{"id":24810855,"url":"https://github.com/vidursatija/fasterconv3d","last_synced_at":"2026-05-01T12:32:13.064Z","repository":{"id":84533415,"uuid":"295152604","full_name":"vidursatija/FasterConv3D","owner":"vidursatija","description":"3D Convolution to 2D Convolution","archived":false,"fork":false,"pushed_at":"2020-09-13T13:06:02.000Z","size":4,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-10-06T22:34:34.799Z","etag":null,"topics":["cnn","convolutional-neural-networks","machine-learning","mobile","python","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/vidursatija.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2020-09-13T13:03:48.000Z","updated_at":"2020-09-13T13:07:09.000Z","dependencies_parsed_at":null,"dependency_job_id":"b693bd1b-48fa-406f-8c33-3ecf91e4fec1","html_url":"https://github.com/vidursatija/FasterConv3D","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/vidursatija/FasterConv3D","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vidursatija%2FFasterConv3D","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vidursatija%2FFasterConv3D/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vidursatija%2FFasterConv3D/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vidursatija%2FFasterConv3D/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vidursatija","download_url":"https://codeload.github.com/vidursatija/FasterConv3D/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vidursatija%2FFasterConv3D/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32497810,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-30T13:12:12.517Z","status":"online","status_checked_at":"2026-05-01T02:00:05.856Z","response_time":64,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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","convolutional-neural-networks","machine-learning","mobile","python","tensorflow"],"created_at":"2025-01-30T12:18:20.242Z","updated_at":"2026-05-01T12:32:13.052Z","avatar_url":"https://github.com/vidursatija.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Comparison between 1 Conv3D op vs 3 Conv2D ops\n\nThis repo serves as dummy code which shows that 3 Conv2Ds are actually faster than 1 Conv3D operation in tensorflow. Obviously this result will vary with the image size, kernel size and hardware stuff.\n\n|      X     | Conv3D | Conv2D |\n|------------|--------|--------|\n| Parameters |  `k*k*k*i*o` | `3*k*1*i*o` |\n| Speed      |  `h*w*d*k*k*k*i*o` | `h*w*d*3*k*1*i*o` |\n\n```\ni = input channels\no = output channels\nh, w, d = input tensor dimensions\nk = kernel size\n```\n\n## Use cases\n1. Mobiles which don't support 3D convolutions and 3D tensors but need such operations\n2. To save space and improve performance of the model\n3. ?\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvidursatija%2Ffasterconv3d","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvidursatija%2Ffasterconv3d","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvidursatija%2Ffasterconv3d/lists"}