{"id":15958528,"url":"https://github.com/vermavinay982/autoencoder-mnist-clustering","last_synced_at":"2026-05-07T06:32:52.046Z","repository":{"id":185366333,"uuid":"332449192","full_name":"vermavinay982/autoencoder-mnist-clustering","owner":"vermavinay982","description":"Applied KMeans to Cluster MNIST features generated via Autoencoders. Unsupervised Learning.","archived":false,"fork":false,"pushed_at":"2021-02-12T15:49:29.000Z","size":783,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-21T17:04:48.304Z","etag":null,"topics":["artificial-intelligence","autoencoder","decoder","deep-learning","encoder","keras","machine-learning","mnist","python","supervised-learning","tensorflow","unsupervised","unsupervised-learning"],"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/vermavinay982.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":"2021-01-24T12:54:09.000Z","updated_at":"2023-11-27T01:04:39.000Z","dependencies_parsed_at":null,"dependency_job_id":"6e54f316-043f-42d3-ba18-2250dff67b21","html_url":"https://github.com/vermavinay982/autoencoder-mnist-clustering","commit_stats":{"total_commits":16,"total_committers":1,"mean_commits":16.0,"dds":0.0,"last_synced_commit":"5574e809415b1c8fddd75d8eae567edb4ff37503"},"previous_names":["vermavinay982/autoencoder-mnist-clustering"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/vermavinay982/autoencoder-mnist-clustering","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vermavinay982%2Fautoencoder-mnist-clustering","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vermavinay982%2Fautoencoder-mnist-clustering/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vermavinay982%2Fautoencoder-mnist-clustering/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vermavinay982%2Fautoencoder-mnist-clustering/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vermavinay982","download_url":"https://codeload.github.com/vermavinay982/autoencoder-mnist-clustering/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vermavinay982%2Fautoencoder-mnist-clustering/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32725997,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-07T02:14:30.463Z","status":"ssl_error","status_checked_at":"2026-05-07T02:14:29.405Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: 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":["artificial-intelligence","autoencoder","decoder","deep-learning","encoder","keras","machine-learning","mnist","python","supervised-learning","tensorflow","unsupervised","unsupervised-learning"],"created_at":"2024-10-07T14:05:06.223Z","updated_at":"2026-05-07T06:32:52.026Z","avatar_url":"https://github.com/vermavinay982.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Autoencoders on CIFAR and MNIST\nYes, N. Nets are used for Supervised Learning - we give them data and labels - they adjust weights to predict - But using autoencoders generate data and apply unsupervised learning to it - KMeans Clustering as applied here to make clusters of MNIST digits\n\n## Motivation\nUsing the Autoencoders and their power to generalize the images, convert the image into compressed form is very exciting. It enables numerous possibilites of saving the data and processing the data at very low cost.\n\n## Code style\n\n[![js-standard-style](https://img.shields.io/badge/code%20style-standard-brightgreen.svg?style=flat)](https://github.com/feross/standard)\n \n## Screenshots\n\nSample 1             |  Sample 2\n:-------------------------:|:-------------------------:\n\u003cimg src=\"cifar_autoenc.png\" alt=\"drawing\" width=\"500\"/\u003e | \u003cimg src=\"ship_cifar_autoenc.png\" alt=\"drawing\" width=\"500\"/\u003e\n\n## Build status\nThe model architecture is ready to be used for development and deployment weights are released.\n\nMNIST and CIFAR10 dataset was used to reduce the computation time and check the results.\n\nhttp://www.cs.toronto.edu/~kriz/cifar.html\n\nhttp://yann.lecun.com/exdb/mnist/\n\n\n## Trained for 3 epoch\n---\n## Tech/framework used\n\u003cb\u003eBuilt with\u003c/b\u003e\n- Tensorflow 2.3.1\n- Keras\n- Numpy\n\n## Features\nThe visualization of the layers allow us to find what is present in compressed version and what is the difference in original and reconstructed version of the image\n\n## Code Example\n\nThis is done faster using Numpy.\n\n```python\n# Creating the AutoEncoder Model - input and output same\n# for MNIST\n# 784 for 1 channel MNIST dataset of digits\nmodel = Sequential()\nmodel.add(Dense(128, activation='relu', input_shape=(784,)))\nmodel.add(Dense( 32, activation='relu')) # symmetric centroid\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dense(784, activation='sigmoid'))\n\n# for CIFAR10\n# 1024 for 1 channel and 3072 for 3 channels\n# input equal to output - and internal hidden layers can be the same\nmodel = Sequential()\nmodel.add(Dense(128, activation='relu', input_shape=(1024,) ))\nmodel.add(Dense( 32, activation='relu'))\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dense(1024, activation='sigmoid'))\n```\n\n## Installation\n- Install the requirements `pip install -r requirements.txt`\n- Train the model or Download pretrained weights\n- Run the evaluation on the image data by passing the path\n\n## How to use?\n- Download dataset and clean it - using `CIFAR_autoencoder.ipynb` or `MNIST_autoencoder.ipynb` notebook\n- Train the model which you are willing to use\n- Evaluation script of the same model is there to infer your models\n\n## Contribute\nYou can for the repository - create a pull request after making changes or can drop the issue by creating a new issue. It would be helpful for the community.\n\n### Last Updated on 4 Feb 2021   \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvermavinay982%2Fautoencoder-mnist-clustering","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvermavinay982%2Fautoencoder-mnist-clustering","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvermavinay982%2Fautoencoder-mnist-clustering/lists"}