{"id":402,"date":"2014-09-11T21:24:43","date_gmt":"2014-09-11T12:24:43","guid":{"rendered":"https:\/\/www.dogrow.net\/nnet\/?p=402"},"modified":"2022-02-15T18:07:26","modified_gmt":"2022-02-15T09:07:26","slug":"blog23","status":"publish","type":"post","link":"https:\/\/www.dogrow.net\/nnet\/blog23\/","title":{"rendered":"(23) GTX760\u304b\u3089GTX780\u306b\u5909\u3048\u3066\u307f\u308b"},"content":{"rendered":"

(22) cuda-convnet2\u306f\u3084\u3063\u3066\u307f\u308c\u306a\u3044 (T_T)<\/a> \u3067\u6b8b\u5ff5\u306a\u601d\u3044\u3092\u3057\u305f\u306e\u306f20\u65e5\u307b\u3069\u524d\u306e\u3053\u3068\u3002
\n\u3053\u3053\u6700\u8fd1\u30671\u4e07\u5186\u8fd1\u304f\u5024\u6bb5\u304c\u4e0b\u304c\u3063\u3066\u304d\u305fGTX780\u30924\u4e07\u5186\u5c11\u3005\u3067\u885d\u52d5\u8cb7\u3044\u3057\u305f\u3002<\/p>\n

27cm\u3082\u3042\u308b\u9577\u3044\u30dc\u30fc\u30c9\u306f\u7aae\u5c48\u306a\u7b50\u4f53\u5185\u3067\u96fb\u6c17\u30b9\u30c8\u30fc\u30d6\u306e\u3088\u3046\u306b\u9ad8\u71b1\u3092\u767a\u3057\u3066\u304a\u308a…
\n\u3057\u3070\u3089\u304f\u306f\u3053\u307e\u3081\u306b\u6e29\u5ea6\u3092\u78ba\u8a8d\u3057\u306a\u304c\u3089\u4f7f\u3046\u3053\u3068\u306b\u306a\u308a\u305d\u3046\u3002
\n\"20140911_01\"<\/p>\n

1. \u4e2d\u8eab\u3092\u306e\u305e\u3044\u3066\u307f\u308b<\/h1>\n

deviceQuery\u306e\u7d50\u679c\u306f\u4ee5\u4e0b\u306e\u901a\u308a\u3002
\nCompute capability 3.5 <\/span>\u304c\u3046\u308c\u3057\u3044\uff01
\nGTX780\u306ecore\u6570\u306f 2304\u500b<\/span>\u3001GTX650 384\u500b\u306e6\u500d<\/span>\u3001GTX760 1152\u500b\u306e2\u500d<\/span>\u306b\u306a\u3063\u305f\uff01<\/p>\n

Device 0: \"GeForce GTX 780\"\r\n  CUDA Driver Version \/ Runtime Version          6.0 \/ 6.0\r\n  CUDA Capability Major\/Minor version number:    3.5<\/span>\r\n  Total amount of global memory:                 3071 MBytes (3220504576 bytes)\r\n  (12) Multiprocessors, (192) CUDA Cores\/MP:     2304 CUDA Cores\r\n  GPU Clock rate:                                1058 MHz (1.06 GHz)\r\n  Memory Clock rate:                             3104 Mhz\r\n  Memory Bus Width:                              384-bit\r\n  L2 Cache Size:                                 1572864 bytes\r\n<\/pre>\n
2. cuda-convnet\u3067\u901f\u5ea6\u8a08\u6e2c<\/h1>\n
(21) GTX650\u304b\u3089GTX760\u306b\u5909\u3048\u3066\u307f\u308b<\/a> \u306e\u3068\u304d\u3068\u540c\u3058\u304f\u3001\u3061\u3087\u3063\u3068\u30ea\u30c3\u30c1\u306aMNIST\u5b66\u7fd2\u7528\u30cd\u30c3\u30c8\u30ef\u30fc\u30af100epochs\u3067\u8a08\u6e2c\u3057\u305f\u3002<\/p>\n
\u7d50\u679c\uff11: \u6700\u65b0\u74b0\u5883(intel Xeon x5570 x 2, GTX780<\/span>)<\/h3>\n
100epochs\u306e\u51e6\u7406\u6642\u9593\u306f 100\u79d2<\/span> \u3001\u30a8\u30e9\u30fc\u7387\u306f 0.010\u3060\u3063\u305f\u3002<\/p>\n
START: 2014\u5e74  9\u6708 11\u65e5 \u6728\u66dc\u65e5 20:57:46 JST\r\n======================Test output======================\r\nlogprob:  0.034160, 0.010400\r\nEND:   2014\u5e74  9\u6708 11\u65e5 \u6728\u66dc\u65e5 20:59:26 JST\r\n<\/pre>\n
\u7d50\u679c\uff12: \u76f4\u524d\u74b0\u5883(intel Xeon x5570 x 2, GTX760<\/span>)<\/h3>\n
100epochs\u306e\u51e6\u7406\u6642\u9593\u306f 157\u79d2<\/span> \u3001\u30a8\u30e9\u30fc\u7387\u306f 0.010\u3060\u3063\u305f\u3002<\/p>\n
START: 2014\u5e74  8\u6708 18\u65e5 \u6708\u66dc\u65e5 15:24:10 JST\r\n======================Test output======================\r\nlogprob:  0.034883, 0.010300\r\nEND:   2014\u5e74  8\u6708 18\u65e5 \u6708\u66dc\u65e5 15:26:47 JST\r\n<\/pre>\n
\u7d50\u679c\uff13: \u65e7\u30de\u30b7\u30f3(intel core-i3 3220, GTX650<\/span>)<\/h3>\n
100epochs\u306e\u51e6\u7406\u6642\u9593\u306f 398\u79d2<\/span> \u3001\u30a8\u30e9\u30fc\u7387\u306f 0.011\u3060\u3063\u305f\u3002<\/p>\n
START: 2014\u5e74  8\u6708 18\u65e5 \u6708\u66dc\u65e5 15:23:48 JST\r\n======================Test output======================\r\nlogprob:  0.034047, 0.010900\r\nEND:   2014\u5e74  8\u6708 18\u65e5 \u6708\u66dc\u65e5 15:30:26 JST\r\n<\/pre>\n
\n","protected":false},"excerpt":{"rendered":"
(22) cuda-convnet2\u306f\u3084\u3063\u3066\u307f\u308c\u306a\u3044 (T_T) \u3067\u6b8b\u5ff5\u306a\u601d\u3044\u3092\u3057\u305f\u306e\u306f20\u65e5\u307b\u3069\u524d\u306e\u3053\u3068\u3002 \u3053\u3053\u6700\u8fd1\u30671\u4e07\u5186\u8fd1\u304f\u5024\u6bb5\u304c\u4e0b\u304c\u3063\u3066\u304d\u305fGTX780\u30924\u4e07\u5186\u5c11\u3005\u3067\u885d\u52d5\u8cb7\u3044\u3057\u305f\u3002 27cm\u3082\u3042\u308b\u9577\u3044\u30dc\u30fc\u30c9\u306f\u7aae\u5c48\u2026 \u7d9a\u304d\u3092\u8aad\u3080 »<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[8,10],"tags":[],"class_list":["post-402","post","type-post","status-publish","format-standard","hentry","category-cuda","category-cuda-convnet"],"views":2846,"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/posts\/402","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/comments?post=402"}],"version-history":[{"count":13,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/posts\/402\/revisions"}],"predecessor-version":[{"id":771,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/posts\/402\/revisions\/771"}],"wp:attachment":[{"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/media?parent=402"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/categories?post=402"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/tags?post=402"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}