{"id":18327980,"url":"https://github.com/gianttreelp/emoji-auto-encoder","last_synced_at":"2026-05-02T06:37:05.336Z","repository":{"id":39676217,"uuid":"169285028","full_name":"GiantTreeLP/emoji-auto-encoder","owner":"GiantTreeLP","description":"Compresses Twemoji emojis down to 32 bytes (8 4-bit floating point numbers).","archived":false,"fork":false,"pushed_at":"2024-07-31T16:09:56.000Z","size":3174,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-07-31T20:06:53.198Z","etag":null,"topics":["autoencoder","compression","emoji","image-compression","python3","tensorflow","tfjs"],"latest_commit_sha":null,"homepage":"https://gianttreelp.github.io/emoji-auto-encoder/www/","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/GiantTreeLP.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":"2019-02-05T17:51:03.000Z","updated_at":"2024-07-31T16:09:53.000Z","dependencies_parsed_at":"2023-01-25T23:15:52.396Z","dependency_job_id":"51f027cf-10fb-4e48-b559-992bc31bc44c","html_url":"https://github.com/GiantTreeLP/emoji-auto-encoder","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/GiantTreeLP%2Femoji-auto-encoder","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GiantTreeLP%2Femoji-auto-encoder/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GiantTreeLP%2Femoji-auto-encoder/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GiantTreeLP%2Femoji-auto-encoder/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GiantTreeLP","download_url":"https://codeload.github.com/GiantTreeLP/emoji-auto-encoder/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248072572,"owners_count":21043262,"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":["autoencoder","compression","emoji","image-compression","python3","tensorflow","tfjs"],"created_at":"2024-11-05T19:12:50.858Z","updated_at":"2026-05-02T06:37:00.316Z","avatar_url":"https://github.com/GiantTreeLP.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# emoji-auto-encoder\n\n![Python Version](https://img.shields.io/badge/Python-3.6%2B-blue.svg)\n[![Requirements Status](https://requires.io/github/GiantTreeLP/emoji-auto-encoder/requirements.svg?branch=master)](https://requires.io/github/GiantTreeLP/emoji-auto-encoder/requirements/?branch=master)\n\n![Preview](https://github.com/GiantTreeLP/emoji-auto-encoder/raw/master/preview.png)\n\nCompresses Twemoji emojis down to 64 bytes (16 4-bit floating point numbers).\n\nThis repository contains an already pretrained model for web use. You can use it as-is without training by hosting\nthe `www` directory on a web server.\n\nTo test the shipped model, just [follow this link](https://gianttreelp.github.io/emoji-auto-encoder/www/).\n\n## Installation\n\n1. Clone this repository.\n1. Install Python 3.6 or later and the accompanying `pip3` module.\n1. (Optional) Create a `virtualenv` for this project.\n1. Run `pip3 install -r requirements.txt`.\n1. (Optional) Install the [GPU support libraries](https://www.tensorflow.org/install/gpu) to use your GPU to train the model.\n1. (Optional) (If you installed the GPU libraries) Install the `tensorflow-gpu` package using `pip3 install tensorflow-gpu`.\n\n## Preparation\n\n1. Navigate to the `src` directory.\n1. Run `python3 svg2png.py` to download and convert the images to a usable format.\n\n## Training\n\nNow we are all set, time to train the network:\n\n1. Navigate to the `src` directory.\n1. Run `python3 autoencoder.py`\n\n## Prepare the model for web use\n\nTo prepare the trained model for use in the web, use the `tensorflowjs_converter`.\n\nIf you have used `virtualenv` to create a virtual environment on Windows, you can find the `tensorflowjs_converter.exe` file in `\u003cvirtualenv directory\u003e\\Scripts\\tensorflowjs_converter.exe`.  \nOn other operating systems, the binary should already be in your $PATH and ready to be used.\n\n- `\u003ctensorflowjs_converter\u003e --input_format keras --output_format tfjs_layers_model logs\\\u003clatest directory\u003e\\model.h5 www`\n\n## Use the model in your web browser\n\nDue to the use of [`tfjs`](https://github.com/tensorflow/tfjs), you have to host the `www` directory on a web server.  \nJust open the `index.html` file in your browser and use the model or design your own page for it.\n\n## URLs\n\n### Emojis\n\n- https://github.com/twitter/twemoji\n\n### Unicode listing\n\n- https://unicode.org/emoji/charts/full-emoji-list.html\n- https://unicode.org/Public/emoji/11.0/emoji-test.txt\n\n### Keras\n\n- https://blog.keras.io/building-autoencoders-in-keras.html\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgianttreelp%2Femoji-auto-encoder","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgianttreelp%2Femoji-auto-encoder","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgianttreelp%2Femoji-auto-encoder/lists"}