{"image_url":null,"provider_name":"Hatena Blog","provider_url":"https://hatena.blog","height":"190","version":"1.0","type":"rich","url":"https://randommemory.hatenablog.com/entry/2019/12/13/021924","published":"2019-12-13 02:19:24","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Frandommemory.hatenablog.com%2Fentry%2F2019%2F12%2F13%2F021924\" title=\"0.485, 0.456, 0.406 - \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>","title":"0.485, 0.456, 0.406","author_url":"https://blog.hatena.ne.jp/derwind/","description":"python - Why Pytorch officially use mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225] to normalize images? - Stack Overflow \u306a\u308b\u307b\u3069\u30fb\u30fb\u30fb\u3063\u3066\u601d\u3063\u3066\u826f\u3044\u306e\u304b\u306f\u5206\u304b\u3089\u306a\u3044\u3051\u3069\u3002\u7a81\u5982\u51fa\u3066\u304f\u308b\u8b0e\u306e\u5e73\u5747\u5024\u3068\u6a19\u6e96\u504f\u5dee\u3067\u3042\u3063\u305f\u3002","blog_title":"\u3089\u3093\u3060\u3080\u306a\u8a18\u61b6","categories":["machine_learning"],"blog_url":"https://randommemory.hatenablog.com/","width":"100%","author_name":"derwind"}