{"id":89843,"date":"2026-08-03T22:33:12","date_gmt":"2026-08-03T14:33:12","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/89843.html"},"modified":"2026-08-03T22:33:12","modified_gmt":"2026-08-03T14:33:12","slug":"%e6%af%95%e8%ae%be-%e6%b7%b1%e5%ba%a6%e5%ad%a6%e4%b9%a0%e6%89%8b%e5%86%99%e6%95%b0%e5%ad%97%e8%af%86%e5%88%ab%e7%b3%bb%e7%bb%9f%e6%ba%90%e7%a0%81%e8%ae%ba%e6%96%87","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/89843.html","title":{"rendered":"\u6bd5\u8bbe \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u6570\u5b57\u8bc6\u522b\u7cfb\u7edf(\u6e90\u7801+\u8bba\u6587)"},"content":{"rendered":"<\/p>\n<h4>\u6587\u7ae0\u76ee\u5f55<\/h4>\n<ul>\n<li>0 \u524d\u8a00<\/li>\n<li>1 \u9879\u76ee\u8fd0\u884c\u6548\u679c<\/li>\n<li>2 \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u5b57\u7b26\u8bc6\u522b\u539f\u7406<\/li>\n<li>\n<ul>\n<li>2.1 \u7ed3\u6784\u89e3\u6790<\/li>\n<li>2.2 C1\u5c42<\/li>\n<li>2.3 S2\u5c42<\/li>\n<li>\n<ul>\n<li>S2\u5c42\u548cC3\u5c42\u8fde\u63a5<\/li>\n<\/ul>\n<\/li>\n<li>2.4 F6\u4e0eC5\u5c42<\/li>\n<\/ul>\n<\/li>\n<li>3 \u5199\u6570\u5b57\u8bc6\u522b\u7b97\u6cd5\u6a21\u578b\u7684\u6784\u5efa<\/li>\n<li>\n<ul>\n<li>3.1 \u8f93\u5165\u5c42\u8bbe\u8ba1<\/li>\n<li>3.2 \u6fc0\u6d3b\u51fd\u6570\u7684\u9009\u53d6<\/li>\n<li>3.3 \u5377\u79ef\u5c42\u8bbe\u8ba1<\/li>\n<li>3.4 \u964d\u91c7\u6837\u5c42<\/li>\n<li>3.5 \u8f93\u51fa\u5c42\u8bbe\u8ba1<\/li>\n<\/ul>\n<\/li>\n<li>4 \u7f51\u7edc\u6a21\u578b\u7684\u603b\u4f53\u7ed3\u6784<\/li>\n<li>5 \u90e8\u5206\u5b9e\u73b0\u4ee3\u7801<\/li>\n<li>6 \u6700\u540e<\/li>\n<\/ul>\n<h2>0 \u524d\u8a00<\/h2>\n<p>&#x1f525;\u8fd9\u4e24\u5e74\u5f00\u59cb\u6bd5\u4e1a\u8bbe\u8ba1\u548c\u6bd5\u4e1a\u7b54\u8fa9\u7684\u8981\u6c42\u548c\u96be\u5ea6\u4e0d\u65ad\u63d0\u5347&#xff0c;\u4f20\u7edf\u7684\u6bd5\u8bbe\u9898\u76ee\u7f3a\u5c11\u521b\u65b0\u548c\u4eae\u70b9&#xff0c;\u5f80\u5f80\u8fbe\u4e0d\u5230\u6bd5\u4e1a\u7b54\u8fa9\u7684\u8981\u6c42&#xff0c;\u8fd9\u4e24\u5e74\u4e0d\u65ad\u6709\u5b66\u5f1f\u5b66\u59b9\u544a\u8bc9\u5b66\u957f\u81ea\u5df1\u505a\u7684\u9879\u76ee\u7cfb\u7edf\u8fbe\u4e0d\u5230\u8001\u5e08\u7684\u8981\u6c42\u3002\u5e76\u4e14\u5f88\u96be\u627e\u5230\u5b8c\u6574\u7684\u6bd5\u8bbe\u53c2\u8003\u5b66\u4e60\u8d44\u6599\u3002<\/p>\n<p>\u4e3a\u4e86\u5927\u5bb6\u80fd\u591f\u987a\u5229\u4ee5\u53ca\u6700\u5c11\u7684\u7cbe\u529b\u901a\u8fc7\u6bd5\u8bbe&#xff0c;\u5b66\u957f\u5206\u4eab\u4f18\u8d28\u6bd5\u4e1a\u8bbe\u8ba1\u9879\u76ee\u63d0\u4f9b\u5927\u5bb6\u53c2\u8003\u5b66\u4e60&#xff0c;\u4eca\u5929\u8981\u5206\u4eab\u7684\u662f<\/p>\n<p>&#x1f6a9; \u6bd5\u4e1a\u8bbe\u8ba1 \u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u7684\u65b0\u95fb\u6587\u672c\u5206\u7c7b\u7b97\u6cd5\u7cfb\u7edf(\u6e90\u7801&#043;\u8bba\u6587)<\/p>\n<p>&#x1f947;\u5b66\u957f\u8fd9\u91cc\u7ed9\u4e00\u4e2a\u9898\u76ee\u7efc\u5408\u8bc4\u5206(\u6bcf\u9879\u6ee1\u52065\u5206)<\/p>\n<p>\u96be\u5ea6\u7cfb\u6570&#xff1a;3\u5206 \u5de5\u4f5c\u91cf&#xff1a;3\u5206 \u521b\u65b0\u70b9&#xff1a;4\u5206<\/p>\n<p>&#x1f9ff;\u9879\u76ee\u5206\u4eab&#xff1a;\u89c1\u4e3b\u9875\u4efb\u610f\u7f6e\u9876\u6587\u7ae0<\/p>\n<h2>1 \u9879\u76ee\u8fd0\u884c\u6548\u679c<\/h2>\n<p><img decoding=\"async\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260803143306-6a70a6a285e81.png\" alt=\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\" \/><img decoding=\"async\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260803143307-6a70a6a357de0.png\" alt=\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\" \/> <img decoding=\"async\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260803143308-6a70a6a41854d.png\" alt=\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\" \/><\/p>\n<p>\u89c6\u9891\u6548\u679c&#xff1a;<\/p>\n<\/p>\n<p>\u6bd5\u4e1a\u8bbe\u8ba1 \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u6570\u5b57\u8bc6\u522b<\/p>\n<\/p>\n<h2>2 \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u5b57\u7b26\u8bc6\u522b\u539f\u7406<\/h2>\n<p>\u8fd9\u91cc\u4ee5LeNet-5\u4e3a\u4f8b\u8fdb\u884c\u6df1\u5ea6\u5b66\u4e60\u5b57\u7b26\u8bc6\u522b\u7684\u5927\u81f4\u8bb2\u89e3\u3002 <img decoding=\"async\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260803143309-6a70a6a53350a.png\" alt=\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\" \/><\/p>\n<h3>2.1 \u7ed3\u6784\u89e3\u6790<\/h3>\n<p>\u8fd9\u662f\u539f\u59cb\u7684\u5e94\u7528\u4e8e\u624b\u5199\u6570\u5b57\u8bc6\u522b\u7684\u7f51\u7edc&#xff0c;\u6211\u8ba4\u4e3a\u8fd9\u4e5f\u662f\u6700\u7b80\u5355\u7684\u6df1\u5ea6\u7f51\u7edc\u3002<\/p>\n<p>LeNet-5\u4e0d\u5305\u62ec\u8f93\u5165&#xff0c;\u4e00\u51717\u5c42&#xff0c;\u8f83\u4f4e\u5c42\u7531\u5377\u79ef\u5c42\u548c\u6700\u5927\u6c60\u5316\u5c42\u4ea4\u66ff\u6784\u6210&#xff0c;\u66f4\u9ad8\u5c42\u5219\u662f\u5168\u8fde\u63a5\u548c\u9ad8\u65af\u8fde\u63a5\u3002<\/p>\n<p>LeNet-5\u7684\u8f93\u5165\u4e0eBP\u795e\u7ecf\u7f51\u8def\u7684\u4e0d\u4e00\u6837\u3002\u8fd9\u91cc\u5047\u8bbe\u56fe\u50cf\u662f\u9ed1\u767d\u7684&#xff0c;\u90a3\u4e48LeNet-5\u7684\u8f93\u5165\u662f\u4e00\u4e2a32*32\u7684\u4e8c\u7ef4\u77e9\u9635\u3002\u540c \u65f6&#xff0c;\u8f93\u5165\u4e0e\u4e0b\u4e00\u5c42\u5e76\u4e0d\u662f\u5168\u8fde\u63a5\u7684&#xff0c;\u800c\u662f\u8fdb\u884c\u7a00\u758f\u8fde\u63a5\u3002\u672c\u5c42\u6bcf\u4e2a\u795e\u7ecf\u5143\u7684\u8f93\u5165\u6765\u81ea\u4e8e\u524d\u4e00\u5c42\u795e\u7ecf\u5143\u7684\u5c40\u90e8\u533a\u57df(5\u00d75)&#xff0c;\u5377\u79ef\u6838\u5bf9\u539f\u59cb\u56fe\u50cf\u5377\u79ef\u7684\u7ed3\u679c\u52a0\u4e0a\u76f8\u5e94\u7684\u9608\u503c&#xff0c;\u5f97\u51fa\u7684\u7ed3\u679c\u518d\u7ecf\u8fc7\u6fc0\u6d3b\u51fd\u6570\u5904\u7406&#xff0c;\u8f93\u51fa\u5373\u5f62\u6210\u5377\u79ef\u5c42&#xff08;C\u5c42&#xff09;\u3002\u5377\u79ef\u5c42\u4e2d\u7684\u6bcf\u4e2a\u7279\u5f81\u6620\u5c04\u90fd\u5404\u81ea\u5171\u4eab\u6743\u91cd\u548c\u9608\u503c&#xff0c;\u8fd9\u6837\u80fd\u5927\u5927\u51cf\u5c11\u8bad\u7ec3\u5f00\u9500\u3002\u964d\u91c7\u6837\u5c42&#xff08;S\u5c42&#xff09;\u4e3a\u51cf\u5c11\u6570\u636e\u91cf\u540c\u65f6\u4fdd\u5b58\u6709\u7528\u4fe1\u606f&#xff0c;\u8fdb\u884c\u4e9a\u62bd\u6837\u3002<\/p>\n<h3>2.2 C1\u5c42<\/h3>\n<p>\u7b2c\u4e00\u4e2a\u5377\u79ef\u5c42&#xff08;C1\u5c42&#xff09;\u75316\u4e2a\u7279\u5f81\u6620\u5c04\u6784\u6210&#xff0c;\u6bcf\u4e2a\u7279\u5f81\u6620\u5c04\u662f\u4e00\u4e2a28\u00d728\u7684\u795e\u7ecf\u5143\u9635\u5217&#xff0c;\u5176\u4e2d\u6bcf\u4e2a\u795e\u7ecf\u5143\u8d1f\u8d23\u4ece5\u00d75\u7684\u533a\u57df\u901a\u8fc7\u5377\u79ef\u6ee4\u6ce2\u5668\u63d0\u53d6\u5c40\u90e8\u7279\u5f81\u3002\u4e00\u822c\u60c5\u51b5\u4e0b&#xff0c;\u6ee4\u6ce2\u5668\u6570\u91cf\u8d8a\u591a&#xff0c;\u5c31\u4f1a\u5f97\u51fa\u8d8a\u591a\u7684\u7279\u5f81\u6620\u5c04&#xff0c;\u53cd\u6620\u8d8a\u591a\u7684\u539f\u59cb\u56fe\u50cf\u7684\u7279\u5f81\u3002\u672c\u5c42\u8bad\u7ec3\u53c2\u6570\u51716\u00d7(5\u00d75&#043;1)&#061;156\u4e2a&#xff0c;\u6bcf\u4e2a\u50cf\u7d20\u70b9\u90fd\u662f\u7531\u4e0a\u5c425\u00d75&#061;25\u4e2a\u50cf\u7d20\u70b9\u548c1\u4e2a\u9608\u503c\u8fde\u63a5\u8ba1\u7b97\u6240\u5f97&#xff0c;\u517128\u00d728\u00d7156&#061;122304\u4e2a\u8fde\u63a5\u3002<\/p>\n<h3>2.3 S2\u5c42<\/h3>\n<p>S2\u5c42\u662f\u5bf9\u5e94\u4e0a\u8ff06\u4e2a\u7279\u5f81\u6620\u5c04\u7684\u964d\u91c7\u6837\u5c42&#xff08;pooling\u5c42&#xff09;\u3002pooling\u5c42\u7684\u5b9e\u73b0\u65b9\u6cd5\u6709\u4e24\u79cd&#xff0c;\u5206\u522b\u662fmax-pooling\u548cmean-pooling&#xff0c;LeNet-5\u91c7\u7528\u7684\u662fmean-pooling&#xff0c;\u5373\u53d6n\u00d7n\u533a\u57df\u5185\u50cf\u7d20\u7684\u5747\u503c\u3002C1\u901a\u8fc72\u00d72\u7684\u7a97\u53e3\u533a\u57df\u50cf\u7d20\u6c42\u5747\u503c\u518d\u52a0\u4e0a\u672c\u5c42\u7684\u9608\u503c&#xff0c;\u7136\u540e\u7ecf\u8fc7\u6fc0\u6d3b\u51fd\u6570\u7684\u5904\u7406&#xff0c;\u5f97\u5230S2\u5c42\u3002pooling\u7684\u5b9e\u73b0&#xff0c;\u5728\u4fdd\u5b58\u56fe\u7247\u4fe1\u606f\u7684\u57fa\u7840\u4e0a&#xff0c;\u51cf\u5c11\u4e86\u6743\u91cd\u53c2\u6570&#xff0c;\u964d\u4f4e\u4e86\u8ba1\u7b97\u6210\u672c&#xff0c;\u8fd8\u80fd\u63a7\u5236\u8fc7\u62df\u5408\u3002\u672c\u5c42\u5b66\u4e60\u53c2\u6570\u5171\u67091*6&#043;6&#061;12\u4e2a&#xff0c;S2\u4e2d\u7684\u6bcf\u4e2a\u50cf\u7d20\u90fd\u4e0eC1\u5c42\u4e2d\u76842\u00d72\u4e2a\u50cf\u7d20\u548c1\u4e2a\u9608\u503c\u76f8\u8fde&#xff0c;\u51716\u00d7(2\u00d72&#043;1)\u00d714\u00d714&#061;5880\u4e2a\u8fde\u63a5\u3002<\/p>\n<h4>S2\u5c42\u548cC3\u5c42\u8fde\u63a5<\/h4>\n<p>S2\u5c42\u548cC3\u5c42\u7684\u8fde\u63a5\u6bd4\u8f83\u590d\u6742\u3002C3\u5377\u79ef\u5c42\u662f\u753116\u4e2a\u5927\u5c0f\u4e3a10\u00d710\u7684\u7279\u5f81\u6620\u5c04\u7ec4\u6210\u7684&#xff0c;\u5f53\u4e2d\u7684\u6bcf\u4e2a\u7279\u5f81\u6620\u5c04\u4e0eS2\u5c42\u7684\u82e5\u5e72\u4e2a\u7279\u5f81\u6620\u5c04\u7684\u5c40\u90e8\u611f\u53d7\u91ce&#xff08;\u5927\u5c0f\u4e3a5\u00d75&#xff09;\u76f8\u8fde\u3002\u5176\u4e2d&#xff0c;\u524d6\u4e2a\u7279\u5f81\u6620\u5c04\u4e0eS2\u5c42\u8fde\u7eed3\u4e2a\u7279\u5f81\u6620\u5c04\u76f8\u8fde&#xff0c;\u540e\u9762\u63a5\u7740\u76846\u4e2a\u6620\u5c04\u4e0eS2\u5c42\u7684\u8fde\u7eed\u76844\u4e2a\u7279\u5f81\u6620\u5c04\u76f8\u8fde&#xff0c;\u7136\u540e\u76843\u4e2a\u7279\u5f81\u6620\u5c04\u4e0eS2\u5c42\u4e0d\u8fde\u7eed\u76844\u4e2a\u7279\u5f81\u6620\u5c04\u76f8\u8fde&#xff0c;\u6700\u540e\u4e00\u4e2a\u6620\u5c04\u4e0eS2\u5c42\u7684\u6240\u6709\u7279\u5f81\u6620\u5c04\u76f8\u8fde\u3002<\/p>\n<p>\u6b64\u5904\u5377\u79ef\u6838\u5927\u5c0f\u4e3a5\u00d75&#xff0c;\u6240\u4ee5\u5b66\u4e60\u53c2\u6570\u5171\u67096\u00d7(3\u00d75\u00d75&#043;1)&#043;9\u00d7(4\u00d75\u00d75&#043;1)&#043;1\u00d7(6\u00d75\u00d75&#043;1)&#061;1516\u4e2a\u53c2\u6570\u3002\u800c\u56fe\u50cf\u5927\u5c0f\u4e3a28\u00d728&#xff0c;\u56e0\u6b64\u5171\u6709151600\u4e2a\u8fde\u63a5\u3002<\/p>\n<p>S4\u5c42\u662f\u5bf9C3\u5c42\u8fdb\u884c\u7684\u964d\u91c7\u6837&#xff0c;\u4e0eS2\u540c\u7406&#xff0c;\u5b66\u4e60\u53c2\u6570\u670916\u00d71&#043;16&#061;32\u4e2a&#xff0c;\u540c\u65f6\u5171\u670916\u00d7(2\u00d72&#043;1)\u00d75\u00d75&#061;2000\u4e2a\u8fde\u63a5\u3002 C5\u5c42\u662f\u7531120\u4e2a\u5927\u5c0f\u4e3a1\u00d71\u7684\u7279\u5f81\u6620\u5c04\u7ec4\u6210\u7684\u5377\u79ef\u5c42&#xff0c;\u800c\u4e14S4\u5c42\u4e0eC5\u5c42\u662f\u5168\u8fde\u63a5\u7684&#xff0c;\u56e0\u6b64\u5b66\u4e60\u53c2\u6570\u603b\u4e2a\u6570\u4e3a120\u00d7(16\u00d725&#043;1)&#061;48120\u4e2a\u3002<\/p>\n<h3>2.4 F6\u4e0eC5\u5c42<\/h3>\n<p>F6\u662f\u4e0eC5\u5168\u8fde\u63a5\u768484\u4e2a\u795e\u7ecf\u5143&#xff0c;\u6240\u4ee5\u5171\u670984\u00d7(120&#043;1)&#061;10164\u4e2a\u5b66\u4e60\u53c2\u6570\u3002<\/p>\n<p>\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u901a\u8fc7\u901a\u8fc7\u7a00\u758f\u8fde\u63a5\u548c\u5171\u4eab\u6743\u91cd\u548c\u9608\u503c&#xff0c;\u5927\u5927\u51cf\u5c11\u4e86\u8ba1\u7b97\u7684\u5f00\u9500&#xff0c;\u540c\u65f6&#xff0c;pooling\u7684\u5b9e\u73b0&#xff0c;\u4e00\u5b9a\u7a0b\u5ea6\u4e0a\u51cf\u5c11\u4e86\u8fc7\u62df\u5408\u95ee\u9898\u7684\u51fa\u73b0&#xff0c;\u975e\u5e38\u9002\u5408\u7528\u4e8e\u56fe\u50cf\u7684\u5904\u7406\u548c\u8bc6\u522b\u3002<\/p>\n<h2>3 \u5199\u6570\u5b57\u8bc6\u522b\u7b97\u6cd5\u6a21\u578b\u7684\u6784\u5efa<\/h2>\n<h3>3.1 \u8f93\u5165\u5c42\u8bbe\u8ba1<\/h3>\n<p>\u8f93\u5165\u4e3a28\u00d728\u7684\u77e9\u9635&#xff0c;\u800c\u4e0d\u662f\u5411\u91cf\u3002<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260803143309-6a70a6a54f7e1.png\" alt=\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\" \/><\/p>\n<h3>3.2 \u6fc0\u6d3b\u51fd\u6570\u7684\u9009\u53d6<\/h3>\n<p>Sigmoid\u51fd\u6570\u5177\u6709\u5149\u6ed1\u6027\u3001\u9c81\u68d2\u6027\u548c\u5176\u5bfc\u6570\u53ef\u7528\u81ea\u8eab\u8868\u793a\u7684\u4f18\u70b9&#xff0c;\u4f46\u5176\u8fd0\u7b97\u6d89\u53ca\u6307\u6570\u8fd0\u7b97&#xff0c;\u53cd\u5411\u4f20\u64ad\u6c42\u8bef\u5dee\u68af\u5ea6\u65f6&#xff0c;\u6c42\u5bfc\u53c8\u6d89\u53ca\u4e58\u9664\u8fd0\u7b97&#xff0c;\u8ba1\u7b97\u91cf\u76f8\u5bf9\u8f83\u5927\u3002\u540c\u65f6&#xff0c;\u9488\u5bf9\u672c\u6587\u6784\u5efa\u7684\u542b\u6709\u4e24\u5c42\u5377\u79ef\u5c42\u548c\u964d\u91c7\u6837\u5c42&#xff0c;\u7531\u4e8esgmoid\u51fd\u6570\u81ea\u8eab\u7684\u7279\u6027&#xff0c;\u5728\u53cd\u5411\u4f20\u64ad\u65f6&#xff0c;\u5f88\u5bb9\u6613\u51fa\u73b0\u68af\u5ea6\u6d88\u5931\u7684\u60c5\u51b5&#xff0c;\u4ece\u800c\u96be\u4ee5\u5b8c\u6210\u7f51\u7edc\u7684\u8bad\u7ec3\u3002\u56e0\u6b64&#xff0c;\u672c\u6587\u8bbe\u8ba1\u7684\u7f51\u7edc\u4f7f\u7528ReLU\u51fd\u6570\u4f5c\u4e3a\u6fc0\u6d3b\u51fd\u6570\u3002<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260803143309-6a70a6a55e1e9.png\" alt=\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\" \/><\/p>\n<h3>3.3 \u5377\u79ef\u5c42\u8bbe\u8ba1<\/h3>\n<p>\u5b66\u957f\u8bbe\u8ba1\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u91c7\u53d6\u7684\u662f\u79bb\u6563\u5377\u79ef&#xff0c;\u5377\u79ef\u6b65\u957f\u4e3a1&#xff0c;\u5373\u6c34\u5e73\u548c\u5782\u76f4\u65b9\u5411\u6bcf\u6b21\u8fd0\u7b97\u5b8c&#xff0c;\u79fb\u52a8\u4e00\u4e2a\u50cf\u7d20\u3002\u5377\u79ef\u6838\u5927\u5c0f\u4e3a5\u00d75\u3002<\/p>\n<h3>3.4 \u964d\u91c7\u6837\u5c42<\/h3>\n<p>\u5b66\u957f\u8bbe\u8ba1\u7684\u964d\u91c7\u6837\u5c42\u7684pooling\u65b9\u5f0f\u662fmax-pooling&#xff0c;\u5927\u5c0f\u4e3a2\u00d72\u3002<\/p>\n<h3>3.5 \u8f93\u51fa\u5c42\u8bbe\u8ba1<\/h3>\n<p>\u8f93\u51fa\u5c42\u8bbe\u7f6e\u4e3a10\u4e2a\u795e\u7ecf\u7f51\u7edc\u8282\u70b9\u3002\u6570\u5b570~9\u7684\u76ee\u6807\u5411\u91cf\u5982\u4e0b\u8868\u6240\u793a&#xff1a;<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260803143309-6a70a6a567ad8.png\" alt=\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\" \/><\/p>\n<h2>4 \u7f51\u7edc\u6a21\u578b\u7684\u603b\u4f53\u7ed3\u6784<\/h2>\n<p><img decoding=\"async\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260803143309-6a70a6a57b73e.png\" alt=\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\" \/><\/p>\n<h2>5 \u90e8\u5206\u5b9e\u73b0\u4ee3\u7801<\/h2>\n<p>\u4f7f\u7528Python&#xff0c;\u8c03\u7528TensorFlow\u7684api\u5b8c\u6210\u624b\u5199\u6570\u5b57\u8bc6\u522b\u7684\u7b97\u6cd5\u3002<\/p>\n<p>\u6ce8&#xff1a;\u6211\u7684\u7a0b\u5e8f\u8fd0\u884c\u73af\u5883\u662f&#xff1a;Win10,python3.\u3002<\/p>\n<p>\u5f53\u7136&#xff0c;\u4e5f\u53ef\u4ee5\u5728Linux\u4e0b\u8fd0\u884c&#xff0c;\u7531\u4e8eTensorFlow\u5bf9py2\u548cpy3\u517c\u5bb9\u5f97\u6bd4\u8f83\u597d&#xff0c;\u5728Linux\u4e0b\u53ef\u4ee5\u5728python2.7\u4e2d\u8fd0\u884c\u3002<\/p>\n<p><span class=\"token comment\">#!\/usr\/bin\/env python2<\/span><br \/>\n<span class=\"token comment\"># -*- coding: utf-8 -*-<\/span><\/p>\n<p><span class=\"token comment\">#import modules<\/span><br \/>\n<span class=\"token keyword\">import<\/span> numpy <span class=\"token keyword\">as<\/span> np<br \/>\n<span class=\"token keyword\">import<\/span> matplotlib<span class=\"token punctuation\">.<\/span>pyplot <span class=\"token keyword\">as<\/span> plt<br \/>\n<span class=\"token comment\">#from sklearn.metrics import confusion_matrix<\/span><br \/>\n<span class=\"token keyword\">import<\/span> tensorflow <span class=\"token keyword\">as<\/span> tf<br \/>\n<span class=\"token keyword\">import<\/span> time<br \/>\n<span class=\"token keyword\">from<\/span> datetime <span class=\"token keyword\">import<\/span> timedelta<br \/>\n<span class=\"token keyword\">import<\/span> math<br \/>\n<span class=\"token keyword\">from<\/span> tensorflow<span class=\"token punctuation\">.<\/span>examples<span class=\"token punctuation\">.<\/span>tutorials<span class=\"token punctuation\">.<\/span>mnist <span class=\"token keyword\">import<\/span> input_data<\/p>\n<p><span class=\"token keyword\">def<\/span> <span class=\"token function\">new_weights<\/span><span class=\"token punctuation\">(<\/span>shape<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n  <span class=\"token keyword\">return<\/span> tf<span class=\"token punctuation\">.<\/span>Variable<span class=\"token punctuation\">(<\/span>tf<span class=\"token punctuation\">.<\/span>truncated_normal<span class=\"token punctuation\">(<\/span>shape<span class=\"token punctuation\">,<\/span>stddev<span class=\"token operator\">&#061;<\/span><span class=\"token number\">0.05<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">new_biases<\/span><span class=\"token punctuation\">(<\/span>length<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n  <span class=\"token keyword\">return<\/span> tf<span class=\"token punctuation\">.<\/span>Variable<span class=\"token punctuation\">(<\/span>tf<span class=\"token punctuation\">.<\/span>constant<span class=\"token punctuation\">(<\/span><span class=\"token number\">0.1<\/span><span class=\"token punctuation\">,<\/span>shape<span class=\"token operator\">&#061;<\/span>length<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">conv2d<\/span><span class=\"token punctuation\">(<\/span>x<span class=\"token punctuation\">,<\/span>W<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n  <span class=\"token keyword\">return<\/span> tf<span class=\"token punctuation\">.<\/span>nn<span class=\"token punctuation\">.<\/span>conv2d<span class=\"token punctuation\">(<\/span>x<span class=\"token punctuation\">,<\/span>W<span class=\"token punctuation\">,<\/span>strides<span class=\"token operator\">&#061;<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span>padding<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;SAME&#039;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">max_pool_2x2<\/span><span class=\"token punctuation\">(<\/span>inputx<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n  <span class=\"token keyword\">return<\/span> tf<span class=\"token punctuation\">.<\/span>nn<span class=\"token punctuation\">.<\/span>max_pool<span class=\"token punctuation\">(<\/span>inputx<span class=\"token punctuation\">,<\/span>ksize<span class=\"token operator\">&#061;<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span>strides<span class=\"token operator\">&#061;<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">2<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span>padding<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;SAME&#039;<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p><span class=\"token comment\">#import data<\/span><br \/>\ndata <span class=\"token operator\">&#061;<\/span> input_data<span class=\"token punctuation\">.<\/span>read_data_sets<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;.\/data&#034;<\/span><span class=\"token punctuation\">,<\/span> one_hot<span class=\"token operator\">&#061;<\/span><span class=\"token boolean\">True<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token comment\"># one_hot means [0 0 1 0 0 0 0 0 0 0] stands for 2<\/span><\/p>\n<p><span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;Size of:&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;&#8211;Training-set:\\\\t\\\\t{}&#034;<\/span><span class=\"token punctuation\">.<\/span><span class=\"token builtin\">format<\/span><span class=\"token punctuation\">(<\/span><span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">.<\/span>train<span class=\"token punctuation\">.<\/span>labels<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;&#8211;Testing-set:\\\\t\\\\t{}&#034;<\/span><span class=\"token punctuation\">.<\/span><span class=\"token builtin\">format<\/span><span class=\"token punctuation\">(<\/span><span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">.<\/span>test<span class=\"token punctuation\">.<\/span>labels<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;&#8211;Validation-set:\\\\t\\\\t{}&#034;<\/span><span class=\"token punctuation\">.<\/span><span class=\"token builtin\">format<\/span><span class=\"token punctuation\">(<\/span><span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">.<\/span>validation<span class=\"token punctuation\">.<\/span>labels<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\ndata<span class=\"token punctuation\">.<\/span>test<span class=\"token punctuation\">.<\/span>cls <span class=\"token operator\">&#061;<\/span> np<span class=\"token punctuation\">.<\/span>argmax<span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">.<\/span>test<span class=\"token punctuation\">.<\/span>labels<span class=\"token punctuation\">,<\/span>axis<span class=\"token operator\">&#061;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">)<\/span>  <span class=\"token comment\"># show the real test labels: [7 2 1 &#8230;, 4 5 6], 10000values<\/span><\/p>\n<p>x <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>placeholder<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;float&#034;<\/span><span class=\"token punctuation\">,<\/span>shape<span class=\"token operator\">&#061;<\/span><span class=\"token punctuation\">[<\/span><span class=\"token boolean\">None<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">784<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span>name<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;x&#039;<\/span><span class=\"token punctuation\">)<\/span><br \/>\nx_image <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>reshape<span class=\"token punctuation\">(<\/span>x<span class=\"token punctuation\">,<\/span><span class=\"token punctuation\">[<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">28<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">28<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>y_true <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>placeholder<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;float&#034;<\/span><span class=\"token punctuation\">,<\/span>shape<span class=\"token operator\">&#061;<\/span><span class=\"token punctuation\">[<\/span><span class=\"token boolean\">None<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">10<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">,<\/span>name<span class=\"token operator\">&#061;<\/span><span class=\"token string\">&#039;y_true&#039;<\/span><span class=\"token punctuation\">)<\/span><br \/>\ny_true_cls <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>argmax<span class=\"token punctuation\">(<\/span>y_true<span class=\"token punctuation\">,<\/span>dimension<span class=\"token operator\">&#061;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token comment\"># Conv 1<\/span><br \/>\nlayer_conv1 <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token string\">&#034;weights&#034;<\/span><span class=\"token punctuation\">:<\/span>new_weights<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">32<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string\">&#034;biases&#034;<\/span><span class=\"token punctuation\">:<\/span>new_biases<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">32<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><br \/>\nh_conv1 <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>nn<span class=\"token punctuation\">.<\/span>relu<span class=\"token punctuation\">(<\/span>conv2d<span class=\"token punctuation\">(<\/span>x_image<span class=\"token punctuation\">,<\/span>layer_conv1<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;weights&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><span class=\"token operator\">&#043;<\/span>layer_conv1<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;biases&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\nh_pool1 <span class=\"token operator\">&#061;<\/span> max_pool_2x2<span class=\"token punctuation\">(<\/span>h_conv1<span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token comment\"># Conv 2<\/span><br \/>\nlayer_conv2 <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token string\">&#034;weights&#034;<\/span><span class=\"token punctuation\">:<\/span>new_weights<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">5<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">32<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">64<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n        <span class=\"token string\">&#034;biases&#034;<\/span><span class=\"token punctuation\">:<\/span>new_biases<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">64<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><br \/>\nh_conv2 <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>nn<span class=\"token punctuation\">.<\/span>relu<span class=\"token punctuation\">(<\/span>conv2d<span class=\"token punctuation\">(<\/span>h_pool1<span class=\"token punctuation\">,<\/span>layer_conv2<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;weights&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><span class=\"token operator\">&#043;<\/span>layer_conv2<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;biases&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\nh_pool2 <span class=\"token operator\">&#061;<\/span> max_pool_2x2<span class=\"token punctuation\">(<\/span>h_conv2<span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token comment\"># Full-connected layer 1<\/span><br \/>\nfc1_layer <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token string\">&#034;weights&#034;<\/span><span class=\"token punctuation\">:<\/span>new_weights<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">7<\/span><span class=\"token operator\">*<\/span><span class=\"token number\">7<\/span><span class=\"token operator\">*<\/span><span class=\"token number\">64<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">1024<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n      <span class=\"token string\">&#034;biases&#034;<\/span><span class=\"token punctuation\">:<\/span>new_biases<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">1024<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><br \/>\nh_pool2_flat <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>reshape<span class=\"token punctuation\">(<\/span>h_pool2<span class=\"token punctuation\">,<\/span><span class=\"token punctuation\">[<\/span><span class=\"token operator\">&#8211;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">7<\/span><span class=\"token operator\">*<\/span><span class=\"token number\">7<\/span><span class=\"token operator\">*<\/span><span class=\"token number\">64<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\nh_fc1 <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>nn<span class=\"token punctuation\">.<\/span>relu<span class=\"token punctuation\">(<\/span>tf<span class=\"token punctuation\">.<\/span>matmul<span class=\"token punctuation\">(<\/span>h_pool2_flat<span class=\"token punctuation\">,<\/span>fc1_layer<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;weights&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><span class=\"token operator\">&#043;<\/span>fc1_layer<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;biases&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token comment\"># Droupout Layer<\/span><br \/>\nkeep_prob <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>placeholder<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;float&#034;<\/span><span class=\"token punctuation\">)<\/span><br \/>\nh_fc1_drop <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>nn<span class=\"token punctuation\">.<\/span>dropout<span class=\"token punctuation\">(<\/span>h_fc1<span class=\"token punctuation\">,<\/span>keep_prob<span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token comment\"># Full-connected layer 2<\/span><br \/>\nfc2_layer <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span><span class=\"token string\">&#034;weights&#034;<\/span><span class=\"token punctuation\">:<\/span>new_weights<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">1024<\/span><span class=\"token punctuation\">,<\/span><span class=\"token number\">10<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">,<\/span><br \/>\n       <span class=\"token string\">&#034;biases&#034;<\/span><span class=\"token punctuation\">:<\/span>new_weights<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">[<\/span><span class=\"token number\">10<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">}<\/span><br \/>\n<span class=\"token comment\"># Predicted class<\/span><br \/>\ny_pred <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>nn<span class=\"token punctuation\">.<\/span>softmax<span class=\"token punctuation\">(<\/span>tf<span class=\"token punctuation\">.<\/span>matmul<span class=\"token punctuation\">(<\/span>h_fc1_drop<span class=\"token punctuation\">,<\/span>fc2_layer<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;weights&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span><span class=\"token operator\">&#043;<\/span>fc2_layer<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;biases&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token comment\"># The output is like [0 0 1 0 0 0 0 0 0 0]<\/span><br \/>\ny_pred_cls <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>argmax<span class=\"token punctuation\">(<\/span>y_pred<span class=\"token punctuation\">,<\/span>dimension<span class=\"token operator\">&#061;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token comment\"># Show the real predict number like &#039;2&#039;<\/span><br \/>\n<span class=\"token comment\"># cost function to be optimized<\/span><br \/>\ncross_entropy <span class=\"token operator\">&#061;<\/span> <span class=\"token operator\">&#8211;<\/span>tf<span class=\"token punctuation\">.<\/span>reduce_mean<span class=\"token punctuation\">(<\/span>y_true<span class=\"token operator\">*<\/span>tf<span class=\"token punctuation\">.<\/span>log<span class=\"token punctuation\">(<\/span>y_pred<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\noptimizer <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>train<span class=\"token punctuation\">.<\/span>AdamOptimizer<span class=\"token punctuation\">(<\/span>learning_rate<span class=\"token operator\">&#061;<\/span><span class=\"token number\">1e-4<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>minimize<span class=\"token punctuation\">(<\/span>cross_entropy<span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token comment\"># Performance Measures<\/span><br \/>\ncorrect_prediction <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>equal<span class=\"token punctuation\">(<\/span>y_pred_cls<span class=\"token punctuation\">,<\/span>y_true_cls<span class=\"token punctuation\">)<\/span><br \/>\naccuracy <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>reduce_mean<span class=\"token punctuation\">(<\/span>tf<span class=\"token punctuation\">.<\/span>cast<span class=\"token punctuation\">(<\/span>correct_prediction<span class=\"token punctuation\">,<\/span><span class=\"token string\">&#034;float&#034;<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n<span class=\"token keyword\">with<\/span> tf<span class=\"token punctuation\">.<\/span>Session<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span> <span class=\"token keyword\">as<\/span> sess<span class=\"token punctuation\">:<\/span><br \/>\n  init <span class=\"token operator\">&#061;<\/span> tf<span class=\"token punctuation\">.<\/span>global_variables_initializer<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n  sess<span class=\"token punctuation\">.<\/span>run<span class=\"token punctuation\">(<\/span>init<span class=\"token punctuation\">)<\/span><br \/>\n  train_batch_size <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">50<\/span><br \/>\n  <span class=\"token keyword\">def<\/span> <span class=\"token function\">optimize<\/span><span class=\"token punctuation\">(<\/span>num_iterations<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    total_iterations<span class=\"token operator\">&#061;<\/span><span class=\"token number\">0<\/span><br \/>\n    start_time <span class=\"token operator\">&#061;<\/span> time<span class=\"token punctuation\">.<\/span>time<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token keyword\">for<\/span> i <span class=\"token keyword\">in<\/span> <span class=\"token builtin\">range<\/span><span class=\"token punctuation\">(<\/span>total_iterations<span class=\"token punctuation\">,<\/span>total_iterations<span class=\"token operator\">&#043;<\/span>num_iterations<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n      x_batch<span class=\"token punctuation\">,<\/span>y_true_batch <span class=\"token operator\">&#061;<\/span> data<span class=\"token punctuation\">.<\/span>train<span class=\"token punctuation\">.<\/span>next_batch<span class=\"token punctuation\">(<\/span>train_batch_size<span class=\"token punctuation\">)<\/span><br \/>\n      feed_dict_train_op <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span>x<span class=\"token punctuation\">:<\/span>x_batch<span class=\"token punctuation\">,<\/span>y_true<span class=\"token punctuation\">:<\/span>y_true_batch<span class=\"token punctuation\">,<\/span>keep_prob<span class=\"token punctuation\">:<\/span><span class=\"token number\">0.5<\/span><span class=\"token punctuation\">}<\/span><br \/>\n      feed_dict_train <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">{<\/span>x<span class=\"token punctuation\">:<\/span>x_batch<span class=\"token punctuation\">,<\/span>y_true<span class=\"token punctuation\">:<\/span>y_true_batch<span class=\"token punctuation\">,<\/span>keep_prob<span class=\"token punctuation\">:<\/span><span class=\"token number\">1.0<\/span><span class=\"token punctuation\">}<\/span><br \/>\n      sess<span class=\"token punctuation\">.<\/span>run<span class=\"token punctuation\">(<\/span>optimizer<span class=\"token punctuation\">,<\/span>feed_dict<span class=\"token operator\">&#061;<\/span>feed_dict_train_op<span class=\"token punctuation\">)<\/span><br \/>\n      <span class=\"token comment\"># Print status every 100 iterations.<\/span><br \/>\n      <span class=\"token keyword\">if<\/span> i<span class=\"token operator\">%<\/span><span class=\"token number\">100<\/span><span class=\"token operator\">&#061;&#061;<\/span><span class=\"token number\">0<\/span><span class=\"token punctuation\">:<\/span><br \/>\n        <span class=\"token comment\"># Calculate the accuracy on the training-set.<\/span><br \/>\n        acc <span class=\"token operator\">&#061;<\/span> sess<span class=\"token punctuation\">.<\/span>run<span class=\"token punctuation\">(<\/span>accuracy<span class=\"token punctuation\">,<\/span>feed_dict<span class=\"token operator\">&#061;<\/span>feed_dict_train<span class=\"token punctuation\">)<\/span><br \/>\n        <span class=\"token comment\"># Message for printing.<\/span><br \/>\n        msg <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;Optimization Iteration:{0:&gt;6}, Training Accuracy: {1:&gt;6.1%}&#034;<\/span><br \/>\n        <span class=\"token comment\"># Print it.<\/span><br \/>\n        <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>msg<span class=\"token punctuation\">.<\/span><span class=\"token builtin\">format<\/span><span class=\"token punctuation\">(<\/span>i<span class=\"token operator\">&#043;<\/span><span class=\"token number\">1<\/span><span class=\"token punctuation\">,<\/span>acc<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token comment\"># Update the total number of iterations performed<\/span><br \/>\n    total_iterations <span class=\"token operator\">&#043;&#061;<\/span> num_iterations<br \/>\n    <span class=\"token comment\"># Ending time<\/span><br \/>\n    end_time <span class=\"token operator\">&#061;<\/span> time<span class=\"token punctuation\">.<\/span>time<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    <span class=\"token comment\"># Difference between start and end_times.<\/span><br \/>\n    time_dif <span class=\"token operator\">&#061;<\/span> end_time<span class=\"token operator\">&#8211;<\/span>start_time<br \/>\n    <span class=\"token comment\"># Print the time-usage<\/span><br \/>\n    <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;Time usage:&#034;<\/span><span class=\"token operator\">&#043;<\/span><span class=\"token builtin\">str<\/span><span class=\"token punctuation\">(<\/span>timedelta<span class=\"token punctuation\">(<\/span>seconds<span class=\"token operator\">&#061;<\/span><span class=\"token builtin\">int<\/span><span class=\"token punctuation\">(<\/span><span class=\"token builtin\">round<\/span><span class=\"token punctuation\">(<\/span>time_dif<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n  test_batch_size <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">256<\/span><br \/>\n  <span class=\"token keyword\">def<\/span> <span class=\"token function\">print_test_accuracy<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span><br \/>\n    <span class=\"token comment\"># Number of images in the test-set.<\/span><br \/>\n    num_test <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">len<\/span><span class=\"token punctuation\">(<\/span>data<span class=\"token punctuation\">.<\/span>test<span class=\"token punctuation\">.<\/span>images<span class=\"token punctuation\">)<\/span><br \/>\n    cls_pred <span class=\"token operator\">&#061;<\/span> np<span class=\"token punctuation\">.<\/span>zeros<span class=\"token punctuation\">(<\/span>shape<span class=\"token operator\">&#061;<\/span>num_test<span class=\"token punctuation\">,<\/span>dtype<span class=\"token operator\">&#061;<\/span>np<span class=\"token punctuation\">.<\/span><span class=\"token builtin\">int<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    i <span class=\"token operator\">&#061;<\/span> <span class=\"token number\">0<\/span><br \/>\n    <span class=\"token keyword\">while<\/span> i <span class=\"token operator\">&lt;<\/span> num_test<span class=\"token punctuation\">:<\/span><br \/>\n      <span class=\"token comment\"># The ending index for the next batch is denoted j.<\/span><br \/>\n      j <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">min<\/span><span class=\"token punctuation\">(<\/span>i<span class=\"token operator\">&#043;<\/span>test_batch_size<span class=\"token punctuation\">,<\/span>num_test<span class=\"token punctuation\">)<\/span><br \/>\n      <span class=\"token comment\"># Get the images from the test-set between index i and j<\/span><br \/>\n      images <span class=\"token operator\">&#061;<\/span> data<span class=\"token punctuation\">.<\/span>test<span class=\"token punctuation\">.<\/span>images<span class=\"token punctuation\">[<\/span>i<span class=\"token punctuation\">:<\/span>j<span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">:<\/span><span class=\"token punctuation\">]<\/span><br \/>\n      <span class=\"token comment\"># Get the associated labels<\/span><br \/>\n      labels <span class=\"token operator\">&#061;<\/span> data<span class=\"token punctuation\">.<\/span>test<span class=\"token punctuation\">.<\/span>labels<span class=\"token punctuation\">[<\/span>i<span class=\"token punctuation\">:<\/span>j<span class=\"token punctuation\">,<\/span> <span class=\"token punctuation\">:<\/span><span class=\"token punctuation\">]<\/span><br \/>\n      <span class=\"token comment\"># Create a feed-dict with these images and labels.<\/span><br \/>\n      feed_dict<span class=\"token operator\">&#061;<\/span><span class=\"token punctuation\">{<\/span>x<span class=\"token punctuation\">:<\/span>images<span class=\"token punctuation\">,<\/span>y_true<span class=\"token punctuation\">:<\/span>labels<span class=\"token punctuation\">,<\/span>keep_prob<span class=\"token punctuation\">:<\/span><span class=\"token number\">1.0<\/span><span class=\"token punctuation\">}<\/span><br \/>\n      <span class=\"token comment\"># Calculate the predicted class using Tensorflow.<\/span><br \/>\n      cls_pred<span class=\"token punctuation\">[<\/span>i<span class=\"token punctuation\">:<\/span>j<span class=\"token punctuation\">]<\/span> <span class=\"token operator\">&#061;<\/span> sess<span class=\"token punctuation\">.<\/span>run<span class=\"token punctuation\">(<\/span>y_pred_cls<span class=\"token punctuation\">,<\/span>feed_dict<span class=\"token operator\">&#061;<\/span>feed_dict<span class=\"token punctuation\">)<\/span><br \/>\n      <span class=\"token comment\"># Set the start-index for the next batch to the<\/span><br \/>\n      <span class=\"token comment\"># end-index of the current batch<\/span><br \/>\n      i <span class=\"token operator\">&#061;<\/span> j<br \/>\n    cls_true <span class=\"token operator\">&#061;<\/span> data<span class=\"token punctuation\">.<\/span>test<span class=\"token punctuation\">.<\/span>cls<br \/>\n    correct <span class=\"token operator\">&#061;<\/span> <span class=\"token punctuation\">(<\/span>cls_true<span class=\"token operator\">&#061;&#061;<\/span>cls_pred<span class=\"token punctuation\">)<\/span><br \/>\n    correct_sum <span class=\"token operator\">&#061;<\/span> correct<span class=\"token punctuation\">.<\/span><span class=\"token builtin\">sum<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n    acc <span class=\"token operator\">&#061;<\/span> <span class=\"token builtin\">float<\/span><span class=\"token punctuation\">(<\/span>correct_sum<span class=\"token punctuation\">)<\/span> <span class=\"token operator\">\/<\/span> num_test<br \/>\n    <span class=\"token comment\"># Print the accuracy<\/span><br \/>\n    msg <span class=\"token operator\">&#061;<\/span> <span class=\"token string\">&#034;Accuracy on Test-Set: {0:.1%} ({1}\/{2})&#034;<\/span><br \/>\n    <span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span>msg<span class=\"token punctuation\">.<\/span><span class=\"token builtin\">format<\/span><span class=\"token punctuation\">(<\/span>acc<span class=\"token punctuation\">,<\/span>correct_sum<span class=\"token punctuation\">,<\/span>num_test<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span><br \/>\n  <span class=\"token comment\"># Performance after 10000 optimization iterations<\/span><br \/>\n  optimize<span class=\"token punctuation\">(<\/span>num_iterations<span class=\"token operator\">&#061;<\/span><span class=\"token number\">10000<\/span><span class=\"token punctuation\">)<\/span><br \/>\n  print_test_accuracy<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n  savew_hl1 <span class=\"token operator\">&#061;<\/span> layer_conv1<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;weights&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">.<\/span><span class=\"token builtin\">eval<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n  saveb_hl1 <span class=\"token operator\">&#061;<\/span> layer_conv1<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;biases&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">.<\/span><span class=\"token builtin\">eval<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n  savew_hl2 <span class=\"token operator\">&#061;<\/span> layer_conv2<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;weights&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">.<\/span><span class=\"token builtin\">eval<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n  saveb_hl2 <span class=\"token operator\">&#061;<\/span> layer_conv2<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;biases&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">.<\/span><span class=\"token builtin\">eval<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n  savew_fc1 <span class=\"token operator\">&#061;<\/span> fc1_layer<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;weights&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">.<\/span><span class=\"token builtin\">eval<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n  saveb_fc1 <span class=\"token operator\">&#061;<\/span> fc1_layer<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;biases&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">.<\/span><span class=\"token builtin\">eval<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n  savew_op <span class=\"token operator\">&#061;<\/span> fc2_layer<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;weights&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">.<\/span><span class=\"token builtin\">eval<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><br \/>\n  saveb_op <span class=\"token operator\">&#061;<\/span> fc2_layer<span class=\"token punctuation\">[<\/span><span class=\"token string\">&#034;biases&#034;<\/span><span class=\"token punctuation\">]<\/span><span class=\"token punctuation\">.<\/span><span class=\"token builtin\">eval<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span><\/p>\n<p>  np<span class=\"token punctuation\">.<\/span>save<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;savew_hl1.npy&#034;<\/span><span class=\"token punctuation\">,<\/span> savew_hl1<span class=\"token punctuation\">)<\/span><br \/>\n  np<span class=\"token punctuation\">.<\/span>save<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;saveb_hl1.npy&#034;<\/span><span class=\"token punctuation\">,<\/span> saveb_hl1<span class=\"token punctuation\">)<\/span><br \/>\n  np<span class=\"token punctuation\">.<\/span>save<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;savew_hl2.npy&#034;<\/span><span class=\"token punctuation\">,<\/span> savew_hl2<span class=\"token punctuation\">)<\/span><br \/>\n  np<span class=\"token punctuation\">.<\/span>save<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;saveb_hl2.npy&#034;<\/span><span class=\"token punctuation\">,<\/span> saveb_hl2<span class=\"token punctuation\">)<\/span><br \/>\n  np<span class=\"token punctuation\">.<\/span>save<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;savew_hl3.npy&#034;<\/span><span class=\"token punctuation\">,<\/span> savew_fc1<span class=\"token punctuation\">)<\/span><br \/>\n  np<span class=\"token punctuation\">.<\/span>save<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;saveb_hl3.npy&#034;<\/span><span class=\"token punctuation\">,<\/span> saveb_fc1<span class=\"token punctuation\">)<\/span><br \/>\n  np<span class=\"token punctuation\">.<\/span>save<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;savew_op.npy&#034;<\/span><span class=\"token punctuation\">,<\/span> savew_op<span class=\"token punctuation\">)<\/span><br \/>\n  np<span class=\"token punctuation\">.<\/span>save<span class=\"token punctuation\">(<\/span><span class=\"token string\">&#034;saveb_op.npy&#034;<\/span><span class=\"token punctuation\">,<\/span> saveb_op<span class=\"token punctuation\">)<\/span><\/p>\n<p>\u8fd0\u884c\u7ed3\u679c\u663e\u793a&#xff1a;\u6d4b\u8bd5\u96c6\u4e2d\u51c6\u786e\u7387\u5927\u6982\u4e3a99.2%\u3002<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260803143309-6a70a6a5b6dee.png\" alt=\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\" \/> \u67e5\u770b\u6df7\u6dc6\u77e9\u9635<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260803143309-6a70a6a5ca02b.png\" alt=\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\" \/><\/p>\n<p>\u7bc7\u5e45\u6709\u9650&#xff0c;\u66f4\u591a\u8be6\u7ec6\u8bbe\u8ba1\u89c1\u8bbe\u8ba1\u8bba\u6587<\/p>\n<h2>6 \u6700\u540e<\/h2>\n<p>\u9879\u76ee\u5305\u542b\u5185\u5bb9<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260803143309-6a70a6a5dd310.png\" alt=\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\" \/><\/p>\n<p>\u5b8c\u6574\u8be6\u7ec6\u8bbe\u8ba1\u8bba\u6587 <img decoding=\"async\" src=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260803143309-6a70a6a5ea108.png\" alt=\"\u5728\u8fd9\u91cc\u63d2\u5165\u56fe\u7247\u63cf\u8ff0\" \/><\/p>\n<p>&#x1f9ff;\u9879\u76ee\u5206\u4eab&#xff1a;\u89c1\u4e3b\u9875\u4efb\u610f\u7f6e\u9876\u6587\u7ae0<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u6587\u7ae0\u76ee\u5f55 0 \u524d\u8a001 \u9879\u76ee\u8fd0\u884c\u6548\u679c2 \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u5b57\u7b26\u8bc6\u522b\u539f\u74062.1 \u7ed3\u6784\u89e3\u67902.2 C1\u5c422.3 S2\u5c42S2\u5c42\u548cC3\u5c42\u8fde\u63a5 2.4 F6\u4e0eC5\u5c42 3 \u5199\u6570\u5b57\u8bc6\u522b\u7b97\u6cd5\u6a21\u578b\u7684\u6784\u5efa3.1 \u8f93\u5165\u5c42\u8bbe\u8ba13.2 \u6fc0\u6d3b\u51fd\u6570\u7684\u9009\u53d63.3 \u5377\u79ef\u5c42\u8bbe\u8ba13.4 \u964d\u91c7\u6837\u5c423.5 \u8f93\u51fa\u5c42\u8bbe\u8ba1 4 \u7f51\u7edc\u6a21\u578b\u7684\u603b\u4f53\u7ed3\u67845 \u90e8\u5206\u5b9e\u73b0\u4ee3\u78016 \u6700\u540e 0 \u524d\u8a00<br \/>\n&#x1f525;\u8fd9\u4e24\u5e74\u5f00\u59cb\u6bd5\u4e1a\u8bbe\u8ba1\u548c\u6bd5\u4e1a\u7b54\u8fa9\u7684\u8981\u6c42\u548c\u96be\u5ea6\u4e0d\u65ad\u63d0\u5347&#xff0c;\u4f20\u7edf\u7684\u6bd5\u8bbe\u9898\u76ee\u7f3a\u5c11\u521b\u65b0\u548c\u4eae\u70b9&#xff0c;\u5f80\u5f80\u8fbe\u4e0d\u5230\u6bd5\u4e1a\u7b54\u8fa9\u7684\u8981\u6c42<\/p>\n","protected":false},"author":2,"featured_media":89831,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[81,1908,1520],"topic":[],"class_list":["post-89843","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-server","tag-python","tag-1908","tag-1520"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u6bd5\u8bbe \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u6570\u5b57\u8bc6\u522b\u7cfb\u7edf(\u6e90\u7801+\u8bba\u6587) - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/89843.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u6bd5\u8bbe \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u6570\u5b57\u8bc6\u522b\u7cfb\u7edf(\u6e90\u7801+\u8bba\u6587) - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u6587\u7ae0\u76ee\u5f55 0 \u524d\u8a001 \u9879\u76ee\u8fd0\u884c\u6548\u679c2 \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u5b57\u7b26\u8bc6\u522b\u539f\u74062.1 \u7ed3\u6784\u89e3\u67902.2 C1\u5c422.3 S2\u5c42S2\u5c42\u548cC3\u5c42\u8fde\u63a5 2.4 F6\u4e0eC5\u5c42 3 \u5199\u6570\u5b57\u8bc6\u522b\u7b97\u6cd5\u6a21\u578b\u7684\u6784\u5efa3.1 \u8f93\u5165\u5c42\u8bbe\u8ba13.2 \u6fc0\u6d3b\u51fd\u6570\u7684\u9009\u53d63.3 \u5377\u79ef\u5c42\u8bbe\u8ba13.4 \u964d\u91c7\u6837\u5c423.5 \u8f93\u51fa\u5c42\u8bbe\u8ba1 4 \u7f51\u7edc\u6a21\u578b\u7684\u603b\u4f53\u7ed3\u67845 \u90e8\u5206\u5b9e\u73b0\u4ee3\u78016 \u6700\u540e 0 \u524d\u8a00 &#x1f525;\u8fd9\u4e24\u5e74\u5f00\u59cb\u6bd5\u4e1a\u8bbe\u8ba1\u548c\u6bd5\u4e1a\u7b54\u8fa9\u7684\u8981\u6c42\u548c\u96be\u5ea6\u4e0d\u65ad\u63d0\u5347&#xff0c;\u4f20\u7edf\u7684\u6bd5\u8bbe\u9898\u76ee\u7f3a\u5c11\u521b\u65b0\u548c\u4eae\u70b9&#xff0c;\u5f80\u5f80\u8fbe\u4e0d\u5230\u6bd5\u4e1a\u7b54\u8fa9\u7684\u8981\u6c42\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/89843.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2026-08-03T14:33:12+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260803143306-6a70a6a285e81.png\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/89843.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/89843.html\",\"name\":\"\u6bd5\u8bbe \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u6570\u5b57\u8bc6\u522b\u7cfb\u7edf(\u6e90\u7801+\u8bba\u6587) - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2026-08-03T14:33:12+00:00\",\"dateModified\":\"2026-08-03T14:33:12+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/89843.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/89843.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/89843.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u6bd5\u8bbe \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u6570\u5b57\u8bc6\u522b\u7cfb\u7edf(\u6e90\u7801+\u8bba\u6587)\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u6bd5\u8bbe \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u6570\u5b57\u8bc6\u522b\u7cfb\u7edf(\u6e90\u7801+\u8bba\u6587) - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/89843.html","og_locale":"zh_CN","og_type":"article","og_title":"\u6bd5\u8bbe \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u6570\u5b57\u8bc6\u522b\u7cfb\u7edf(\u6e90\u7801+\u8bba\u6587) - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u6587\u7ae0\u76ee\u5f55 0 \u524d\u8a001 \u9879\u76ee\u8fd0\u884c\u6548\u679c2 \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u5b57\u7b26\u8bc6\u522b\u539f\u74062.1 \u7ed3\u6784\u89e3\u67902.2 C1\u5c422.3 S2\u5c42S2\u5c42\u548cC3\u5c42\u8fde\u63a5 2.4 F6\u4e0eC5\u5c42 3 \u5199\u6570\u5b57\u8bc6\u522b\u7b97\u6cd5\u6a21\u578b\u7684\u6784\u5efa3.1 \u8f93\u5165\u5c42\u8bbe\u8ba13.2 \u6fc0\u6d3b\u51fd\u6570\u7684\u9009\u53d63.3 \u5377\u79ef\u5c42\u8bbe\u8ba13.4 \u964d\u91c7\u6837\u5c423.5 \u8f93\u51fa\u5c42\u8bbe\u8ba1 4 \u7f51\u7edc\u6a21\u578b\u7684\u603b\u4f53\u7ed3\u67845 \u90e8\u5206\u5b9e\u73b0\u4ee3\u78016 \u6700\u540e 0 \u524d\u8a00 &#x1f525;\u8fd9\u4e24\u5e74\u5f00\u59cb\u6bd5\u4e1a\u8bbe\u8ba1\u548c\u6bd5\u4e1a\u7b54\u8fa9\u7684\u8981\u6c42\u548c\u96be\u5ea6\u4e0d\u65ad\u63d0\u5347&#xff0c;\u4f20\u7edf\u7684\u6bd5\u8bbe\u9898\u76ee\u7f3a\u5c11\u521b\u65b0\u548c\u4eae\u70b9&#xff0c;\u5f80\u5f80\u8fbe\u4e0d\u5230\u6bd5\u4e1a\u7b54\u8fa9\u7684\u8981\u6c42","og_url":"https:\/\/www.wsisp.com\/helps\/89843.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2026-08-03T14:33:12+00:00","og_image":[{"url":"https:\/\/www.wsisp.com\/helps\/wp-content\/uploads\/2026\/08\/20260803143306-6a70a6a285e81.png"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"6 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/89843.html","url":"https:\/\/www.wsisp.com\/helps\/89843.html","name":"\u6bd5\u8bbe \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u6570\u5b57\u8bc6\u522b\u7cfb\u7edf(\u6e90\u7801+\u8bba\u6587) - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2026-08-03T14:33:12+00:00","dateModified":"2026-08-03T14:33:12+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/89843.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/89843.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/89843.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"\u6bd5\u8bbe \u6df1\u5ea6\u5b66\u4e60\u624b\u5199\u6570\u5b57\u8bc6\u522b\u7cfb\u7edf(\u6e90\u7801+\u8bba\u6587)"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/89843","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=89843"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/89843\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media\/89831"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=89843"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=89843"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=89843"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=89843"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}