{"id":15456687,"url":"https://github.com/coyotespike/convolutions-from-scratch","last_synced_at":"2026-05-07T14:37:39.327Z","repository":{"id":228155432,"uuid":"612962692","full_name":"coyotespike/convolutions-from-scratch","owner":"coyotespike","description":"Some models built from scratch with PyTorch during my graduate program at UT Austin","archived":false,"fork":false,"pushed_at":"2023-03-13T04:00:42.000Z","size":15,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-10-12T12:08:47.583Z","etag":null,"topics":["cnn","convolutions","fcn","machine-learning","pytorch","unet"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":false,"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/coyotespike.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}},"created_at":"2023-03-12T14:02:17.000Z","updated_at":"2023-03-12T14:46:10.000Z","dependencies_parsed_at":"2024-03-17T10:48:11.124Z","dependency_job_id":null,"html_url":"https://github.com/coyotespike/convolutions-from-scratch","commit_stats":null,"previous_names":["coyotespike/convolutions-from-scratch"],"tags_count":0,"template":false,"template_full_name":"coyotespike/my-template-repo","purl":"pkg:github/coyotespike/convolutions-from-scratch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coyotespike%2Fconvolutions-from-scratch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coyotespike%2Fconvolutions-from-scratch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coyotespike%2Fconvolutions-from-scratch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coyotespike%2Fconvolutions-from-scratch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/coyotespike","download_url":"https://codeload.github.com/coyotespike/convolutions-from-scratch/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/coyotespike%2Fconvolutions-from-scratch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32741996,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-07T02:14:30.463Z","status":"ssl_error","status_checked_at":"2026-05-07T02:14:29.405Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["cnn","convolutions","fcn","machine-learning","pytorch","unet"],"created_at":"2024-10-01T22:35:59.140Z","updated_at":"2026-05-07T14:37:39.297Z","avatar_url":"https://github.com/coyotespike.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Convolutional Networks in PyTorch from Scratch\n\nThe wonderful thing about PyTorch is that it's high-level and low-level at the same time.\n\nIt abstracts away backprop via its shadow computation graph, which is nicely high-level. And at the same time its forward-feed layers are little more than wrappers over the basic matrix multiplications.\n\nThe combination of these attributes makes implementing architectures from papers fast and easy.\n\nAs part of my graduate program in computer science from UT Austin, I took Deep Learning in 2023, studying the theory and mathematics and the implementation of a variety of architectures. This repo holds the convolutional networks.\n\n## Usage\n\nEach folder houses a different model and a readme with any relevant notes I felt like adding.\n\n## torchinfo and torchsummary\n\nI recommend torchinfo over torchsummary. Usage is exactly the same, but torchinfo catches shape errors much better, and groups output by class, which is much easier to read.\n\n## Creation\n\nLike all my libraries, this repo was created and is managed with [Terraform](https://github.com/coyotespike/terraform-scripts), and was based on a template.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcoyotespike%2Fconvolutions-from-scratch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcoyotespike%2Fconvolutions-from-scratch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcoyotespike%2Fconvolutions-from-scratch/lists"}