{"id":4232,"date":"2020-12-09T10:15:47","date_gmt":"2020-12-09T01:15:47","guid":{"rendered":"https:\/\/www.kagoya.jp\/howto\/?p=4232"},"modified":"2023-07-18T17:47:17","modified_gmt":"2023-07-18T08:47:17","slug":"gpu-container4","status":"publish","type":"post","link":"https:\/\/www.kagoya.jp\/howto\/engineer\/hpc\/gpu-container4\/","title":{"rendered":"Chainer\u3092\u4f7f\u3063\u305f\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u3010\u7b2c4\u56de:GPU\u30b3\u30f3\u30c6\u30ca\u3067\u6a5f\u68b0\u5b66\u7fd2\u3059\u308b\u3011"},"content":{"rendered":"
\u3010\u9023\u8f09\u4f01\u753b\u3011GPU\u30b3\u30f3\u30c6\u30ca\u6d3b\u7528 \u3010\u51686\u56de\u3011<\/th> <\/tr> <\/thead>
GPU\u30b3\u30f3\u30c6\u30ca\u3068\u306f\u4f55\u304b\uff1f\u4f55\u304c\u4fbf\u5229\u306a\u306e\u304b\uff1f\u3010\u7b2c1\u56de\uff1aGPU\u30b3\u30f3\u30c6\u30ca\u3067\u901f\u653b\u74b0\u5883\u69cb\u7bc9\u3011<\/a> <\/td> <\/tr>
TensorFlow\u3068Keras\u306b\u3088\u308b\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u2460\u3010\u7b2c2\u56de:GPU\u30b3\u30f3\u30c6\u30ca\u3067\u753b\u50cf\u89e3\u6790\u301c\u6e96\u5099\u7de8\u301c\u3011<\/a> <\/td> <\/tr>
TensorFlow\u3068Keras\u306b\u3088\u308b\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u2461\u3010\u7b2c3\u56de:GPU\u30b3\u30f3\u30c6\u30ca\u3067\u753b\u50cf\u89e3\u6790\u301c\u5b9f\u8df5\u7de8\u301c\u3011<\/a> <\/td> <\/tr>
Chainer\u3092\u4f7f\u3063\u305f\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u3010\u7b2c4\u56de:GPU\u30b3\u30f3\u30c6\u30ca\u3067\u6a5f\u68b0\u5b66\u7fd2\u3059\u308b\u3011 <\/td> <\/tr>
PyTorch\u3067\u6a5f\u68b0\u5b66\u7fd2\u3010\u7b2c5\u56de:GPU\u30b3\u30f3\u30c6\u30ca\u3067\u30c6\u30f3\u30bd\u30eb\u306e\u57fa\u672c\u3092\u7406\u89e3\u3059\u308b\u3011<\/a> <\/td> <\/tr> <\/tbody> <\/table><\/div>
\n
\"GPU\u30b3\u30f3\u30c6\u30ca\"<\/figure>\n<\/div>\n\n\n

AI\u521d\u5b66\u8005\u306b\u3068\u3063\u3066\u30cf\u30fc\u30c9\u30eb\u306e\u3072\u3068\u3064\u306b\u306a\u3063\u3066\u3044\u308bGPU\u74b0\u5883\u69cb\u7bc9\u3092\u3067\u304d\u308b\u3060\u3051\u52b9\u7387\u7684\u306b\u884c\u3046\u305f\u3081\u306b\u3001\u30b3\u30f3\u30c6\u30ca\u3092\u6709\u52b9\u6d3b\u7528\u3059\u308b\u3053\u3068\u3092\u76ee\u7684\u306b\u9023\u8f09\u3092\u30b9\u30bf\u30fc\u30c8\u3057\u307e\u3057\u305f\u3002\u524d\u56de\u306f\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u306e\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3068\u3057\u3066\u30e1\u30b8\u30e3\u30fc\u306aTensorFlow\u3068Keras\u3092\u4f7f\u3044\u3001\u624b\u66f8\u304d\u6587\u5b57\u306e\u5206\u985e\u3092\u884c\u3044\u307e\u3057\u305f\u3002\u4eca\u56de\u306f\u3053\u3061\u3089\u3082\u30e1\u30b8\u30e3\u30fc\u306a\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u306e\u3072\u3068\u3064\u3067\u3042\u308bChainer\uff08\u30c1\u30a7\u30a4\u30ca\u30fc\uff09\u3092\u4f7f\u3063\u3066\u3001\u524d\u56de\u540c\u69d8\u306b\u624b\u66f8\u304d\u6587\u5b57\u753b\u50cf\u306e\u5206\u985e\u3092\u884c\u3044\u307e\u3059\u3002<\/p>\n\n\n\n

\u3053\u306e\u9023\u8f09\u306b\u3064\u3044\u3066<\/h2>\n\n\n\n

\u672c\u9023\u8f09\u306f\u3001\u51686\u56de\u306e\u30b7\u30ea\u30fc\u30ba\u3092\u901a\u3057\u3066\u3067\u304d\u308b\u3060\u3051\u52b9\u7387\u7684\u306b\u3001GPU\u306e\u74b0\u5883\u69cb\u7bc9\u3092\u884c\u3046\u305f\u3081\u306b\u30b3\u30f3\u30c6\u30ca\u306e\u6d3b\u7528\u3092\u884c\u3063\u3066\u3044\u304d\u307e\u3059\u3002\u300c\u6a5f\u68b0\u5b66\u7fd2\u3084\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u3092GPU\u3067\u5b9f\u884c\u3057\u3066\u307f\u305f\u3044\u3051\u3069\u96e3\u3057\u305d\u3046\u2026\u300d\u306a\u3069\u5c0e\u5165\u306b\u30cf\u30fc\u30c9\u30eb\u3092\u611f\u3058\u3089\u308c\u3066\u3044\u308b\u65b9\u306b\u3001\u30b3\u30f3\u30c6\u30ca\u3092\u6d3b\u7528\u3059\u308b\u3053\u3068\u3067\u3001\u74b0\u5883\u69cb\u7bc9\u306b\u8981\u3059\u308b\u5de5\u6570\u3092\u5727\u5012\u7684\u306b\u524a\u6e1b\u3057\u3001\u5373\u5ea7\u306b\u8ab2\u984c\u306b\u53d6\u308a\u7d44\u3080\u3053\u3068\u304c\u3067\u304d\u308b\u30e1\u30ea\u30c3\u30c8\u3092\u611f\u3058\u3066\u3044\u305f\u3060\u304d\u307e\u3059\u3002\u305d\u306e\u305f\u3081\u306b\u5fc5\u8981\u306a\u77e5\u8b58\u3084\u64cd\u4f5c\u65b9\u6cd5\u3092\u3001\u5f53\u793e\u306eGPU\u30b5\u30fc\u30d0\u30fc\u3092\u4f7f\u3044\u89e3\u8aac\u3057\u3066\u3044\u304d\u307e\u3059\u3002
\u9023\u8f09\u3092\u8aad\u307f\u7d42\u3048\u308b\u3053\u308d\u306b\u306f\u3001TensorFlow\u3084PyTorch\u306a\u3069\u306e\u30e1\u30b8\u30e3\u30fc\u306a\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3092\u4f7f\u3063\u305f\u6f14\u7fd2\u304c\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u3063\u3066\u3044\u308b\u306f\u305a\u3067\u3059\u3002<\/p>\n\n\n

\n
\"GPU\u30b3\u30f3\u30c6\u30ca\u3067\u6a5f\u68b0\u5b66\u7fd2\"<\/figure>\n<\/div>\n\n\n

\u672c\u9023\u8f09\u306f\u3001\u3053\u3061\u3089\u306e\u624b\u9806\u3067\u9032\u3081\u3066\u3044\u307e\u3059<\/h2>\n\n\n\n

\u30fbGPU\u30b3\u30f3\u30c6\u30ca\u3068\u306f\u4f55\u304b\uff1f\u4f55\u304c\u4fbf\u5229\u306a\u306e\u304b\uff1f\uff08\u7b2c1\u56de\uff09<\/h3>\n\n\n\n

AI\u521d\u5b66\u8005\u304cGPU\u3092\u4f7f\u3063\u3066\u6a5f\u68b0\u5b66\u7fd2\u3084\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u306b\u53d6\u308a\u7d44\u307f\u305f\u3044\u5834\u5408\u3001\u74b0\u5883\u69cb\u7bc9\u306b\u60f3\u50cf\u4ee5\u4e0a\u306e\u5de5\u6570\u304c\u767a\u751f\u3059\u308b\u3053\u3068\u304c\u3042\u308a\u307e\u3059\u3002\u30bb\u30c3\u30c8\u30a2\u30c3\u30d7\u4f5c\u696d\u306b\u8981\u3059\u308b\u6642\u9593\u3092\u6975\u529b\u524a\u6e1b\u3059\u308b\u305f\u3081\u306b\u30b3\u30f3\u30c6\u30ca\u6280\u8853\u3092\u9069\u7528\u3057\u3001\u30b3\u30f3\u30c6\u30ca\u5185\u304b\u3089GPU\u3092\u5229\u7528\u3059\u308b\u305f\u3081\u306e\u6e96\u5099\u3068\u624b\u9806\u306b\u3064\u3044\u3066\u7d39\u4ecb\u3057\u307e\u3059\u3002<\/p>\n\n\n\n

\u25cfGPU\u30b3\u30f3\u30c6\u30ca\u3068\u306f\u4f55\u304b\uff1f\u4f55\u304c\u4fbf\u5229\u306a\u306e\u304b\uff1f\uff08\u7b2c1\u56de\uff09
https:\/\/www.kagoya.jp\/howto\/cloud\/gpu-container1\/<\/a><\/p>\n\n\n\n

\u30fbTensorFlow\u3068Keras\u306b\u3088\u308b\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u2460\uff08\u7b2c2\u56de\uff09<\/h3>\n\n\n\n

OSS\uff08\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30bd\u30d5\u30c8\u30a6\u30a8\u30a2\uff09\u306e\u6a5f\u68b0\u5b66\u7fd2\u30e9\u30a4\u30d6\u30e9\u30ea\u306e\u4e2d\u304b\u3089TensorFlow\uff08\u30c6\u30f3\u30bd\u30eb\u30d5\u30ed\u30fc\uff09\u3001Keras\uff08\u30b1\u30e9\u30b9\uff09<\/mark>\u3092\u53d6\u308a\u4e0a\u3052\u3001\u3053\u308c\u3089\u304c\u7a3c\u50cd\u3059\u308b\u30b3\u30f3\u30c6\u30ca\u3092\u4f5c\u6210\u3057\u3001\u30b3\u30f3\u30c6\u30ca\u5185\u304b\u3089GPU\u3092\u6307\u5b9a\u3059\u308b\u65b9\u6cd5\u306b\u3064\u3044\u3066\u7d39\u4ecb\u3057\u307e\u3059\u3002TensorFlow\u306fKeras\u3092\u53d6\u308a\u8fbc\u3080\u5f62\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u3066\u3001\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u3092\u3059\u308b\u969b\u306e\u4f7f\u3044\u52dd\u624b\u306e\u826f\u3055\u304b\u3089\u3001\u591a\u304f\u306e\u30e6\u30fc\u30b6\u30fc\u306b\u5229\u7528\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u3053\u306e\u56de\u3067\u306f\u30b3\u30f3\u30c6\u30ca\u5185\u306eTensorFlow\u3067GPU\u3092\u5229\u7528\u3067\u304d\u308b\u72b6\u614b\u307e\u3067\u78ba\u8a8d\u3057\u307e\u3059\u3002<\/p>\n\n\n\n

\u25cfGPU\u30b3\u30f3\u30c6\u30ca\u3067\u753b\u50cf\u89e3\u6790~\u6e96\u5099\u7de8~\uff08\u7b2c2\u56de\uff09
https:\/\/www.kagoya.jp\/howto\/cloud\/gpu-container2\/<\/a><\/p>\n\n\n\n

\u30fbTensorFlow\u3068Keras\u306b\u3088\u308b\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u2461\uff08\u7b2c3\u56de\uff09<\/h3>\n\n\n\n

TensorFlow\uff08\u30c6\u30f3\u30bd\u30eb\u30d5\u30ed\u30fc\uff09\u3084Theano\uff08\u30c6\u30a2\u30ce\uff09\uff0fCNTK\uff08Cognitive Toolkit\uff09<\/mark>\u306e\u8907\u6570\u306e\u30d0\u30c3\u30af\u30a8\u30f3\u30c9\u3068\u3057\u3066\u5229\u7528\u53ef\u80fd\u306aKeras\uff08\u30b1\u30e9\u30b9\uff09<\/mark>\u3092\u53d6\u308a\u4e0a\u3052\u3001TensorFlow\u3068Keras\u3092\u4f7f\u3063\u305f\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u3092\u884c\u3044\u307e\u3059\u3002\u3053\u3053\u3067\u306fAI\u521d\u5b66\u8005\u306e\u65b9\u304c\u89aa\u3057\u307f\u3084\u3059\u3044\u8ab2\u984c\u3092\u6271\u3046\u3053\u3068\u3092\u610f\u56f3\u3057\u3001TensorFlow\u306e\u516c\u5f0f\u30ac\u30a4\u30c9\u306b\u8a18\u8f09\u3055\u308c\u3066\u3044\u308b\u300c\u521d\u5fc3\u8005\u306e\u305f\u3081\u306e TensorFlow 2.0 \u5165\u9580\u300d\u306e\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3092\u53d6\u308a\u4e0a\u3052\u307e\u3057\u305f\u3002<\/p>\n\n\n\n

\u25cfGPU\u30b3\u30f3\u30c6\u30ca\u3067\u753b\u50cf\u89e3\u6790~\u5b9f\u8df5\u7de8~\uff08\u7b2c3\u56de\uff09
https:\/\/www.kagoya.jp\/howto\/cloud\/gpu-container3\/<\/a><\/p>\n\n\n\n

\u30fbChainer\u3092\u4f7f\u3063\u305f\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\uff08\u7b2c4\u56de\uff09\u4eca\u56de\u306e\u8a18\u4e8b<\/h3>\n\n\n\n

\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u306e\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3068\u3057\u3066\u6709\u540d\u306aChainer\uff08\u30c1\u30a7\u30a4\u30ca\u30fc\uff09<\/mark>\u306e\u5229\u7528\u65b9\u6cd5\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002\u30b3\u30f3\u30c6\u30ca\u304b\u3089Python\u306e\u30d7\u30ed\u30b0\u30e9\u30e0\u5b9f\u884c\u7d50\u679c\u3092\u901a\u3057\u3066\u78ba\u8a8d\u3057\u307e\u3059\u3002C\u8a00\u8a9e\u306b\u6bd4\u3079\u3066\u51e6\u7406\u6642\u9593\u304c\u304b\u304b\u308b\u3068\u8a00\u308f\u308c\u3066\u3044\u308bPython\u3067\u3059\u304c\u3001\u6570\u5024\u8a08\u7b97\u3092\u52b9\u7387\u7684\u306b\u884c\u3046\u305f\u3081\u306e\u62e1\u5f35\u30e2\u30b8\u30e5\u30fc\u30eb\u3067\u3042\u308bNumPy\uff08\u30ca\u30e0\u30d1\u30a4\uff09<\/mark>\u3082\u5229\u7528\u3057\u307e\u3059\u3002\u4eca\u56de\u6271\u3046\u984c\u6750\u3068\u3057\u3066Chainer\u306e\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3092\u53d6\u308a\u4e0a\u3052\u307e\u3059\u3002<\/p>\n\n\n\n

\u30fbPytorch\u3067\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\uff08\u7b2c5\u56de\uff09<\/h3>\n\n\n\n

Python\u306e\u6a5f\u68b0\u5b66\u7fd2\u7528\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308bPytorch\uff08\u30d1\u30a4\u30c8\u30fc\u30c1\uff09<\/mark>\u3092\u53d6\u308a\u4e0a\u3052\u307e\u3059\u3002PyTorch\u3067\u306fTensor\uff08\u30c6\u30f3\u30bd\u30eb\uff09<\/mark>\u3068\u3044\u3046\u578b\u3067\u884c\u5217\u3092\u8868\u73fe\u3057\u307e\u3059\u3002Tensor\u306f\u591a\u6b21\u5143\u914d\u5217\u3092\u6271\u3046\u305f\u3081\u306e\u30c7\u30fc\u30bf\u69cb\u9020\u3067\u3042\u308a\u3001GPU\u3092\u30b5\u30dd\u30fc\u30c8\u3057\u3066\u3044\u308b\u3053\u3068\u304b\u3089\u3001Pytorch\u304c\u7a3c\u50cd\u3059\u308b\u30b3\u30f3\u30c6\u30ca\u3092\u5229\u7528\u3057\u3001GPU\u306b\u3088\u308b\u9ad8\u901f\u51e6\u7406\u3092\u884c\u3046\u624b\u9806\u306b\u3064\u3044\u3066\u7d39\u4ecb\u3057\u307e\u3059\u3002<\/p>\n\n\n\n

\u30fbOpenPose\u306b\u3088\u308b\u95a2\u7bc0\u70b9\u62bd\u51fa\u30fb\u59ff\u52e2\u63a8\u5b9a\uff08\u7b2c6\u56de\uff09<\/h3>\n\n\n\n

\u30ab\u30e1\u30e9\u753b\u50cf\u306eAI\u753b\u50cf\u8a8d\u8b58\u3068\u8a00\u3048\u3070\u300c\u9854\u8a8d\u8a3c\u300d\u3092\u601d\u3044\u6d6e\u304b\u3079\u308b\u4eba\u304c\u591a\u3044\u3068\u601d\u3044\u307e\u3059\u304c\u3001\u6700\u8fd1\u306f\u4e00\u6b69\u9032\u307f\u3001\u4eba\u304c\u6620\u3063\u305f\u9759\u6b62\u753b\u3084\u52d5\u753b\u304b\u3089\u95a2\u7bc0\u70b9\u62bd\u51fa\u30fb\u59ff\u52e2\u63a8\u5b9a\u306b\u53d6\u308a\u7d44\u3080\u30b1\u30fc\u30b9\u304c\u5897\u3048\u3066\u3044\u307e\u3059\u3002\u4eba\u4f53\u3001\u9854\u3001\u624b\u8db3\u306a\u3069\u306e\u30ad\u30fc\u30dd\u30a4\u30f3\u30c8\u3092\u753b\u50cf\u304b\u3089\u691c\u51fa\u3059\u308b\u6280\u8853\u304c\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u306b\u3088\u308a\u3001\u5b9f\u7528\u30ec\u30d9\u30eb\u307e\u3067\u5411\u4e0a\u3057\u3066\u3044\u308b\u304b\u3089\u3067\u3059\u3002\u3053\u306e\u56de\u3067\u306fOpenPose\uff08\u30aa\u30fc\u30d7\u30f3\u30dd\u30fc\u30ba\uff09<\/mark>\u3068\u3044\u3046\u30e9\u30a4\u30d6\u30e9\u30ea\u3092GPU\u4e0a\u3067\u52d5\u304b\u3059\u30b3\u30f3\u30c6\u30ca\u3092\u4f7f\u3044\u3001\u52d5\u753b\u30d5\u30a1\u30a4\u30eb\u306e\u95a2\u7bc0\u70b9\u62bd\u51fa\u624b\u9806\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002<\/p>\n\n\n\n

\u524d\u56de(\u7b2c3\u56de)\u306e\u632f\u308a\u8fd4\u308a<\/h2>\n\n\n\n

\u524d\u56de\u306f\u3001Docker\u74b0\u5883\u3067GPU\u30b3\u30f3\u30c6\u30ca\u304b\u3089TensroFlow\u3068Keras<\/mark>\u3092\u52d5\u304b\u3057\u3001\u624b\u66f8\u304d\u6587\u5b57\u306e\u8a8d\u8b58\u3092\u884c\u3044\u307e\u3057\u305f\u3002
\u3010 \u7b2c3\u56de\u306e\u9023\u8f09\u8a18\u4e8b\u306f\u3053\u3061\u3089\u3000https:\/\/www.kagoya.jp\/howto\/cloud\/gpu-container3\/ <\/a>\u3011<\/p>\n\n\n\n

MNIST(\u30a8\u30e0\u30cb\u30b9\u30c8)\u3092\u4f7f\u3063\u305f\u624b\u66f8\u304d\u6587\u5b57\u306e\u5224\u5225\u51e6\u7406<\/h3>\n\n\n\n

AI\u521d\u5b66\u8005\u306e\u65b9\u304c\u89aa\u3057\u307f\u3084\u3059\u3044\u8ab2\u984c\u3092\u6271\u3046\u3053\u3068\u3092\u610f\u56f3\u3057\u3001TensorFlow\u306e\u516c\u5f0f\u30b5\u30a4\u30c8\u306b\u8a18\u8f09\u3055\u308c\u3066\u3044\u308b\u300c\u521d\u5fc3\u8005\u306e\u305f\u3081\u306e TensorFlow 2.0 \u5165\u9580\u300d<\/mark>\u306e\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3092\u53d6\u308a\u4e0a\u3052\u307e\u3057\u305f\u3002
\u3010\u3000https:\/\/www.tensorflow.org\/tutorials\/quickstart\/beginner?hl=ja<\/a>\u3000\u3011<\/p>\n\n\n\n

\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3067\u884c\u3063\u3066\u3044\u308b\u4ee5\u4e0b\u306e\u5185\u5bb9\u3092\u5b9f\u8df5\u3057\u307e\u3057\u305f<\/p>\n\n\n\n

    \n
  1. \u624b\u66f8\u304d\u6587\u5b57\u753b\u50cf\u3092\u5206\u985e\u3059\u308b\u305f\u3081\u306e\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u306e\u30e2\u30c7\u30eb\u3092\u5b9a\u7fa9\u3059\u308b<\/li>\n\n\n\n
  2. \u69cb\u7bc9\u3057\u305f\u30e2\u30c7\u30eb\u306b\u5bfe\u3057\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u7528\u753b\u50cf\u3092\u4f7f\u3044\u3001\u5b66\u7fd2\u3092\u884c\u3046<\/li>\n\n\n\n
  3. \u30c6\u30b9\u30c8\u7528\u753b\u50cf\u3092\u4f7f\u3044\u3001\u30e2\u30c7\u30eb\u3092\u6027\u80fd\u8a55\u4fa1\u3059\u308b<\/li>\n<\/ol>\n\n\n\n

    MNIST\u3068\u306f<\/h3>\n\n\n
    \n
    \"\"<\/figure>\n<\/div>\n\n\n

    \uff10\u304b\u3089\uff19\u306e\u624b\u66f8\u304d\u6570\u5b57\u6587\u5b57\u306e\u753b\u50cf\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067\u3059\u3002\u6a5f\u68b0\u5b66\u7fd2\u306e\u9818\u57df\u3067\u30b5\u30f3\u30d7\u30eb\u3068\u3057\u3066\u5229\u7528\u3055\u308c\u308b\u3053\u3068\u304c\u591a\u3044\u4f7f\u3044\u52dd\u624b\u306e\u3088\u3044\u30c7\u30fc\u30bf\u96c6\u3067\u3042\u308a\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u7528\u30c7\u30fc\u30bf60,000\u679a\u3068\u30c6\u30b9\u30c8\u7528\u30c7\u30fc\u30bf10,000\u679a\u304c\u542b\u307e\u308c\u307e\u3059\u3002MNIST\u306e\u30c7\u30fc\u30bf\u306f\u3001\u624b\u66f8\u304d\u6587\u5b57\u306e\u753b\u50cf\u30c7\u30fc\u30bf\u304c\u4f55\u306e\u6570\u5b57\u304b\u3092\u793a\u3059\u300c\u30e9\u30d9\u30eb\u30c7\u30fc\u30bf\u300d\u3068\u7e26\u30fb\u6a2a \u5404\u300528\u30d4\u30af\u30bb\u30eb\u306e\u300c\u753b\u50cf\u30c7\u30fc\u30bf\u300d\u304b\u3089\u69cb\u6210\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n

    \u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u306e\u30e2\u30c7\u30eb\u3092\u5b9a\u7fa9<\/h3>\n\n\n\n

    MNIST\u306e\u753b\u50cf\u3092\u5206\u985e\u3059\u308b\u305f\u3081\u306e\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3092\u69cb\u7bc9\u3057\u307e\u3059\u3002\u3053\u306e\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3067\u306f\u300cSequential\u30e2\u30c7\u30eb\u300d\u3068\u547c\u3070\u308c\u308b\u3001\u5404\u5c64\u3092\u9806\u756a\u306b\u3064\u306a\u3052\u3066\u3044\u304f\u30e2\u30c7\u30eb\u3092\u5b9a\u7fa9\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n

    \n>>>model = tf.keras.models.Sequential([\ntf.keras.layers.Flatten(input_shape=(28, 28)),\ntf.keras.layers.Dense(128, activation='relu'),\ntf.keras.layers.Dropout(0.2),\ntf.keras.layers.Dense(10)\n])\n<\/pre><\/div>\n\n\n
    \u4e0a\u8a18\u306e\u30e2\u30c7\u30eb\u3067\u4e88\u6e2c\u3059\u308b<\/h3>\n\n\n\n
    \u524d\u6bb5\u3067\u5b9a\u7fa9\u3057\u305f\u30e2\u30c7\u30eb\u3092\u4f7f\u3063\u3066\u4e88\u6e2c\u3092\u884c\u3044\u307e\u3059\u3002\u3053\u306e\u6642\u70b9\u3067\u306f\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u524d\u3067\u3059\u3002
    \u4ee5\u4e0b\u3001\u8a73\u3057\u3044\u8aac\u660e\u306f\u7701\u7565\u3057\u3066\u3044\u307e\u3059\u306e\u3067\u3001\u524d\u56de\u306e\u8a18\u4e8b\u3092\u53c2\u7167\u3057\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n\n\n
    \n>>>predictions = model(x_train[:1]).numpy()\n2020-09-04 04:51:53.991893:\nI tensorflow\/stream_executor\/platform\/default\/dso_loader.cc:44]\nSuccessfully opened dynamic library libcublas.so.10\n>>>\n<\/pre><\/div>\n\n
    \n>>>predictions\n  array([[-0.0729934 , -0.5482341 , 0.3433068 , -0.15514854, 0.44248402,\n  \u3000\u3000\u3000\u3000\u3000 0.24744856, -0.15032545, 0.24870253, 0.16561234, -0.56604826]],\n  \u3000\u3000\u3000\u3000\u3000 dtype=float32)\n<\/pre><\/div>\n\n
    \n>>>tf.nn.softmax(predictions).numpy()\n<\/pre><\/div>\n\n
    \narray([[0.15495376, 0.12319947, 0.12194902, 0.07117186, 0.05812015,\n\u3000\u3000\u3000\u3000 0.0898917 , 0.08244707, 0.04264582, 0.13558292, 0.12003825]],\n\u3000\u3000\u3000\u3000 dtype=float32)\n<\/pre><\/div>\n\n
    \n>>>loss_fn = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)\n>>>loss_fn(y_train[:1], predictions).numpy()\n2.4091496\n<\/pre><\/div>\n\n
    \n>>>model.compile(optimizer='adam',\nloss=loss_fn,\nmetrics=['accuracy'])\n<\/pre><\/div>\n\n\n
    \u30e2\u30c7\u30eb\u306e\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\uff08\u5b66\u7fd2\uff09\u3092\u884c\u3044\u307e\u3059<\/h3>\n\n\n\n
    \u5b66\u7fd2\u30e2\u30c7\u30eb\u306b\u5bfe\u3057\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30c7\u30fc\u30bf\u3001\u6559\u5e2b\u30e9\u30d9\u30eb\u30c7\u30fc\u30bf\u3092\u4e0e\u3048\u3001\u753b\u50cf\u3068\u30e9\u30d9\u30eb\u306e\u5bfe\u5fdc\u95a2\u4fc2\u3092\u5b66\u7fd2\u3057\u307e\u3059\u3002\u30e2\u30c7\u30eb\u306b\u5bfe\u3057\u3001\u30c6\u30b9\u30c8\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u4e88\u6e2c\u3092\u884c\u308f\u305b\u3001\u4e88\u6e2c\u7d50\u679c\u3068\u30c6\u30b9\u30c8\u7528\u6559\u5e2b\u30e9\u30d9\u30eb\u3092\u7167\u5408\u3057\u307e\u3059\u3002\u30a8\u30dd\u30c3\u30af\u56de\u6570\u30925\u3068\u8a2d\u5b9a\u3057\u3001model.fit\u95a2\u6570\u3092\u4f7f\u3044\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3092\u958b\u59cb\u3057\u307e\u3059\u3002<\/p>\n\n\n
    \n>>>model.fit(x_train, y_train, epochs=5)\nEpoch 1\/5\n1875\/1875 [==============================] - 4s 2ms\/step - loss: 0.2965 - accuracy: 0.9138\nEpoch 2\/5\n1875\/1875 [==============================] - 3s 2ms\/step - loss: 0.1459 - accuracy: 0.9571\nEpoch 3\/5\n1875\/1875 [==============================] - 4s 2ms\/step - loss: 0.1082 - accuracy: 0.9674\nEpoch 4\/5\n1875\/1875 [==============================] - 4s 2ms\/step - loss: 0.0881 - accuracy: 0.9724\nEpoch 5\/5\n1875\/1875 [==============================] - 4s 2ms\/step - loss: 0.0754 - accuracy: 0.9768\n&lt;tensorflow.python.keras.callbacks.History object at 0x7f03d0b977b8>\n<\/pre><\/div>\n\n\n
    \u6b63\u89e3\u7387\u306e\u8a55\u4fa1<\/h3>\n\n\n\n
    \u30e2\u30c7\u30eb\u306e\u691c\u8a3c\u3092\u884c\u3044\u307e\u3059\u30025\u56de\u306e\u30a8\u30dd\u30c3\u30af\u3067\u30e2\u30c7\u30eb\u306e\u6b63\u89e3\u7387\u304c\u793a\u3055\u308c\u307e\u3057\u305f\u304c\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3067\u5229\u7528\u3057\u306a\u304b\u3063\u305f\u30c6\u30b9\u30c8\u7528\u30c7\u30fc\u30bf\u3068\u30c6\u30b9\u30c8\u7528\u6559\u5e2b\u30e9\u30d9\u30eb\u30c7\u30fc\u30bf\u3092\u4f7f\u3044\u3001\u8aa4\u5dee\u3068\u6b63\u89e3\u7387\u3092\u6c42\u3081\u307e\u3059\u3002<\/p>\n\n\n
    \n>>>model.evaluate(x_test, y_test, verbose=2)\n313\/313 - 1s - loss: 0.0737 - accuracy: 0.9774\n[0.07369402796030045, 0.977400004863739]\n<\/pre><\/div>\n\n\n
    \u691c\u8a3c\u7d50\u679c\u306f\u4e0a\u8a18\u306e\u3088\u3046\u306b\u8aa4\u5dee\u304c\u7d04 0.07<\/strong> \u3001\u6b63\u89e3\u7387\u306f\u7d04 0.98<\/strong> \u3068\u8868\u793a\u3055\u308c\u307e\u3057\u305f\u3002
    5\u56de\u306e\u5b66\u7fd2\u3067\u9ad8\u3044\u6b63\u89e3\u7387\u304c\u51fa\u305f\u3053\u3068\u3067\u3001\u3053\u3053\u3067\u5b66\u7fd2\u306f\u7d42\u4e86\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
    \u30c6\u30b9\u30c8\u7528\u753b\u50cf\u3067\u63a8\u8ad6<\/h3>\n\n\n\n
    \u5b66\u7fd2\u304c\u7d42\u308f\u3063\u305f\u306e\u3067\u3001\u6700\u5f8c\u306b\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u6e08\u30e2\u30c7\u30eb\u3092\u4f7f\u3063\u3066\u63a8\u8ad6\u51e6\u7406\u3057\u307e\u3059\u304c\u3001\u30bd\u30d5\u30c8\u30de\u30c3\u30af\u30b9\u95a2\u6570\u3092\u30e2\u30c7\u30eb\u5168\u4f53\u306b\u5bfe\u3057\u3066\u6307\u5b9a\u3057\u3001\u30c6\u30b9\u30c8\u7528\u753b\u50cf\uff15\u3064\u306b\u3064\u3044\u3066\u63a8\u8ad6\u3057\u307e\u3059\u3002<\/p>\n\n\n
    \n>>>probability_model = tf.keras.Sequential([\n\u3000\u3000model,\n\u3000\u3000tf.keras.layers.Softmax()\n])\n>>>probability_model(x_test[:5])\n<\/pre><\/div>\n\n\n
    \u4ee5\u4e0b\u306e\u3088\u3046\u306a\u7d50\u679c\u306b\u306a\u308a\u307e\u3057\u305f\u3002<\/p>\n\n\n
    \n&lt;tf.Tensor: shape=(5, 10), dtype=float32, numpy=\n\u3000\u3000\u3000array([[7.41418518e-08, 7.91325783e-10, 3.75941590e-06, 2.61097477e-04,\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000 9.48091952e-11, 3.16857694e-07, 4.86965676e-11, 9.99731362e-01,\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000 4.52538757e-07, 2.88244155e-06],\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000[1.33913982e-11, 2.29599886e-04, 9.99751031e-01, 1.92872030e-05,\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000 1.66144136e-15, 1.58800315e-08, 2.13381668e-08, 9.98626540e-16,\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000 3.95744095e-08, 4.06508526e-14],\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000[4.50110349e-07, 9.99431074e-01, 3.84905434e-05, 1.16055037e-06,\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000 3.32167328e-05, 5.31233536e-06, 1.03985847e-04, 3.38415528e-04,\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000 4.75658890e-05, 1.63871476e-07],\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000[9.99950290e-01, 7.11293871e-12, 3.84013947e-05, 2.12064151e-07,\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000 1.02987372e-07, 4.20437999e-07, 2.38990742e-06, 2.65470180e-06,\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000 1.09450021e-07, 5.40031533e-06],\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000[7.92320952e-06, 2.07563033e-09, 8.12820872e-06, 2.62512536e-08,\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000 9.88838971e-01, 1.17090956e-07, 1.72804573e-06, 2.94550318e-05,\n\u3000\u3000\u3000\u3000\u3000\u3000\u3000 5.51807261e-06, 1.11081181e-02]], dtype=float32)>\n<\/pre><\/div>\n\n\n
    \u914d\u5217\u306e\u4e2d\u8eab\u3092\u78ba\u8a8d\u3057\u307e\u3059\u3002
    \uff11\u3064\u76ee\u306e\u30c6\u30b9\u30c8\u753b\u50cf\u306b\u5bfe\u3059\u308b\u63a8\u8ad6\u7d50\u679c\u306f\u3001\u6570\u5b57\u306e\uff17\u3067\u3042\u308b\u78ba\u7387\u304c\u7d0499%<\/strong>\u3068\u6700\u3082\u9ad8\u304f\u306a\u308a\u307e\u3057\u305f\u3002\uff081\u756a\u76ee\u306e\u914d\u5217\u306e\u4e26\u3073\u9806\u306b\u6570\u5b57\u306e0,1,2,3,4,5,6,7,8,9\u3067\u3042\u308b\u78ba\u7387\u3092\u793a\u3057\u3066\u304a\u308a\u30019.99731362e-01 \u3068\u4e00\u756a\u9ad8\u3044\u78ba\u7387\u3092\u793a\u3057\u3066\u3044\u308b\u306e\u304c\u3001\u6570\u5b57\u306e\uff17\u306b\u5bfe\u5fdc\u3057\u305f\u30ce\u30fc\u30c9\u3067\u3042\u308b\u304b\u3089\uff09
    \u4ee5\u4e0b\u3001\u540c\u69d8\u306b\u898b\u3066\u3044\u304d\u307e\u3059\u3002
    2\u3064\u76ee\u306e\u30c6\u30b9\u30c8\u753b\u50cf\u306e\u63a8\u8ad6\u7d50\u679c\u306f\u6570\u5b57\u306e2\u3067\u3042\u308b\u78ba\u7387\u304c\u7d0499\uff05<\/strong>\u3001
    3\u3064\u76ee\u306e\u30c6\u30b9\u30c8\u753b\u50cf\u306e\u63a8\u8ad6\u7d50\u679c\u306f\u6570\u5b57\u306e1\u3067\u3042\u308b\u78ba\u7387\u304c\u7d0499\uff05<\/strong>\u3001
    4\u3064\u76ee\u306e\u30c6\u30b9\u30c8\u753b\u50cf\u306e\u63a8\u8ad6\u7d50\u679c\u306f\u6570\u5b57\u306e0\u3067\u3042\u308b\u78ba\u7387\u304c\u7d0499\uff05<\/strong>\u3001
    5\u3064\u76ee\u306e\u30c6\u30b9\u30c8\u753b\u50cf\u306e\u63a8\u8ad6\u7d50\u679c\u306f\u6570\u5b57\u306e4\u3067\u3042\u308b\u78ba\u7387\u304c\u7d0499\uff05<\/strong>
    \u3068\u7b97\u51fa\u3055\u308c\u307e\u3057\u305f\u3002<\/p>\n\n\n
    \n
    \"\"<\/figure>\n<\/div>\n\n\n
    \u30c6\u30b9\u30c8\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u753b\u50cf\u30d5\u30a1\u30a4\u30eb\u306e\u4e2d\u8eab\u306e\u4e00\u90e8\u306f\u4e0b\u8a18\u306e\u3088\u3046\u306a\u3063\u3066\u3044\u307e\u3059\u3002
    <\/p>\n\n\n\n
    \u5de6\u7aef\u304b\u3089\u53f3\u65b9\u5411\u306b\uff11\u3064\u76ee\u304b\u30895\u3064\u76ee\u306e\u753b\u50cf\u3068\u63a8\u8ad6\u7d50\u679c\u3092\u7167\u3089\u3057\u5408\u308f\u305b\u308b\u3068\u3001\uff17\u3001\uff12\u3001\uff11\u3001\uff10\u3001\uff14\u3067\u5408\u81f4\u3057\u3066\u3044\u308b\u3053\u3068\u304c\u308f\u304b\u308a\u307e\u3057\u305f\u3002<\/p>\n\n\n\n
    \u516c\u5f0f\u30ac\u30a4\u30c9\u306e\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u306b\u6cbf\u3063\u3066\u3001\u624b\u66f8\u304d\u6587\u5b57\u8a8d\u8b58\u306e\u30e2\u30c7\u30eb\u69cb\u7bc9\u3001\u5b66\u7fd2\u3001\u63a8\u8ad6\u3068\u3044\u3046\u4e00\u9023\u306e\u6d41\u308c\u3092\u898b\u3066\u304d\u307e\u3057\u305f\u3002
    \u30b3\u30f3\u30c6\u30ca\u5185\u90e8\u3067\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3092\u5229\u7528\u3059\u308b\u3053\u3068\u3067\u3001\u307b\u3068\u3093\u3069\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u3059\u308b\u3053\u3068\u306a\u304f\u3001\u95a2\u6570\u306e\u547c\u3073\u51fa\u3057\u3068\u30d1\u30e9\u30e1\u30fc\u30bf\u306e\u8a2d\u5b9a\u306b\u3088\u308a\u3001\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u3067\u304d\u308b<\/strong>\u3053\u3068\u304c\u78ba\u8a8d\u3067\u304d\u307e\u3057\u305f\u3002<\/p>\n\n\n\n
    Chainer\u3092\u4f7f\u3063\u305f\u6a5f\u68b0\u5b66\u7fd2<\/h2>\n\n\n\n
    \u524d\u56de\u3001TensorFlow<\/mark>\u3068Keras<\/mark>\u3092\u4f7f\u3063\u3066\u624b\u66f8\u304d\u6587\u5b57\u306e\u5206\u985e\u3092\u884c\u3044\u307e\u3057\u305f\u304c\u3001\u4eca\u56de\u306fChainer<\/mark>\u306e\u958b\u767a\u5143\u3067\u3042\u308bPFN\u793e\u306e\u30b5\u30a4\u30c8\u306b\u3042\u308bChainer\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u306b\u6cbf\u3063\u3066\u6a5f\u68b0\u5b66\u7fd2\u3092\u884c\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
    Chainer(\u30c1\u30a7\u30a4\u30ca\u30fc)\u3068\u306f<\/h3>\n\n\n\n
    \u4eca\u56de\u3001\u3068\u308a\u3042\u3052\u308b Chainer \u306fPFN\uff08Preferred Networks\uff1a\u30d7\u30ea\u30d5\u30a1\u30fc\u30c9\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u30b9\uff09\u3068\u3044\u3046\u65e5\u672c\u306e\u4f01\u696d\u304c\u958b\u767a\u3057\u305fPython\u30d9\u30fc\u30b9\u306e\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u5411\u3051\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3059\u3002\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30bd\u30d5\u30c8\u30a6\u30a8\u30a2\u3067\u3042\u308b\u3053\u3068\u3084\u3001\u8907\u96d1\u306a\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3092\u6bd4\u8f03\u7684\u30b7\u30f3\u30d7\u30eb\u306b\u5b9a\u7fa9\u3067\u304d\u308b\u3053\u3068\u306a\u3069\u3001\u4f7f\u3044\u52dd\u624b\u306e\u826f\u3055\u304b\u3089\u65e5\u672c\u306e\u591a\u304f\u306e\u30e6\u30fc\u30b6\u30fc\u304b\u3089\u652f\u6301\u3055\u308c\u3066\u304d\u307e\u3057\u305f\u3002<\/p>\n\n\n\n
    \u4eca\u56de\u884c\u3046\u3053\u3068\u306e\u6982\u8981<\/h3>\n\n\n\n
    AI\u521d\u5b66\u8005\u306e\u65b9\u304c\u89aa\u3057\u307f\u3084\u3059\u3044\u8ab2\u984c\u3092\u6271\u3046\u3053\u3068\u3092\u610f\u56f3\u3057\u3001Chainer\u306e\u516c\u5f0f\u30b5\u30a4\u30c8\u306b\u8a18\u8f09\u3055\u308c\u3066\u3044\u308bChainer\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u306e\u4e2d\u304b\u308914.Chainer\u306e\u57fa\u790e<\/mark>\u3092\u53d6\u308a\u4e0a\u3052\u307e\u3057\u305f\u3002
    \u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u306e\u5185\u5bb9\u3092\u88dc\u8db3\u3057\u306a\u304c\u3089\u9032\u3081\u3066\u3044\u304d\u307e\u3059\u306e\u3067\u3001\u4e0b\u8a18\u306e\u8a18\u8f09\u4e8b\u9805\u3082\u3042\u308f\u305b\u3066\u898b\u3066\u3044\u305f\u3060\u3051\u308b\u3068\u7406\u89e3\u304c\u6df1\u307e\u308b\u3068\u601d\u3044\u307e\u3059\u3002
    \u3010\u53c2\u8003\u30b5\u30a4\u30c8\uff1ahttps:\/\/tutorials.chainer.org\/ja\/14_Basics_of_Chainer.html?hl=ja<\/a>\u3011<\/p>\n\n\n\n
    \u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3067\u884c\u3063\u3066\u3044\u308b\u4ee5\u4e0b\u306e\u5185\u5bb9\u3092\u5b9f\u8df5\u3057\u307e\u3059\u3002<\/p>\n\n\n\n
      \n
    1. \u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u306e\u30e2\u30c7\u30eb\u3092\u5b9a\u7fa9\u3059\u308b<\/li>\n\n\n\n
    2. \u69cb\u7bc9\u3057\u305f\u30e2\u30c7\u30eb\u306b\u5bfe\u3057\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u7528\u30c7\u30fc\u30bf\u3092\u4f7f\u3044\u3001\u5b66\u7fd2\u3092\u884c\u3046<\/li>\n\n\n\n
    3. \u30c6\u30b9\u30c8\u7528\u30c7\u30fc\u30bf\u3092\u4f7f\u3044\u3001\u30e2\u30c7\u30eb\u3092\u6027\u80fd\u8a55\u4fa1\u3059\u308b<\/li>\n<\/ol>\n\n\n\n
      Chainer\u306e\u30b3\u30f3\u30c6\u30ca\u3092\u6e96\u5099\u3059\u308b<\/h3>\n\n\n
      \n
      \"Chainer\u306e\u30b3\u30f3\u30c6\u30ca\u3092\u6e96\u5099\"<\/figure>\n<\/div>\n\n\n
      \u65e9\u901f\u3001docker hub\u304b\u3089chainer\u306e\u30b3\u30f3\u30c6\u30ca\u30a4\u30e1\u30fc\u30b8\u3092pull\u3057\u307e\u3057\u3087\u3046\u3002
      \u4e0b\u8a18\u306eURL\u304b\u3089 pip install \u30b3\u30de\u30f3\u30c9\u3067 chainer\u3092\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3057\u307e\u3059\u3002
      Dockerhub \u53c2\u7167\u30b5\u30a4\u30c8\uff1a      https:\/\/hub.docker.com\/r\/chainer\/chainer\/<\/a>
      <\/p>\n\n\n
      \n$ pip install chainer\n<\/pre><\/div>\n\n\n
      \u30b3\u30f3\u30c6\u30ca\u30a4\u30e1\u30fc\u30b8\u3092\u78ba\u8a8d\u3057\u307e\u3059\u3002<\/p>\n\n\n
      \n$ docker images chainer\/chainer\nREPOSITORY          TAG                 IMAGE ID            CREATED             SIZE\nchainer\/chainer     latest              3ce7a8bfbbab        3 months ago        4.24GB\n<\/pre><\/div>\n\n\n
      chainer\u306e\u30b3\u30f3\u30c6\u30ca\u5185\u304b\u3089nvidia-smi\u3092\u5b9f\u884c\u3057\u3001GPU\u304c\u8a8d\u8b58\u3067\u304d\u3066\u3044\u308b\u304b\u3092\u78ba\u8a8d\u3057\u307e\u3059\u3002<\/p>\n\n\n
      \n$ docker run --gpus all chainer\/chainer nvidia-smi\nFri Nov 20 05:30:28 2020\n+-----------------------------------------------------------------------------+\n| NVIDIA-SMI 440.64.00    Driver Version: 440.64.00    CUDA Version: 10.2     |\n|-------------------------------+----------------------+----------------------+\n| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |\n| Fan  Temp  Perf  Pwr:Usage\/Cap|         Memory-Usage | GPU-Util  Compute M. |\n|===============================+======================+======================|\n|   0  Tesla P40           Off  | 00000000:03:00.0 Off |                    0 |\n| N\/A   38C    P0    50W \/ 250W |  21697MiB \/ 22919MiB |      0%      Default |\n+-------------------------------+----------------------+----------------------+\n\n+-----------------------------------------------------------------------------+\n| Processes:                                                       GPU Memory |\n|  GPU       PID   Type   Process name                             Usage      |\n|=============================================================================|\n+-----------------------------------------------------------------------------+\n<\/pre><\/div>\n\n\n
      \u4e0a\u8a18\u306e\u3088\u3046\u306bGPU\u95a2\u9023\u306e\u60c5\u5831\u304c\u8868\u793a\u3055\u308c\u308b\u3053\u3068\u304c\u78ba\u8a8d\u3067\u304d\u307e\u3057\u305f\u3002<\/p>\n\n\n\n
      Python\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3059\u308b<\/h3>\n\n\n\n
      \u3042\u3089\u305f\u3081\u3066Chainer\u306e\u30b3\u30f3\u30c6\u30ca\u30a4\u30e1\u30fc\u30b8\u304b\u3089bash\u3092\u305f\u3061\u3042\u3052\u3001pip3 list\u30b3\u30de\u30f3\u30c9\u3067\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u6e08\u306e\u30d1\u30c3\u30b1\u30fc\u30b8\u4e00\u89a7\u3092\u8868\u793a\u3057\u307e\u3059\u3002<\/p>\n\n\n
      \n$ docker run --gpus all -it chainer\/chainer:latest bash\nroot@790e21b683b1:\/# pip3 list\nchainer (7.7.0)\ncupy-cuda92 (7.7.0)\nfastrlock (0.5)\nfilelock (3.0.12)\nnumpy (1.18.5)\npip (8.1.1)\nprotobuf (3.12.4)\nsetuptools (20.7.0)\nsix (1.15.0)\ntyping-extensions (3.7.4.2)\nwheel (0.29.0)\nYou are using pip version 8.1.1, however version 20.2.4 is available.\nYou should consider upgrading via the 'pip install --upgrade pip' command.\n<\/pre><\/div>\n\n\n
      pip\u306e\u30a2\u30c3\u30d7\u30b0\u30ec\u30fc\u30c9\u3092\u4fc3\u3059\u30e1\u30c3\u30bb\u30fc\u30b8\u304c\u8868\u793a\u3055\u308c\u305f\u306e\u3067\u5b9f\u65bd\u3057\u307e\u3059\u3002\uff08\u30a2\u30c3\u30d7\u30b0\u30ec\u30fc\u30c9\u306e\u5fc5\u8981\u304c\u306a\u3044\u65b9\u306f\u7121\u8996\u3057\u3066\u5148\u306b\u9032\u3093\u3067\u304f\u3060\u3055\u3044\uff09<\/p>\n\n\n
      \nroot@790e21b683b1:\/# pip3 install --upgrade pip\nCollecting pip\n  Downloading https:\/\/files.pythonhosted.org\/packages\/cb\/28\/91f26bd088ce8e22169032100d4260614fc3da435025ff389ef1d396a433\/pip-20.2.4-py2.py3-none-any.whl (1.5MB)\n    100% |################################| 1.5MB 652kB\/s\nInstalling collected packages: pip\n  Found existing installation: pip 8.1.1\n    Not uninstalling pip at \/usr\/lib\/python3\/dist-packages, outside environment \/usr\nSuccessfully installed pip-20.2.4\n<\/pre><\/div>\n\n\n
      \u30a2\u30c3\u30d7\u30b0\u30ec\u30fc\u30c9\u304c\u7d42\u308f\u3063\u305f\u306e\u3067\u3001\u3082\u3046\u4e00\u5ea6pip3 list\u30b3\u30de\u30f3\u30c9\u3067\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u6e08\u306e\u30d1\u30c3\u30b1\u30fc\u30b8\u4e00\u89a7\u3092\u8868\u793a\u3057\u307e\u3059\u3002<\/p>\n\n\n
      \nroot@790e21b683b1:\/# pip3 list\nWARNING: pip is being invoked by an old script wrapper. This will fail in a future version of pip.\nPlease see https:\/\/github.com\/pypa\/pip\/issues\/5599 for advice on fixing the underlying issue.\nTo avoid this problem you can invoke Python with '-m pip' instead of running pip directly.\nDEPRECATION: Python 3.5 reached the end of its life on September 13th, 2020. Please upgrade your Python as Python 3.5 is no longer maintained. pip 21.0 will drop support for Python 3.5 in January 2021. pip 21.0 will remove support for this functionality.\nPackage           Version\n----------------- -------\nchainer           7.7.0\ncupy-cuda92       7.7.0\nfastrlock         0.5\nfilelock          3.0.12\nnumpy             1.18.5\npip               20.2.4\nprotobuf          3.12.4\nsetuptools        20.7.0\nsix               1.15.0\ntyping-extensions 3.7.4.2\nwheel             0.29.0\n<\/pre><\/div>\n\n\n
      \u4eca\u56de\u306e\u6f14\u7fd2\u3067\u306f\u3001\u8a08\u7b97\u7d50\u679c\u3092\u30b0\u30e9\u30d5\u5316\u3059\u308b\u305f\u3081\u306b\u300cmatplotlib<\/mark>\u300d\u3068\u3044\u3046\u30b0\u30e9\u30d5\u63cf\u753b\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u5229\u7528\u3057\u307e\u3059\u306e\u3067\u3001\u3053\u306e\u30bf\u30a4\u30df\u30f3\u30b0\u3067\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3057\u3066\u304a\u304d\u307e\u3059\u3002<\/p>\n\n\n
      \nroot@790e21b683b1:\/# pip3 install matplotlib\nWARNING: pip is being invoked by an old script wrapper. This will fail in a future version of pip.\nPlease see https:\/\/github.com\/pypa\/pip\/issues\/5599 for advice on fixing the underlying issue.\nTo avoid this problem you can invoke Python with '-m pip' instead of running pip directly.\nDEPRECATION: Python 3.5 reached the end of its life on September 13th, 2020. Please upgrade your Python as Python 3.5 is no longer maintained. pip 21.0 will drop support for Python 3.5 in January 2021. pip 21.0 will remove support for this functionality.\nCollecting matplotlib\n  Downloading matplotlib-3.0.3-cp35-cp35m-manylinux1_x86_64.whl (13.0 MB)\n     |################################| 13.0 MB 13.3 MB\/s\nCollecting kiwisolver>=1.0.1\n  Downloading kiwisolver-1.1.0-cp35-cp35m-manylinux1_x86_64.whl (90 kB)\n     |################################| 90 kB 10.5 MB\/s\n\uff08\u7565\uff09\nSuccessfully installed cycler-0.10.0 kiwisolver-1.1.0 matplotlib-3.0.3 pyparsing-2.4.7 python-dateutil-2.8.1\n<\/pre><\/div>\n\n\n
      \u540c\u69d8\u306b\u300cscikit-learn<\/mark>\u300d\u3068\u3044\u3046Python\u306e\u6a5f\u68b0\u5b66\u7fd2\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u5229\u7528\u3057\u307e\u3059\u306e\u3067\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3057\u307e\u3059\u3002<\/p>\n\n\n
      \nroot@790e21b683b1:\/# pip3 install scikit-learn\nWARNING: pip is being invoked by an old script wrapper. This will fail in a future version of pip.\nPlease see https:\/\/github.com\/pypa\/pip\/issues\/5599 for advice on fixing the underlying issue.\nTo avoid this problem you can invoke Python with '-m pip' instead of running pip directly.\nDEPRECATION: Python 3.5 reached the end of its life on September 13th, 2020. Please upgrade your Python as Python 3.5 is no longer maintained. pip 21.0 will drop support for Python 3.5 in January 2021. pip 21.0 will remove support for this functionality.\nCollecting scikit-learn\n  Downloading scikit_learn-0.22.2.post1-cp35-cp35m-manylinux1_x86_64.whl (7.0 MB)\n     |################################| 7.0 MB 8.6 MB\/s\nCollecting scipy>=0.17.0\n  Downloading scipy-1.4.1-cp35-cp35m-manylinux1_x86_64.whl (26.0 MB)\n     |################################| 26.0 MB 53.8 MB\/s\n\uff08\u7565\uff09\nSuccessfully installed joblib-0.14.1 scikit-learn-0.22.2.post1 scipy-1.4.\n<\/pre><\/div>\n\n\n
      pip3 list\u30b3\u30de\u30f3\u30c9\u3067\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u6e08\u306e\u30d1\u30c3\u30b1\u30fc\u30b8\u4e00\u89a7\u3092\u8868\u793a\u3057\u307e\u3059\u3002\u300cmatplotlib<\/mark>\u300d\u300cscikit-learn<\/mark>\u300d\u95a2\u9023\u306e\u30e9\u30a4\u30d6\u30e9\u30ea\u304c\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3055\u308c\u305f\u3053\u3068\u304c\u78ba\u8a8d\u3067\u304d\u307e\u3057\u305f\u3002<\/p>\n\n\n
      \nroot@790e21b683b1:\/# pip3 list\nWARNING: pip is being invoked by an old script wrapper. This will fail in a future version of pip.\nPlease see https:\/\/github.com\/pypa\/pip\/issues\/5599 for advice on fixing the underlying issue.\nTo avoid this problem you can invoke Python with '-m pip' instead of running pip directly.\nDEPRECATION: Python 3.5 reached the end of its life on September 13th, 2020. Please upgrade your Python as Python 3.5 is no longer maintained. pip 21.0 will drop support for Python 3.5 in January 2021. pip 21.0 will remove support for this functionality.\nPackage           Version\n----------------- ------------\nchainer           7.7.0\ncupy-cuda92       7.7.0\ncycler            0.10.0\nfastrlock         0.5\nfilelock          3.0.12\njoblib            0.14.1\nkiwisolver        1.1.0\nmatplotlib        3.0.3\nnumpy             1.18.5\npip               20.2.4\nprotobuf          3.12.4\npyparsing         2.4.7\npython-dateutil   2.8.1\nscikit-learn      0.22.2.post1\nscipy             1.4.1\nsetuptools        20.7.0\nsix               1.15.0\ntyping-extensions 3.7.4.2\nwheel             0.29.0\n<\/pre><\/div>\n\n\n
      \u30b3\u30f3\u30c6\u30ca\u304b\u3089Python\u3092\u8d77\u52d5\u3057\u3001chainer\u3092\u5b9f\u884c\u3059\u308b\u74b0\u5883\u306e\u60c5\u5831\u3092\u8868\u793a\u3057\u307e\u3059\u3002<\/p>\n\n\n
      \nroot@790e21b683b1:\/# python3\nPython 3.5.2 (default, Oct  8 2019, 13:06:37)\n[GCC 5.4.0 20160609] on linux\nType "help", "copyright", "credits" or "license" for more information.\n>>> import chainer\n>>> chainer.print_runtime_info()\nPlatform: Linux-4.4.0-154-generic-x86_64-with-Ubuntu-16.04-xenial\nChainer: 7.7.0\nChainerX: Available\nNumPy: 1.18.5\nCuPy:\n  CuPy Version          : 7.7.0\n  CUDA Root             : \/usr\/local\/cuda\n  CUDA Build Version    : 9020\n  CUDA Driver Version   : 10020\n  CUDA Runtime Version  : 9020\n  cuBLAS Version        : 9020\n  cuFFT Version         : 9020\n  cuRAND Version        : 9020\n  cuSOLVER Version      : (9, 2, 0)\n  cuSPARSE Version      : 9020\n  NVRTC Version         : (9, 2)\n  cuDNN Build Version   : 7600\n  cuDNN Version         : 7605\n  NCCL Build Version    : 2408\n  NCCL Runtime Version  : 2408\n  CUB Version           : None\n  cuTENSOR Version      : None\niDeep: Not Available\n<\/pre><\/div>\n\n\n
      OS\u3084Chainer\u3001Numpy\u306e\u30d0\u30fc\u30b8\u30e7\u30f3\u60c5\u5831\u306a\u3069\u304c\u8868\u793a\u3055\u308c\u307e\u3059\u3002CuPy<\/mark>(GPU\u3092\u4f7f\u3044NumPy\u4e92\u63db\u306e\u6a5f\u80fd\u3092\u63d0\u4f9b\u3059\u308b\u30e9\u30a4\u30d6\u30e9\u30ea)\u3082\u5229\u7528\u3067\u304d\u308b\u3053\u3068\u304c\u308f\u304b\u308a\u307e\u3059\u3002<\/p>\n\n\n\n
      \u6a5f\u68b0\u5b66\u7fd2\u7528\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u6e96\u5099\u3059\u308b<\/h3>\n\n\n\n
      \u4eca\u56de\u306e\u6f14\u7fd2\u3067\u306f\u3001scikit-learn\u306b\u4ed8\u5c5e\u3057\u3066\u3044\u308b\u300eIris plants dataset\u300f\u3092\u4f7f\u3044\u3001\uff13\u7a2e\u985e\u306e\u3042\u3084\u3081\uff08\u30a2\u30a4\u30ea\u30b9\uff09\u306e\u82b1\u306e\u6e2c\u5b9a\u5024\u304b\u3089\u3001\u3069\u306e\u54c1\u7a2e\u306b\u5c5e\u3059\u308b\u304b\u3092\u5206\u985e\u3059\u308b\u6a5f\u68b0\u5b66\u7fd2\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3057\u307e\u3059\u3002
      \u53c2\u8003\uff1a\u300eIris plants dataset\u300f\u306e\u4ed5\u69d8\u306f\u3053\u3061\u3089<\/a><\/p>\n\n\n\n
      \u4f7f\u7528\u3059\u308b\u300eIris plants dataset\u300f\u3092\u8aad\u307f\u8fbc\u3093\u3067\u3001\u5185\u5bb9\u306b\u3064\u3044\u3066\u78ba\u8a8d\u3057\u307e\u3057\u3087\u3046\u3002
      sklearn.datasets \u30e2\u30b8\u30e5\u30fc\u30eb\u306b\u3042\u308b load_iris()<\/strong> \u95a2\u6570\u3092\u5b9f\u884c\u3059\u308b\u3053\u3068\u3067\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u8aad\u307f\u8fbc\u3080\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n
      \n>>> from sklearn.datasets import load_iris\n>>> iris = load_iris()\n<\/pre><\/div>\n\n\n
      load_iris() \u95a2\u6570\u306e\u8aac\u660e<\/a>\u306e\u30da\u30fc\u30b8\u3092\u53c2\u7167\u3059\u308b\u3068\u3001\u8a73\u7d30\u8aac\u660e\u304cDESCR\u3068\u3044\u3046\u5f15\u6570\u3067\u7167\u4f1a\u3067\u304d\u308b\u3068\u8a18\u8f09\u3055\u308c\u3066\u3044\u307e\u3059\u306e\u3067\u3001\u78ba\u8a8d\u3057\u307e\u3059\u3002<\/p>\n\n\n
      \n>>> print(iris.DESCR)\n.. _iris_dataset:\n\nIris plants dataset\n--------------------\n\n**Data Set Characteristics:**\n\n    :Number of Instances: 150 (50 in each of three classes)\n    :Number of Attributes: 4 numeric, predictive attributes and the class\n    :Attribute Information:\n        - sepal length in cm\n        - sepal width in cm\n        - petal length in cm\n        - petal width in cm\n        - class:\n                - Iris-Setosa\n                - Iris-Versicolour\n                - Iris-Virginica\n\n    :Summary Statistics:\n\n    ============== ==== ==== ======= ===== ====================\n                    Min  Max   Mean    SD   Class Correlation\n    ============== ==== ==== ======= ===== ====================\n    sepal length:   4.3  7.9   5.84   0.83    0.7826\n    sepal width:    2.0  4.4   3.05   0.43   -0.4194\n    petal length:   1.0  6.9   3.76   1.76    0.9490  (high!)\n    petal width:    0.1  2.5   1.20   0.76    0.9565  (high!)\n    ============== ==== ==== ======= ===== ====================\n\n    :Missing Attribute Values: None\n    :Class Distribution: 33.3% for each of 3 classes.\n    :Creator: R.A. Fisher\n    :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\n    :Date: July, 1988\n\n<\/pre><\/div>\n\n\n
      **Data Set Characteristics:*<\/span><\/strong>*<\/strong>\u3068\u66f8\u304b\u308c\u305f\u90e8\u5206\u306b\u6ce8\u76ee\u3057\u307e\u3059\u3002<\/span>9\u884c\u76ee\u306b150 \u500b\u306e\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9\uff08\u3042\u3084\u3081\u306e\u30c7\u30fc\u30bf\uff09\u304c\u5b58\u5728\u3057\u3001\u5404\u3005\uff15\uff10\u500b\u305a\u3064\u306e\uff13\u3064\u306e\u30af\u30e9\u30b9\u304b\u3089\u69cb\u6210\u3055\u308c\u3066\u3044\u308b\u3068\u8a18\u8f09\u3055\u308c\u3066\u3044\u307e\u3059\u3002
      10\u884c\u76ee\u300111\u884c\u76ee\u306e\u8a18\u8f09\u5185\u5bb9\u3092\u898b\u308b\u3068\u3001\u3053\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306b\u306f\u300cIris-Setosa<\/strong>\uff08\u30d2\u30aa\u30a6\u30ae\u30a2\u30e4\u30e1\uff09\u300d\u300cIris-Versicolour<\/strong>\uff08\u30a2\u30a4\u30ea\u30b9\u30d0\u30fc\u30b8\u30ab\u30e9\u30fc\uff09\u300d\u300cIris-Virginica<\/strong>\uff08\u30a2\u30a4\u30ea\u30b9\u30d0\u30fc\u30b8\u30cb\u30ab\uff09\u300d\u3068\u3044\u3046\uff13\u7a2e\u985e\u306e\u3042\u3084\u3081\u306e\u6e2c\u5b9a\u30c7\u30fc\u30bf\u304c\u542b\u307e\u308c\u3066\u304a\u308a\u3001\u300csepal<\/strong>\uff08\u304c\u304f\u7247\uff09\u300d\u300cpetal<\/strong>\uff08\u82b1\u5f01\uff09\u300d\u306e\u300clength\uff08\u9577\u3055\uff09\u300d\u300cwidth\uff08\u5e45\uff09\u300d\u3092\u8a08\u6e2c\u3057\u305f\u30c7\u30fc\u30bf\uff08\u5358\u4f4d\uff1a\u30bb\u30f3\u30c1\u30e1\u30fc\u30c8\u30eb\uff09\u304c\u542b\u307e\u308c\u3066\u3044\u308b\u3053\u3068\u304c\u308f\u304b\u308a\u307e\u3059\u3002load_iris()\u95a2\u6570\u3067150 \u500b\u306e\u3042\u3084\u3081\u306e\u304c\u304f\u7247\u306e\u9577\u3055\u30fb\u5e45\u3001\u82b1\u5f01\u306e\u9577\u3055\u30fb\u5e45\u306e\u30c7\u30fc\u30bf\u3068\u3001\u5404\u3005\u306e\u3042\u3084\u3081\u306e\u7a2e\u985e\u3092\u793a\u3059\u30af\u30e9\u30b9 ID\u3092\u53d6\u5f97\u3057\u3001\u305d\u308c\u305e\u308c x<\/span><\/code> \u3068 t<\/span><\/code> \u3068\u3044\u3046\u5909\u6570\u3067\u53d7\u3051\u53d6\u308a\u3001\u5404\u3005\u306e\u914d\u5217\u306e\u5f62\u3092\u8868\u793a\u3057\u307e\u3059\u3002
      \u3010\u53c2\u8003\u30da\u30fc\u30b8\uff1a      Visualizing Datasets<\/a>\u3011<\/p>\n\n\n
      \n
      \"Iris\"<\/figure>\n<\/div>\n\n
      \n>>> x, t = load_iris(return_X_y=True)\n>>> print('x:', x.shape)\nx: (150, 4)\n>>> print('t:', t.shape)\nt: (150,)\n<\/pre><\/div>\n\n\n
      \u30c7\u30fc\u30bf\u306e\u5f62\u5f0f\u3092 Chainer \u306b\u5408\u308f\u305b\u307e\u3059\u3002
      Chainer \u3067\u5b66\u7fd2\u7528\u30e2\u30c7\u30eb\u306b\u30c7\u30fc\u30bf\u3092\u5f15\u304d\u6e21\u3059\u305f\u3081\u306b\u3001\u5165\u529b\u5024\u306e\u30c7\u30fc\u30bf\u578b\u3092 numpy.float32<\/strong>\uff0832\u30d3\u30c3\u30c8\u6d6e\u52d5\u5c0f\u6570\u70b9\u6570\uff09\u306b\u3001\u5206\u985e\u554f\u984c\u3067\u306f\u76ee\u6a19\u5024\u306e\u30c7\u30fc\u30bf\u578b\u3092 numpy.int32<\/strong>\uff0832\u30d3\u30c3\u30c8\u306e\u7b26\u53f7\u4ed8\u304d\u6574\u6570\uff09 \u306b\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002 NumPy\u914d\u5217ndarray\u3067\u306f\u30c7\u30fc\u30bf\u578bdtype\u3092\u4fdd\u6301\u3057\u3066\u304a\u308a\u3001\u3053\u308c\u3089\u306e\u578b\u306b\u5408\u308f\u305b\u308b\u305f\u3081 astype()<\/strong> \u95a2\u6570\u3092\u4f7f\u3063\u3066\u30c7\u30fc\u30bf\u578b\u3092\u5909\u66f4\u3057\u307e\u3059\u3002<\/p>\n\n\n
      \n>>> x = x.astype('float32')\n>>> t = t.astype('int32')\n<\/pre><\/div>\n\n\n
      \u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u5206\u5272\u3059\u308b<\/h3>\n\n\n\n
      \u5b66\u7fd2\u30e2\u30c7\u30eb\u306e\u6b63\u89e3\u7387\u3092\u6b63\u3057\u304f\u5224\u65ad\u3059\u308b\u305f\u3081\u306b\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u7528\u3068\u30c6\u30b9\u30c8\u7528\u306b\u5206\u5272\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u7528\u306b\u6e96\u5099\u3057\u305f\u30c7\u30fc\u30bf\u3092\u30c6\u30b9\u30c8\u7528\u306b\u3082\u4f7f\u3046\u3068\u3001\u65e2\u77e5\u306e\u30c7\u30fc\u30bf\u3067\u3042\u308b\u3053\u3068\u304b\u3089\u3001\u6b63\u89e3\u7387\u304c\u9ad8\u304f\u306a\u3063\u3066\u3057\u307e\u3046\u305f\u3081\u3001\u305d\u308c\u3092\u907f\u3051\u308b\u305f\u3081\u306b\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u300c\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u7528\u300d\u3068\u300c\u30c6\u30b9\u30c8\u7528\u300d\u306b\u5206\u5272\u3057\u307e\u3059\u3002\u3053\u3053\u3067\u306f\u524d\u8ff0\u306e\uff12\u3064\u306b\u52a0\u3048\u300c\u691c\u8a3c\u7528\u300d\u306e3\u3064\u306b\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u5206\u5272\u3057\u307e\u3059\u3002
      \u307e\u305a\u306f\u5168\u4f53\u3092\u300e\u300c\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u300d<\/strong>\u3000\u300c\u691c\u8a3c\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u300d<\/strong>\u300f\u3068\u300e\u300c\u30c6\u30b9\u30c8\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u300d<\/strong>\u300f\u306e2\u3064\u306b\u5206\u5272\u3057\u307e\u3059\u3002\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u5206\u5272\u3059\u308b\u305f\u3081\u306bscikit-learn<\/strong>\u306etrain_test_split<\/strong>()\u95a2\u6570\u3092\u4f7f\u7528\u3057\u307e\u3059\u3002
      \u3053\u306e\u3068\u304d\u300c\u30c6\u30b9\u30c8\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u300d\u306e\u30b5\u30a4\u30ba\u3092\u5168\u4f53\u306e30%\u306b\u3059\u308b\u305f\u3081\u306b\u95a2\u6570\u306e\u5f15\u6570 test_size<\/strong>=0.3 \u3068\u6307\u5b9a\u3057\u307e\u3059\u3002\u3053\u308c\u3067\u3001\u300c\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u300d\u3068\u300c\u691c\u8a3c\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u300d\u3092\u5408\u308f\u305b\u305f\u30c7\u30fc\u30bf\u304c\u5168\u4f53\u306e70\uff05\u3001\u30c6\u30b9\u30c8\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u304c30\uff05\u306b\u5206\u5272\u3055\u308c\u307e\u3059\u3002 \u5f15\u6570 random_state<\/span><\/strong>=0 \u306f\u3001\u4e71\u6570\u306e\u30b7\u30fc\u30c9\u5024\u3092\u6307\u5b9a\u3057\u306a\u3044\u8a2d\u5b9a\u3067\u3059\u3002train_test_split()\u95a2\u6570\u3092\u4f7f\u3044\u3001\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u5206\u5272\u3059\u308b\u51e6\u7406\u3092\u8907\u6570\u56de\u884c\u3063\u305f\u969b\u306b\u3001\u6bce\u56de\u7570\u306a\u308b\u6570\u5b57\u306e\u4e26\u3073\u306b\u306a\u308b\u3088\u3046\u306b\u5b9f\u884c\u3059\u308b\u305f\u3073\u30e9\u30f3\u30c0\u30e0\u306b\u5206\u5272\u3057\u305f\u3044\u5834\u5408\u306f\u4e71\u6570\u306e\u30b7\u30fc\u30c9\u5024\u3092\u6307\u5b9a\u3057\u307e\u305b\u3093\u3002<\/span><\/p>\n\n\n
      \n>>> from sklearn.model_selection import train_test_split\n>>> x_train_val, x_test, t_train_val, t_test = train_test_split(x, t, test_size=0.3, random_state=0)\n<\/pre><\/div>\n\n\n
      \u7d9a\u3044\u3066\u300c\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u300d\u3068\u300c\u691c\u8a3c\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u300d\u306b\u5206\u5272\u3057\u307e\u3059\u3002 \u300c\u691c\u8a3c\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u300d\u306e\u30b5\u30a4\u30ba\u306f\u300c\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u300d\u300c\u691c\u8a3c\u7528\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u300d\u3092\u5408\u308f\u305b\u305f\u30b5\u30a4\u30ba\u306e30%\u306b\u306a\u308b\u3088\u3046test_size=0.3\u3068\u6307\u5b9a\u3057\u307e\u3059\u3002<\/p>\n\n\n
      \n>>> x_train, x_val, t_train, t_val = train_test_split(x_train_val, t_train_val, test_size=0.3, random_state=0)\n<\/pre><\/div>\n\n\n
      \u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u306e\u30e2\u30c7\u30eb\u5b9a\u7fa9<\/h3>\n\n\n\n
      \u7d9a\u3051\u3066\u3001\u3042\u3084\u3081\u306e\u7a2e\u985e\u3092\u5206\u985e\u3059\u308b\u305f\u3081\u306e\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3092\u69cb\u7bc9\u3057\u307e\u3059\u3002\u4eca\u56de\u3068\u308a\u3042\u3052\u305fChainer\u306e\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3067\u306f\u300cSequential\u30e2\u30c7\u30eb<\/strong>\u300d\u3068\u547c\u3070\u308c\u308b\u3001\u5404\u5c64\u3092\u9806\u756a\u306b\u3064\u306a\u3052\u3066\u3044\u304f\u30e2\u30c7\u30eb\u3092\u5b9a\u7fa9\u3057\u3066\u3044\u307e\u3059\u3002
      chainer\u3067\u30e2\u30c7\u30eb\u306e\u5b9a\u7fa9\u3092\u3059\u308b\u306b\u3042\u305f\u3063\u3066\u3001chainer.links<\/strong>\uff08\u30d1\u30e9\u30e1\u30fc\u30bf\u3092\u6301\u3064\u95a2\u6570\uff09 \u3001chainer.functions<\/strong>\uff08\u30d1\u30e9\u30e1\u30fc\u30bf\u3092\u6301\u305f\u306a\u3044\u95a2\u6570\uff09 \u3068\u3044\u3046\u95a2\u6570\u3092\u5229\u7528\u3067\u304d\u308b\u3088\u3046\u6e96\u5099\u3057\u307e\u3059\u3002
      import chainer.links as L<\/strong> \u3084 import chainer.functions as F<\/strong> \u306e\u3088\u3046\u306b\u5225\u540d\u3092\u4ed8\u4e0e\u3059\u308b\u8a18\u8ff0\u306e\u4ed5\u65b9\u306b\u3064\u3044\u3066\u306f\u3001chainer\u3092\u4f7f\u3046\u969b\u306e\u304a\u4f5c\u6cd5\u306e\u3088\u3046\u306a\u3082\u306e\u3068\u8003\u3048\u307e\u3057\u3087\u3046\u3002<\/p>\n\n\n
      \n>>> import chainer.links as L\n>>> import chainer.functions as F\n<\/pre><\/div>\n\n\n
      \u5148\u305a\u3001\u5165\u529b\u6b21\u5143\u6570\u304c 3\u3001\u51fa\u529b\u6b21\u5143\u6570\u304c 2 \u306e\u5168\u7d50\u5408\u5c64\u3092 L.Linear \u30af\u30e9\u30b9\u3067\u5b9a\u7fa9\u3057\u307e\u3059\u3002\u7b2c1\u5f15\u6570\u306f\u5165\u529b\u4fe1\u53f7\u6570\u3001\u7b2c2\u5f15\u6570\u306f\u51fa\u529b\u4fe1\u53f7\u6570\u3067\u3059\u3002\u5168\u7d50\u5408\u5c64\u3068\u306f\u3001\u3059\u3079\u3066\u306e\u30ce\u30fc\u30c9\u304c\u6b21\u306e\u5c64\u306e\u3059\u3079\u3066\u306e\u30ce\u30fc\u30c9\u306b\u3064\u306a\u304c\u3063\u3066\u3044\u308b\u5c64\u306a\u306e\u3067\u30013\u500b\u306e\u30ce\u30fc\u30c9\u304b\u30892\u500b\u306e\u30ce\u30fc\u30c9\u306b\u63a5\u7d9a\u3059\u308b\u8a18\u8ff0\u306f\u4ee5\u4e0b\u306b\u306a\u308a\u307e\u3059\u3002<\/p>\n\n\n
      \n>>> l = L.Linear(3, 2)\n<\/pre><\/div>\n\n\n
      \u6b21\u306b Sequential \u30af\u30e9\u30b9\u3068 Linear \u30af\u30e9\u30b9\u3001relu() \u3092\u4f7f\u3063\u3066\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3092\u5b9a\u7fa9\u3057\u307e\u3059\u3002
      \u5165\u529b\u5c64\u3001\u4e2d\u9593\u5c64\u3001\u51fa\u529b\u5c64\u306e\uff13\u3064\u306e\u5c64\u306b\u3064\u3044\u3066\u4e0b\u8a18\u306e\u8a2d\u5b9a\u3092\u884c\u3044\u307e\u3059\u3002
      Iris \u306e\u30c7\u30fc\u30bf\u306f\u5165\u529b\u5909\u6570\u304c 4 \u3064\uff08\u300csepal<\/strong>\uff08\u304c\u304f\u7247\uff09\u300d\u300cpetal<\/strong>\uff08\u82b1\u5f01\uff09\u300d\u306e\u300clength\uff08\u9577\u3055\uff09<\/strong>\u300d\u300cwidth\uff08\u5e45\uff09<\/strong>\u300d\uff09\u3067\u3059\u306e\u3067\u3001\u6700\u521d\u306e\u5168\u7d50\u5408\u5c64\u306e\u5165\u529b\u6b21\u5143\u6570\u306f 4 \u306b\u306a\u308a\u307e\u3059\u3002
      2\u3064\u76ee\u306e\u5168\u7d50\u5408\u5c64\u306e\u5165\u529b\u6b21\u5143\u6570\u306f\u4efb\u610f\u306e\u5024\u3092\u6307\u5b9a\u53ef\u80fd\u3067\u3059\u304c\u3001\u3053\u3053\u3067\u306f 10 \u3068\u3057\u307e\u3059\u3002
      Iris \u306e\u30af\u30e9\u30b9\u6570\u306f 3 (\u3042\u3084\u3081\u306e\u7a2e\u985e\u304c\uff13\u3064)\u306a\u306e\u3067\u3001\u6700\u5f8c\u306e\u5168\u7d50\u5408\u5c64\u306e\u51fa\u529b\u6b21\u5143\u6570\u306f 3 \u3067\u3059\u3002
      \u6d3b\u6027\u5316\u95a2\u6570\u3068\u3057\u3066ReLU\u95a2\u6570\uff08\u30e9\u30f3\u30d7\u95a2\u6570\uff09\u3092\u9069\u7528\u3059\u308b\u3068\u30010\u4ee5\u4e0b\u306a\u3089\u300c0\u300d\u3092\u30010\u3088\u308a\u5927\u304d\u3051\u308c\u3070\u300c\u5165\u529b\u5024\u305d\u306e\u3082\u306e\u300d\u304c\u8fd4\u3063\u3066\u304d\u307e\u3059\u306e\u3067\u3001\u30de\u30a4\u30ca\u30b9\u5024\u3092\u5207\u308a\u6368\u3066\u3001\u7279\u5fb4\u304c\u306f\u3063\u304d\u308a\u3068\u3057\u305f\u30c7\u30fc\u30bf\u3068\u3057\u3066\u6271\u3046\u3053\u3068\u304c\u53ef\u80fd\u306b\u306a\u308a\u307e\u3059\u3002<\/p>\n\n\n
      \n>>> from chainer import Sequential\n>>>\n>>> n_input = 4\n>>> n_hidden = 10\n>>> n_output = 3\n>>>\n>>> net = Sequential(\n... L.Linear(n_input, n_hidden), F.relu,\n... L.Linear(n_hidden, n_hidden), F.relu,\n... L.Linear(n_hidden, n_output)\n... )\n>>>\n<\/pre><\/div>\n\n\n
      \u6700\u9069\u5316\u624b\u6cd5\u3092\u6c7a\u5b9a\u3059\u308b<\/h3>\n\n\n\n
      \u6a5f\u68b0\u5b66\u7fd2\u3067\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3092\u884c\u3046\u305f\u3081\u306e\u6700\u9069\u5316\u624b\u6cd5\u3092\u6c7a\u3081\u307e\u3059\u304c\u3001\u3053\u306e\u6f14\u7fd2\u3067\u306f\u3001\u78ba\u7387\u7684\u52fe\u914d\u964d\u4e0b\u6cd5 (SGD\uff1aStochastic Gradient Descent) \u3092\u5229\u7528\u3057\u307e\u3059\u3002 Chainer \u306b\u306f chainer.optimizers<\/strong> \u306b\u3044\u304f\u3064\u304b\u306e\u6700\u9069\u5316\u624b\u6cd5\u3092\u5229\u7528\u3059\u308b\u305f\u3081\u306e\u30af\u30e9\u30b9\u304c\u7528\u610f\u3055\u308c\u3066\u3044\u3066\u3001\u78ba\u7387\u7684\u52fe\u914d\u964d\u4e0b\u6cd5\u306f SGD \u3068\u3044\u3046\u540d\u524d\u3067\u5b9a\u7fa9\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n
      \u5b66\u7fd2\u7387 lr \u3092 0.01\u3068\u6307\u5b9a\u3057\u3001\u524d\u8ff0\u306echainer.optimizers.SGD<\/strong>\u3092\u5229\u7528\u3057\u3001optimizer \u3068\u3044\u3046\u540d\u524d\u306e\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9\u3092\u4f5c\u6210\u3057\u307e\u3059\u3002<\/p>\n\n\n
      \n>>> optimizer = chainer.optimizers.SGD(lr=0.01)\n<\/pre><\/div>\n\n\n
      \u30a4\u30f3\u30b9\u30bf\u30f3\u30b9 optimizer \u306b\u5bfe\u3057\u3001\u524d\u6bb5\u3067\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u306e\u5b9a\u7fa9\u3092\u3057\u305f net \u3092\u30bb\u30c3\u30c8\u3057\u3066\u3001net \u306e\u30d1\u30e9\u30e1\u30fc\u30bf\u304c\u78ba\u7387\u7684\u52fe\u914d\u964d\u4e0b\u6cd5\u306b\u3088\u3063\u3066\u66f4\u65b0\u3055\u308c\u308b\u3088\u3046\u306b\u3057\u307e\u3059\u3002<\/p>\n\n\n
      \n>>> optimizer.setup(net)\n<\/pre><\/div>\n\n\n
      \u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u306e\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3092\u5b9f\u884c\u3059\u308b<\/h3>\n\n\n\n
      \u3053\u3053\u307e\u3067\u306b\u5b9a\u7fa9\u3057\u305f\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3092\u4f7f\u3063\u3066\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3092\u884c\u3044\u307e\u3059\u304c\u3001\u305d\u306e\u305f\u3081\u306e\u30a8\u30dd\u30c3\u30af\u6570\u3068\u30d0\u30c3\u30c1\u30b5\u30a4\u30ba\u3092\u5404\u3005 30 \u3068 16 \u306b\u8a2d\u5b9a\u3057\u307e\u3059\u3002\u5143\u306b\u306a\u308b\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u30b5\u30a4\u30ba\u81ea\u4f53\u304c\u5c0f\u3055\u3044\u3053\u3068\u304b\u3089\u3001\u30d0\u30c3\u30c1\u30b5\u30a4\u30ba\u3082 16 \u3068\u5c0f\u3055\u304f\u8a2d\u5b9a\u3057\u300130\u56de\u306e\u5b66\u7fd2\u56de\u6570\u3067\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3092\u884c\u3044\u307e\u3059\u3002<\/p>\n\n\n
      \n>>> n_epoch = 30\n>>> n_batchsize = 16\n<\/pre><\/div>\n\n\n
      \u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u306e\u5b9f\u884c<\/b>
      \u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u306f\u4ee5\u4e0b\u306e\u51e6\u7406\u3092\u7e70\u308a\u8fd4\u3057\u307e\u3059\u3002<\/p>\n\n\n\n