{"id":18440549,"url":"https://github.com/mkashirin/scratches","last_synced_at":"2025-04-07T22:31:40.465Z","repository":{"id":223326694,"uuid":"759938785","full_name":"mkashirin/scratches","owner":"mkashirin","description":"Scratches is a project, which provides a comprehensive guide to creating deep learning models from scratch using Python and NumPy.","archived":false,"fork":false,"pushed_at":"2024-06-07T17:45:01.000Z","size":16017,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-06-07T19:04:03.507Z","etag":null,"topics":["artificial-intelligence","artificial-neural-networks","deep-learning","deep-neural-networks","from-scratch","machine-learning","machine-learning-algorithms","numpy","python"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mkashirin.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2024-02-19T16:15:14.000Z","updated_at":"2024-06-07T17:45:04.000Z","dependencies_parsed_at":"2024-06-07T19:10:03.064Z","dependency_job_id":null,"html_url":"https://github.com/mkashirin/scratches","commit_stats":null,"previous_names":["mkashirin/scratches"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mkashirin%2Fscratches","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mkashirin%2Fscratches/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mkashirin%2Fscratches/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mkashirin%2Fscratches/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mkashirin","download_url":"https://codeload.github.com/mkashirin/scratches/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223295391,"owners_count":17121780,"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":["artificial-intelligence","artificial-neural-networks","deep-learning","deep-neural-networks","from-scratch","machine-learning","machine-learning-algorithms","numpy","python"],"created_at":"2024-11-06T06:31:08.653Z","updated_at":"2024-11-06T06:32:03.106Z","avatar_url":"https://github.com/mkashirin.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003ch1 align=\"center\"\u003eScratches\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\nScratches is a project that is inspired by the \"Deep Learning from Scratch\"\nbook by Seth Weidman, which provides a comprehensive guide to creating deep\nlearning models from scratch using Python and NumPy. The project aims to provide\npure Python and NumPy implementations of classic machine learning algorithms\nsuch as k-nearest neighbors, linear and multiple regressions, and elementary and\nconvolutional neural networks.\n\u003c/p\u003e\n\n## Requirements\n\nThe only system requirement for this application is that you use Conda or\nMiniconda to manage your Python packages.\n\n## Installation and usage\n\nUse the Git command-line interface (CLI) to clone this repository into your\nworking directory using the following command:\n```bash\ngit clone https://github.com/mkashirin/scratches\n```\nTo create a virtual environment, please follow the lines below:\n```bash\nconda init\nconda env create --file=\"environment.yml\" --name=\"scratches\"\nconda activate scratches\n```\nAlthough NumPy is a crucial dependency for the functioning of the algorithms,\nJupiter, Matplotlib, and Pandas are also present in the environment in order to\nprovide a seamless experience.\n\nIf you wish to change the default path for your environment, you can edit the\n\"prefix\" value in the \"environment.yml\" file (the default location is\n\"~/anaconda3/envs/scratches\").\n\nAfter that You can just run the Jupyter sever to access the notebooks from the\n**examples** directory by executing the following command:\n```bash\njupyter lab\n```\nAnd that's it. You are all set!\n\n## Suggestions\n\nThe only specific suggestion is to not use it outside the educational context.\n\nIf you are still unsure, do not worry. The documentation in the source code can\nbe considered sufficient. The code has been written in a clear and concise\nmanner, focusing on readability rather than efficiency.\n\nSo, feel free to experiment with machine learning models! Combine various\nstructures to create your own neural networks. Explore the code to gain a deeper\nunderstanding of fundamental ML and AI principles.\n\n## Licencing\n\nThis project is distributed under the MIT open source licence.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmkashirin%2Fscratches","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmkashirin%2Fscratches","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmkashirin%2Fscratches/lists"}