{"id":19419275,"url":"https://github.com/mahdizynali/mazenet","last_synced_at":"2025-04-24T14:31:43.161Z","repository":{"id":196220488,"uuid":"695065365","full_name":"mahdizynali/MazeNet","owner":"mahdizynali","description":"Mnist digits multi perceptron neural-network training from scratch with c++ and opencv matrix. (nn with c++)","archived":false,"fork":false,"pushed_at":"2023-12-03T07:37:19.000Z","size":7974,"stargazers_count":8,"open_issues_count":3,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-03T06:12:43.070Z","etag":null,"topics":["artificial-intelligence","classification","cpp","cpp-neural-network","cpp-training","machine-learning","mnist","mnist-cpp","multi-classification","neural-network","neural-networks","opencv","preceptron","scratch","training"],"latest_commit_sha":null,"homepage":"","language":"C++","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/mahdizynali.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}},"created_at":"2023-09-22T09:24:02.000Z","updated_at":"2024-06-17T07:23:28.000Z","dependencies_parsed_at":"2023-09-23T13:39:29.896Z","dependency_job_id":"de91f081-ffa4-46d4-86e0-cd8039fdab17","html_url":"https://github.com/mahdizynali/MazeNet","commit_stats":null,"previous_names":["mahdizynali/mazenet"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mahdizynali%2FMazeNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mahdizynali%2FMazeNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mahdizynali%2FMazeNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mahdizynali%2FMazeNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mahdizynali","download_url":"https://codeload.github.com/mahdizynali/MazeNet/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250643422,"owners_count":21464172,"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","classification","cpp","cpp-neural-network","cpp-training","machine-learning","mnist","mnist-cpp","multi-classification","neural-network","neural-networks","opencv","preceptron","scratch","training"],"created_at":"2024-11-10T13:16:59.526Z","updated_at":"2025-04-24T14:31:42.586Z","avatar_url":"https://github.com/mahdizynali.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MazeNet\nMnist multi perceptron neural-network training from scratch with c++ and opencv matrix. \\\nin this repository there are two folder that includes folder contains header files and src contains cpp programs.\n## How to train\nFirst clone repository via this command :\n```\ngit clone https://github.com/mahdizynali/MazeNet.git\n```\nNow try to run shell script easy to use :\n```\nchmod a+x run.sh\n```\n```\n./run.sh\n```\n### Run as developer\nafter that you have to extract dataset from compress file (dataset.tar.xz).\ntar.xz is being support by linux \u0026 mac systems. \\\nyou would change config.hpp header in order to set your hyperparameter as you need.\n\n```\n# define l_rate 0.005\n# define total_epochs 10\n# define batch_size 64\n```\nright now inside MazeNet folder follow these commands to build and run training loop :\n```\nmkdir build \u0026\u0026 cd build\n```\n```\nmake\n```\nOr try this for a bit faster :\n```\nmake -j`nproc`\n```\nfinally run the program :\n```\n./maze\n```\nafter training , neuron weights will recive and save into a yml file besides maze program.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmahdizynali%2Fmazenet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmahdizynali%2Fmazenet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmahdizynali%2Fmazenet/lists"}