{"id":16135561,"url":"https://github.com/mayukhdeb/patrick","last_synced_at":"2026-05-08T06:32:56.127Z","repository":{"id":112697048,"uuid":"322061786","full_name":"Mayukhdeb/patrick","owner":"Mayukhdeb","description":"Tiny neural net library written from scratch with cupy :warning: under construction :warning:","archived":false,"fork":false,"pushed_at":"2020-12-20T17:29:28.000Z","size":577,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-02-12T22:22:22.877Z","etag":null,"topics":["cuda","deep-learning","gpu-computing","machine-learning","neural-network","regression"],"latest_commit_sha":null,"homepage":"","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/Mayukhdeb.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":"2020-12-16T17:59:19.000Z","updated_at":"2021-03-10T12:08:13.000Z","dependencies_parsed_at":null,"dependency_job_id":"5af43a0d-3c8f-4b76-99e8-746523085469","html_url":"https://github.com/Mayukhdeb/patrick","commit_stats":{"total_commits":15,"total_committers":2,"mean_commits":7.5,"dds":0.06666666666666665,"last_synced_commit":"d39f93616932c304fbf5d44bc85a4880263b7089"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mayukhdeb%2Fpatrick","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mayukhdeb%2Fpatrick/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mayukhdeb%2Fpatrick/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Mayukhdeb%2Fpatrick/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Mayukhdeb","download_url":"https://codeload.github.com/Mayukhdeb/patrick/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247511033,"owners_count":20950584,"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":["cuda","deep-learning","gpu-computing","machine-learning","neural-network","regression"],"created_at":"2024-10-09T23:08:33.829Z","updated_at":"2026-05-08T06:32:51.098Z","avatar_url":"https://github.com/Mayukhdeb.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# patrick\n\u003e Spongebob's best friend\n\nTiny neural net library written from scratch with [cupy](https://cupy.dev/) backend (sorry CPU gang). Still under construction. \n\n\u003cp align=\"center\"\u003e\n\u003cimg src = \"images/patrick.png\" width = \"20%\"\u003e\n\u003c/p\u003e\n\n\n```python\nfrom patrick.nn import NN as nn\nfrom patrick.losses import mse_loss\nfrom patrick.activations import leaky_relu\nfrom patrick.layers  import FCLayer as linear\n\n\"\"\"\nLoad and preprocess your data here \n\"\"\"\n\nclass Model(nn):\n    def __init__(self):\n        self.layers =  [\n                    linear(64,32),  ## input size is 64\n                    leaky_relu(),\n                    linear(32, 16),\n                    leaky_relu(),\n                    linear(16,1)  ## output size is 1\n                ]\n\nnet = Model()\n\nnet.fit(\n    x_train,    ## your input features, shape: (num_batches, batch_size, input_size)\n    y_train,    ## your labels, shape: (num_batches, batch_size, output_size)\n    epochs=60,\n    learning_rate=0.005, \n    loss = mse_loss\n)\n```\n\n\"The best way to learn how something works is to make it from scratch\" \n\n\u003cp align=\"center\"\u003e\n-Probably Someone\n\u003c/p\u003e\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmayukhdeb%2Fpatrick","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmayukhdeb%2Fpatrick","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmayukhdeb%2Fpatrick/lists"}