{"id":31365771,"url":"https://github.com/developer0hye/torch-batchnorm-from-scratch","last_synced_at":"2026-02-18T05:02:17.654Z","repository":{"id":113583206,"uuid":"471879105","full_name":"developer0hye/Torch-BatchNorm-From-Scratch","owner":"developer0hye","description":null,"archived":false,"fork":false,"pushed_at":"2022-03-20T04:32:21.000Z","size":3,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-19T00:53:36.734Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"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/developer0hye.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,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2022-03-20T04:31:44.000Z","updated_at":"2022-09-18T09:33:57.000Z","dependencies_parsed_at":"2023-07-18T15:32:46.876Z","dependency_job_id":null,"html_url":"https://github.com/developer0hye/Torch-BatchNorm-From-Scratch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/developer0hye/Torch-BatchNorm-From-Scratch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/developer0hye%2FTorch-BatchNorm-From-Scratch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/developer0hye%2FTorch-BatchNorm-From-Scratch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/developer0hye%2FTorch-BatchNorm-From-Scratch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/developer0hye%2FTorch-BatchNorm-From-Scratch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/developer0hye","download_url":"https://codeload.github.com/developer0hye/Torch-BatchNorm-From-Scratch/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/developer0hye%2FTorch-BatchNorm-From-Scratch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29569853,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-18T04:18:28.490Z","status":"ssl_error","status_checked_at":"2026-02-18T04:13:49.018Z","response_time":162,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 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":[],"created_at":"2025-09-27T09:59:47.018Z","updated_at":"2026-02-18T05:02:17.650Z","avatar_url":"https://github.com/developer0hye.png","language":null,"readme":"# Torch-BatchNorm-From-Scratch\n\n```python\n\nfrom typing import Optional, Any\n\nimport torch\nfrom torch import Tensor\nfrom torch import nn\n\nclass BatchNorm2d(nn.Module):\n    def __init__(\n        self,\n        num_features: int,\n        eps: float = 1e-5,\n        momentum: float = 0.1,\n        affine: bool = True,\n        track_running_stats: bool = True,\n        device=None,\n        dtype=None\n    ) -\u003e None:\n        factory_kwargs = {'device': device, 'dtype': dtype}\n        super(BatchNorm2d, self).__init__()\n        self.num_features = num_features\n        self.eps = eps\n        self.momentum = momentum\n        self.affine = affine\n        self.track_running_stats = track_running_stats\n        if self.affine:\n            self.weight = nn.Parameter(torch.empty(num_features, **factory_kwargs))\n            self.bias = nn.Parameter(torch.empty(num_features, **factory_kwargs))\n        else:\n            self.register_parameter(\"weight\", None)\n            self.register_parameter(\"bias\", None)\n        if self.track_running_stats:\n            self.register_buffer('running_mean', torch.zeros(num_features, **factory_kwargs))\n            self.register_buffer('running_var', torch.ones(num_features, **factory_kwargs))\n            self.running_mean: Optional[Tensor]\n            self.running_var: Optional[Tensor]\n            self.register_buffer('num_batches_tracked',\n                                 torch.tensor(0, dtype=torch.long,\n                                              **{k: v for k, v in factory_kwargs.items() if k != 'dtype'}))\n            self.num_batches_tracked: Optional[Tensor]\n        else:\n            self.register_buffer(\"running_mean\", None)\n            self.register_buffer(\"running_var\", None)\n            self.register_buffer(\"num_batches_tracked\", None)\n        self.reset_parameters()\n\n    def reset_running_stats(self) -\u003e None:\n        if self.track_running_stats:\n            # running_mean/running_var/num_batches... are registered at runtime depending\n            # if self.track_running_stats is on\n            self.running_mean.zero_()  # type: ignore[union-attr]\n            self.running_var.fill_(1)  # type: ignore[union-attr]\n            self.num_batches_tracked.zero_()  # type: ignore[union-attr,operator]\n\n    def reset_parameters(self) -\u003e None:\n        self.reset_running_stats()\n        if self.affine:\n            nn.init.ones_(self.weight)\n            nn.init.zeros_(self.bias)\n    \n    def forward(self, x: Tensor) -\u003e Tensor:\n        if self.training and self.track_running_stats:\n            mean = x.mean(dim=[0, 2, 3], keepdim=True)\n            var = ((x - mean) ** 2).mean(dim=[0, 2, 3], keepdim=True)\n            with torch.no_grad():\n                self.running_mean = (1 - self.momentum) * self.running_mean + self.momentum * mean.view(-1)\n                self.running_var = (1 - self.momentum) * self.running_var + self.momentum * var.view(-1)\n        else:\n            var, mean = self.running_var, self.running_mean\n        \n        x = (x-mean.view(1, self.num_features, 1, 1))/torch.sqrt(var.view(1, self.num_features, 1, 1)+self.eps)\n        x = self.weight.view(1, self.num_features, 1, 1) * x  + self.bias.view(1, self.num_features, 1, 1)\n        return x\n```\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeveloper0hye%2Ftorch-batchnorm-from-scratch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeveloper0hye%2Ftorch-batchnorm-from-scratch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeveloper0hye%2Ftorch-batchnorm-from-scratch/lists"}