{"id":13740208,"url":"https://github.com/charlescearl/DeepRacket","last_synced_at":"2025-05-08T19:36:42.995Z","repository":{"id":145881460,"uuid":"86529327","full_name":"charlescearl/DeepRacket","owner":"charlescearl","description":"A simple starting point for doing deep learning in Racket","archived":false,"fork":false,"pushed_at":"2019-12-07T23:51:11.000Z","size":42,"stargazers_count":67,"open_issues_count":7,"forks_count":8,"subscribers_count":11,"default_branch":"master","last_synced_at":"2024-11-15T10:41:22.903Z","etag":null,"topics":["cudnn","deep-learning","racket","scheme"],"latest_commit_sha":null,"homepage":"","language":"Racket","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/charlescearl.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}},"created_at":"2017-03-29T02:26:49.000Z","updated_at":"2024-11-06T15:00:43.000Z","dependencies_parsed_at":"2024-01-20T11:57:47.849Z","dependency_job_id":null,"html_url":"https://github.com/charlescearl/DeepRacket","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/charlescearl%2FDeepRacket","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/charlescearl%2FDeepRacket/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/charlescearl%2FDeepRacket/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/charlescearl%2FDeepRacket/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/charlescearl","download_url":"https://codeload.github.com/charlescearl/DeepRacket/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253135800,"owners_count":21859688,"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":["cudnn","deep-learning","racket","scheme"],"created_at":"2024-08-03T04:00:44.454Z","updated_at":"2025-05-08T19:36:42.577Z","avatar_url":"https://github.com/charlescearl.png","language":"Racket","funding_links":[],"categories":["Machine Learning","Racket"],"sub_categories":["Machine Learning"],"readme":"# DeepRacket\n\nThis package provides a set of interfaces for doing deep learning in the [Racket](https://racket-lang.org/) (a Scheme/Lisp dialect) programming language. \n\nThe project is still in the growing pains phase, so please excuse the mess. \n\nThe code here is split into two parts. The first and most useful for now is a very preliminary interface to the [Dynet](https://github.com/clab/dynet) neural \nnetwork library. Dynet seems to have many of the features that you would expect in a lisp like language, foremost is the dynamic specification of neural \nnetworks. A few simple cases are included. \n\nThe second approach is a low level interface to the  NVIDIA [cudnn](https://developer.nvidia.com/cudnn) deep learning library. While this gives a lot of flexibility,\nthere is a lot more to do here. The next big hurdle is including loss calculaton and weight updates. The code now provides the ability to create cudnn objects (e.g RNNs) \nand perform simple forward calculations on models.\n\nThe approach I've taken is to use the [Torch](https://github.com/soumith/cudnn.torch/blob/master/ffi.lua) Deep Learning library wrapper as a guide.\n\nSuggestions welcome.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcharlescearl%2FDeepRacket","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcharlescearl%2FDeepRacket","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcharlescearl%2FDeepRacket/lists"}