{"id":16535944,"url":"https://github.com/algebra-fun/neuroflow.jl","last_synced_at":"2025-03-03T16:25:13.025Z","repository":{"id":65942645,"uuid":"601622917","full_name":"Algebra-FUN/NeuroFlow.jl","owner":"Algebra-FUN","description":"NeuroFlow is an experimental deep learning framework written in Julia.","archived":false,"fork":false,"pushed_at":"2023-03-03T09:52:04.000Z","size":12,"stargazers_count":5,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-14T02:44:08.554Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Julia","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/Algebra-FUN.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":"2023-02-14T13:18:08.000Z","updated_at":"2023-02-21T14:30:32.000Z","dependencies_parsed_at":"2023-03-13T03:46:32.942Z","dependency_job_id":null,"html_url":"https://github.com/Algebra-FUN/NeuroFlow.jl","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/Algebra-FUN%2FNeuroFlow.jl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Algebra-FUN%2FNeuroFlow.jl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Algebra-FUN%2FNeuroFlow.jl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Algebra-FUN%2FNeuroFlow.jl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Algebra-FUN","download_url":"https://codeload.github.com/Algebra-FUN/NeuroFlow.jl/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241697573,"owners_count":20005035,"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":[],"created_at":"2024-10-11T18:29:18.597Z","updated_at":"2025-03-03T16:25:13.002Z","avatar_url":"https://github.com/Algebra-FUN.png","language":"Julia","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NeuroFlow\n\n[![Build Status](https://github.com/Algebra-FUN/`NeuroFlow.jl`/actions/workflows/CI.yml/badge.svg?branch=main)](https://github.com/Algebra-FUN/NeuroFlow.jl/actions/workflows/CI.yml?query=branch%3Amain)\n\n`NeuroFlow` is an experimental deep learning framework written in Julia.\n\nIt implements `auto-gradient` functionality with an atomic level dynamic computational graph and provides api in `Pytorch` style. \n\n## Installation\n\n```julia\nimport Pkg\nPkg.add(\"NeuroFlow\")\n```\n\n## Quick Start\n\nWe start with a simple linear example:\n\n```julia\nusing NeuroFlow\nimport Distributions: Uniform, Normal, mean\nusing Plots\n\n# generate some fake data obeyed the linear model\nN = 1000\nx = rand(Uniform(-10, 10), N) |\u003e sort\nϵ = rand(Normal(0, 1), N)\n# parameters setting\na, b = 2.5, 1.5\ny = a .* x .+ b .+ ϵ\n\n# declare parameters which needs to be optimize\nâ,b̂ = Param(1.), Param(1.)\n# define the linear model with parameters\nlm(x) = â * x + b̂\n# use SGD optimizer\noptimizer = SGD([â;b̂]; η=1e-2)\n\nloss_records = []\n\n# train for 100 epochs\nfor epoch in 1:100\n    ŷ = lm.(x)\n    loss = mean((y.-ŷ).^2)\n\n    # this three steps are just like pytorch\n    zero_grad!(optimizer)\n    backward!(loss)\n    step!(optimizer)\n\n    push!(loss_records, loss.val)\n    if epoch % 5 == 0\n        println(\"epoch=$epoch,loss=$(loss.val)\")\n    end\nend\n```\n\n\u003e More detail about this example can be seen in [examples/LinearRegression.jl](examples/LinearRegression.jl)\n\n## Examples\n\nMore examples can be found in [`examples`](examples/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falgebra-fun%2Fneuroflow.jl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falgebra-fun%2Fneuroflow.jl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falgebra-fun%2Fneuroflow.jl/lists"}