Gordon](https://www.youtube.com/watch?v=Gj0iyo265bc\u0026list=PLOU2XLYxmsIIuiBfYad6rFYQU_jL2ryal\u0026index=1)  \n2. [How to Make a TF Image Classifier, by Siraj Raval](https://github.com/llSourcell/How_to_make_a_tensorflow_image_classifier_LIVE)\n3. [TensorFlow Tutorials, by Hvass Labs ](https://github.com/Hvass-Labs/TensorFlow-Tutorials)\n4. [CS231n: Convolutional Neural Networks for Visual Recognition](http://cs231n.github.io/)\n5. [Getting started with TensorFlow](https://www.tensorflow.org/get_started/get_started)\n6. [Not another mnist tutorial with tensorflow](https://www.oreilly.com/learning/not-another-mnist-tutorial-with-tensorflow)\n7. [Training convolutional neural network for image classification](http://cv-tricks.com/tensorflow-tutorial/training-convolutional-neural-network-for-image-classification/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhereismari%2Fmnist-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhereismari%2Fmnist-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhereismari%2Fmnist-tensorflow/lists"}