{"blog_url":"https://ohke.hateblo.jp/","author_url":"https://blog.hatena.ne.jp/ohke/","url":"https://ohke.hateblo.jp/entry/2019/06/12/131500","published":"2019-06-12 13:15:00","provider_name":"Hatena Blog","blog_title":"\u3051\u65e5\u8a18","version":"1.0","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fohke.hateblo.jp%2Fentry%2F2019%2F06%2F12%2F131500\" title=\"\u5b66\u7fd2\u3057\u3066\u306a\u3044\u30e9\u30f3\u30c0\u30e0\u306aCNN\u3067\u3082\u7279\u5fb4\u62bd\u51fa\u306e\u5f79\u306b\u7acb\u3064 - \u3051\u65e5\u8a18\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","categories":["Python","CV","Keras"],"title":"\u5b66\u7fd2\u3057\u3066\u306a\u3044\u30e9\u30f3\u30c0\u30e0\u306aCNN\u3067\u3082\u7279\u5fb4\u62bd\u51fa\u306e\u5f79\u306b\u7acb\u3064","width":"100%","height":"190","type":"rich","provider_url":"https://hatena.blog","author_name":"ohke","image_url":"https://cdn.user.blog.st-hatena.com/default_entry_og_image/99455833/1533459624629378","description":"\u5148\u6708\u304b\u3089\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u3092\u6559\u3048\u3066\u304f\u308c\u308b\u8b1b\u5ea7\u3092\u53d7\u8b1b\u3057\u3066\u3044\u307e\u3059\u3002 \u4eca\u9031\u304b\u3089CNN\u306b\u5165\u3063\u305f\u306e\u3067\u3059\u304c\u3001\u5148\u751f\u304c\u300cCNN\u306f\u7279\u5fb4\u62bd\u51fa\u5668\u3068\u3057\u3066\u304b\u306a\u308a\u512a\u79c0\u3067\u3001\u5b66\u7fd2\u3057\u3066\u3044\u306a\u3044\u30e9\u30f3\u30c0\u30e0\u306aCNN\u3067\u3082\u9ad8\u3044\u7cbe\u5ea6\u304c\u51fa\u305b\u308b\u300d\u3068\u6559\u3048\u3066\u304f\u308c\u307e\u3057\u305f\u3002 \u300c\u3048\u3001\u305d\u3046\u306a\u306e\uff01\uff1f\u300d\u3068\u3073\u3063\u304f\u308a\u3057\u307e\u3057\u305f\u306e\u3067\u3001MNIST\u3092\u4f7f\u3063\u3066\u7c21\u5358\u306b\u5b9f\u9a13\u3057\u3066\u307f\u307e\u3057\u305f\u3002 \u307e\u305a\u306f\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u30ed\u30fc\u30c9\u3057\u3066\u6574\u5f62\u3057\u307e\u3059\u3002 import numpy as np from keras.models import Sequential from keras.layers import Conv2D, MaxPool2D, Dense, Flatten from keras.l\u2026"}