{"blog_title":"\u3089\u3093\u3060\u3080\u306a\u8a18\u61b6","author_url":"https://blog.hatena.ne.jp/derwind/","image_url":null,"blog_url":"https://randommemory.hatenablog.com/","title":"NHWC","width":"100%","published":"2021-11-29 01:22:30","author_name":"derwind","url":"https://randommemory.hatenablog.com/entry/2021/11/29/012230","height":"190","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Frandommemory.hatenablog.com%2Fentry%2F2021%2F11%2F29%2F012230\" title=\"NHWC - \u3089\u3093\u3060\u3080\u306a\u8a18\u61b6\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","provider_url":"https://hatena.blog","description":"(beta) Channels Last Memory Format in PyTorch \u2014 PyTorch Tutorials 1.10.1+cu102 documentation Why does pytorch prefer using NCHW? - PyTorch Forums \u3059\u3050\u306b\u5fd8\u308c\u3066\u3057\u307e\u3046\u304c\u3001PyTorch \u306f NCHW (BCHW) \u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u3092\u4f7f\u3063\u3066\u3044\u308b\u30fb\u30fb\u30fb\u3089\u3057\u3044\u3002\u305d\u306e\u610f\u5473\u3067\u306f\u3001https://github.com/yusugomori/deeplearning-keras-tf2-torch/blob/08e7b1fbd965eb5d6dbc50fd79c22dc\u2026","categories":["machine_learning"],"provider_name":"Hatena Blog","type":"rich","version":"1.0"}