{"id":15649577,"url":"https://github.com/erogol/net2net","last_synced_at":"2025-04-30T16:28:50.042Z","repository":{"id":145077701,"uuid":"104352237","full_name":"erogol/Net2Net","owner":"erogol","description":"Net2Net implementation on PyTorch for any possible vision layers.","archived":false,"fork":false,"pushed_at":"2017-10-09T07:59:24.000Z","size":11537,"stargazers_count":38,"open_issues_count":4,"forks_count":9,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-30T17:51:12.405Z","etag":null,"topics":["computer-vision","deep-learning","net2net","pytorch"],"latest_commit_sha":null,"homepage":null,"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/erogol.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":"2017-09-21T13:33:27.000Z","updated_at":"2024-04-01T06:53:47.000Z","dependencies_parsed_at":null,"dependency_job_id":"b68defeb-995c-4aec-8c86-0a01e7b561d3","html_url":"https://github.com/erogol/Net2Net","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/erogol%2FNet2Net","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erogol%2FNet2Net/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erogol%2FNet2Net/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erogol%2FNet2Net/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/erogol","download_url":"https://codeload.github.com/erogol/Net2Net/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251741934,"owners_count":21636345,"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":["computer-vision","deep-learning","net2net","pytorch"],"created_at":"2024-10-03T12:30:19.864Z","updated_at":"2025-04-30T16:28:49.535Z","avatar_url":"https://github.com/erogol.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Net2Net\nNet2Net implementation on PyTorch for any possible vision layers (nn.Linear, nn.Conv2d, nn.Conv3D, even wider operator btw nn.ConvX to nn.Linear).\nCheckout the [paper](https://arxiv.org/abs/1511.05641:) for more detail\n\n## Observations:\n\n- Using BatchNorm between layers, improves the competence of Net2Net. Otherwise, Net2Net approach is not able to get\ncomparable results to a network trained from scratch.\n\n- Inducing noise to new units and connections prelude to better networks. The effect is more evident without BathNorm layer.\n\n- Normalizing layer weights before any Net2Net operation increases the speed of learning and gives better convergence. Even so, it worths to investgate better normalization methods than L2 norm.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ferogol%2Fnet2net","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ferogol%2Fnet2net","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ferogol%2Fnet2net/lists"}