{"id":477239,"date":"2023-08-09T09:09:43","date_gmt":"2023-08-09T09:09:43","guid":{"rendered":""},"modified":"2023-10-30T17:12:07","modified_gmt":"2023-10-30T17:12:07","slug":"fine-tuning","status":"publish","type":"wiki","link":"https:\/\/oneproxy.pro\/cn\/wiki\/fine-tuning\/","title":{"rendered":"\u5fae\u8c03"},"content":{"rendered":"<p>\u5728\u673a\u5668\u5b66\u4e60\u548c\u4eba\u5de5\u667a\u80fd\u9886\u57df\uff0c\u5fae\u8c03\u662f\u6a21\u578b\u4f18\u5316\u8fc7\u7a0b\u4e2d\u4e0d\u53ef\u6216\u7f3a\u7684\u4e00\u90e8\u5206\u3002\u672c\u8d28\u4e0a\uff0c\u5b83\u6d89\u53ca\u4e00\u79cd\u8fc1\u79fb\u5b66\u4e60\u6280\u672f\uff0c\u5176\u4e2d\u9884\u5148\u8bad\u7ec3\u7684\u6a21\u578b\u7ecf\u8fc7\u8c03\u6574\u4ee5\u9002\u5e94\u4e0d\u540c\u4f46\u76f8\u5173\u7684\u4efb\u52a1\u3002<\/p>\n<h2>\u5fae\u8c03\u7684\u8d77\u6e90\u548c\u6f14\u53d8<\/h2>\n<p>\u673a\u5668\u5b66\u4e60\u548c\u6df1\u5ea6\u5b66\u4e60\u80cc\u666f\u4e0b\u7684\u5fae\u8c03\u6e90\u81ea\u8fc1\u79fb\u5b66\u4e60\u7684\u6982\u5ff5\u3002\u8fd9\u4e2a\u60f3\u6cd5\u662f\u5229\u7528\u5df2\u7ecf\u8bad\u7ec3\u7684\u6a21\u578b\uff08\u79f0\u4e3a\u57fa\u7840\u6a21\u578b\uff09\u7684\u529b\u91cf\uff0c\u4e3a\u4e0d\u540c\u4f46\u76f8\u5173\u7684\u4efb\u52a1\u8bad\u7ec3\u65b0\u6a21\u578b\u3002\u8fc1\u79fb\u5b66\u4e60\u9996\u6b21\u88ab\u63d0\u53ca\u662f\u5728 20 \u4e16\u7eaa 90 \u5e74\u4ee3\u672b\uff0c\u4f46\u968f\u7740 2010 \u5e74\u4ee3\u6df1\u5ea6\u5b66\u4e60\u548c\u5927\u6570\u636e\u7684\u51fa\u73b0\uff0c\u5b83\u53d8\u5f97\u8d8a\u6765\u8d8a\u6d41\u884c\u3002<\/p>\n<h2>\u6df1\u5165\u5fae\u8c03<\/h2>\n<p>\u5fae\u8c03\u662f\u4e00\u4e2a\u5728\u65b0\u4efb\u52a1\u4e0a\u5229\u7528\u9884\u5148\u8bad\u7ec3\u7684\u6a21\u578b\u800c\u65e0\u9700\u4ece\u5934\u5f00\u59cb\u7684\u8fc7\u7a0b\u3002\u57fa\u672c\u601d\u60f3\u662f\u5c06\u521d\u59cb\u4efb\u52a1\u4e2d\u9884\u8bad\u7ec3\u6a21\u578b\u5b66\u5230\u7684\u201c\u7279\u5f81\u201d\u91cd\u65b0\u7528\u4e8e\u65b0\u4efb\u52a1\uff0c\u800c\u65b0\u4efb\u52a1\u53ef\u80fd\u6ca1\u6709\u90a3\u4e48\u591a\u53ef\u7528\u7684\u6807\u8bb0\u6570\u636e\u3002<\/p>\n<p>\u6b64\u8fc7\u7a0b\u5177\u6709\u4e00\u4e9b\u4f18\u70b9\u3002\u9996\u5148\uff0c\u4e0e\u4ece\u5934\u5f00\u59cb\u8bad\u7ec3\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u76f8\u6bd4\uff0c\u5b83\u8282\u7701\u4e86\u5927\u91cf\u7684\u65f6\u95f4\u548c\u8ba1\u7b97\u8d44\u6e90\u3002\u5176\u6b21\uff0c\u5b83\u4f7f\u6211\u4eec\u80fd\u591f\u5229\u7528\u57fa\u7840\u6a21\u578b\u4ece\u5927\u89c4\u6a21\u4efb\u52a1\u4e2d\u5b66\u5230\u7684\u6a21\u5f0f\u6765\u5904\u7406\u6807\u8bb0\u6570\u636e\u8f83\u5c11\u7684\u4efb\u52a1\u3002<\/p>\n<h2>\u5fae\u8c03\u7684\u5185\u90e8\u5de5\u4f5c\u539f\u7406<\/h2>\n<p>\u5fae\u8c03\u901a\u5e38\u5206\u4e24\u4e2a\u9636\u6bb5\u8fdb\u884c\u3002<\/p>\n<ol>\n<li>\u7279\u5f81\u63d0\u53d6\uff1a\u8fd9\u91cc\uff0c\u9884\u8bad\u7ec3\u7684\u6a21\u578b\u88ab\u51bb\u7ed3\u5e76\u7528\u4f5c\u56fa\u5b9a\u7684\u7279\u5f81\u63d0\u53d6\u5668\u3002\u8be5\u6a21\u578b\u7684\u8f93\u51fa\u88ab\u8f93\u5165\u5230\u4e00\u4e2a\u65b0\u6a21\u578b\uff08\u901a\u5e38\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u5206\u7c7b\u5668\uff09\u4e2d\uff0c\u7136\u540e\u9488\u5bf9\u65b0\u4efb\u52a1\u8fdb\u884c\u8bad\u7ec3\u3002<\/li>\n<li>\u5fae\u8c03\uff1a\u7279\u5f81\u63d0\u53d6\u540e\uff0c\u6a21\u578b\u7684\u7279\u5b9a\u5c42\uff08\u6709\u65f6\u662f\u6574\u4e2a\u6a21\u578b\uff09\u88ab\u201c\u89e3\u51bb\u201d\uff0c\u5e76\u9488\u5bf9\u65b0\u4efb\u52a1\u518d\u6b21\u8bad\u7ec3\u6a21\u578b\u3002\u5728\u6b64\u9636\u6bb5\uff0c\u5b66\u4e60\u7387\u8bbe\u7f6e\u5f97\u975e\u5e38\u4f4e\uff0c\u4ee5\u907f\u514d\u201c\u5fd8\u8bb0\u201d\u5728\u9884\u8bad\u7ec3\u9636\u6bb5\u5b66\u5230\u7684\u6709\u7528\u7279\u5f81\u3002<\/li>\n<\/ol>\n<h2>\u5fae\u8c03\u7684\u4e3b\u8981\u7279\u70b9<\/h2>\n<ul>\n<li><strong>\u77e5\u8bc6\u8f6c\u79fb<\/strong>\uff1a\u5fae\u8c03\u6709\u6548\u5730\u5c06\u77e5\u8bc6\u4ece\u4e00\u9879\u4efb\u52a1\u8f6c\u79fb\u5230\u53e6\u4e00\u9879\u4efb\u52a1\uff0c\u51cf\u5c11\u4e86\u65b0\u4efb\u52a1\u5bf9\u5927\u91cf\u6807\u8bb0\u6570\u636e\u7684\u9700\u6c42\u3002<\/li>\n<li><strong>\u8ba1\u7b97\u6548\u7387<\/strong>\uff1a\u4e0e\u4ece\u5934\u5f00\u59cb\u8bad\u7ec3\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u76f8\u6bd4\uff0c\u5b83\u7684\u8ba1\u7b97\u5f3a\u5ea6\u8f83\u5c0f\u3002<\/li>\n<li><strong>\u7075\u6d3b\u6027<\/strong>\uff1a\u8be5\u6280\u672f\u5f88\u7075\u6d3b\uff0c\u56e0\u4e3a\u5b83\u53ef\u4ee5\u6839\u636e\u57fa\u7840\u4efb\u52a1\u548c\u65b0\u4efb\u52a1\u4e4b\u95f4\u7684\u76f8\u4f3c\u6027\u5e94\u7528\u4e8e\u9884\u8bad\u7ec3\u6a21\u578b\u7684\u4e0d\u540c\u5c42\u3002<\/li>\n<li><strong>\u63d0\u9ad8\u6027\u80fd<\/strong>\uff1a\u5b83\u901a\u5e38\u4f1a\u63d0\u9ad8\u6a21\u578b\u6027\u80fd\uff0c\u7279\u522b\u662f\u5f53\u65b0\u4efb\u52a1\u7684\u6570\u636e\u7a00\u7f3a\u6216\u4e0d\u591f\u591a\u6837\u5316\u65f6\u3002<\/li>\n<\/ul>\n<h2>\u5fae\u8c03\u7684\u7c7b\u578b<\/h2>\n<p>\u5fae\u8c03\u4e3b\u8981\u6709\u4e24\u79cd\u7c7b\u578b\uff1a<\/p>\n<ol>\n<li><strong>\u57fa\u4e8e\u7279\u5f81\u7684\u5fae\u8c03<\/strong>\uff1a\u8fd9\u91cc\uff0c\u9884\u8bad\u7ec3\u7684\u6a21\u578b\u7528\u4f5c\u56fa\u5b9a\u7279\u5f81\u63d0\u53d6\u5668\uff0c\u800c\u65b0\u6a21\u578b\u5219\u4f7f\u7528\u8fd9\u4e9b\u63d0\u53d6\u7684\u7279\u5f81\u8fdb\u884c\u8bad\u7ec3\u3002<\/li>\n<li><strong>\u5168\u9762\u5fae\u8c03<\/strong>\uff1a\u5728\u8fd9\u79cd\u65b9\u6cd5\u4e2d\uff0c\u9884\u8bad\u7ec3\u6a21\u578b\u7684\u6240\u6709\u6216\u7279\u5b9a\u5c42\u90fd\u88ab\u89e3\u51bb\u5e76\u9488\u5bf9\u65b0\u4efb\u52a1\u8fdb\u884c\u8bad\u7ec3\uff0c\u5e76\u4ee5\u8f83\u4f4e\u7684\u5b66\u4e60\u7387\u4fdd\u7559\u9884\u5b66\u4e60\u7684\u7279\u5f81\u3002<\/li>\n<\/ol>\n<table>\n<thead>\n<tr>\n<th>\u5fae\u8c03\u578b<\/th>\n<th>\u63cf\u8ff0<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>\u57fa\u4e8e\u7279\u5f81<\/td>\n<td>\u7528\u4f5c\u56fa\u5b9a\u7279\u5f81\u63d0\u53d6\u5668\u7684\u9884\u8bad\u7ec3\u6a21\u578b<\/td>\n<\/tr>\n<tr>\n<td>\u6ee1\u7684<\/td>\n<td>\u9488\u5bf9\u65b0\u4efb\u52a1\u91cd\u65b0\u8bad\u7ec3\u7279\u5b9a\u5c42\u6216\u6574\u4e2a\u9884\u8bad\u7ec3\u6a21\u578b<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>\u5fae\u8c03\uff1a\u5e94\u7528\u3001\u6311\u6218\u548c\u89e3\u51b3\u65b9\u6848<\/h2>\n<p>\u5fae\u8c03\u5728\u8ba1\u7b97\u673a\u89c6\u89c9\uff08\u76ee\u6807\u68c0\u6d4b\u3001\u56fe\u50cf\u5206\u7c7b\uff09\u3001\u81ea\u7136\u8bed\u8a00\u5904\u7406\uff08\u60c5\u611f\u5206\u6790\u3001\u6587\u672c\u5206\u7c7b\uff09\u548c\u97f3\u9891\u5904\u7406\uff08\u8bed\u97f3\u8bc6\u522b\uff09\u7b49\u5404\u79cd\u673a\u5668\u5b66\u4e60\u9886\u57df\u6709\u7740\u5e7f\u6cdb\u7684\u5e94\u7528\u3002<\/p>\n<p>\u7136\u800c\uff0c\u5b83\u786e\u5b9e\u5e26\u6765\u4e86\u4e00\u4e9b\u6311\u6218\uff1a<\/p>\n<ol>\n<li><strong>\u707e\u96be\u6027\u9057\u5fd8<\/strong>\uff1a\u8fd9\u662f\u6307\u6a21\u578b\u5728\u5bf9\u65b0\u4efb\u52a1\u8fdb\u884c\u5fae\u8c03\u65f6\u5fd8\u8bb0\u4e86\u4ece\u57fa\u672c\u4efb\u52a1\u4e2d\u5b66\u5230\u7684\u7279\u5f81\u3002\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\u7684\u65b9\u6cd5\u662f\u5728\u5fae\u8c03\u65f6\u4f7f\u7528\u8f83\u4f4e\u7684\u5b66\u4e60\u7387\u3002<\/li>\n<li><strong>\u8d1f\u8fc1\u79fb<\/strong>\uff1a\u8fd9\u662f\u57fa\u7840\u6a21\u578b\u7684\u77e5\u8bc6\u5bf9\u65b0\u4efb\u52a1\u7684\u6027\u80fd\u4ea7\u751f\u8d1f\u9762\u5f71\u54cd\u7684\u60c5\u51b5\u3002\u89e3\u51b3\u65b9\u6848\u5728\u4e8e\u4ed4\u7ec6\u9009\u62e9\u8981\u5fae\u8c03\u7684\u5c42\uff0c\u5e76\u5728\u5fc5\u8981\u65f6\u4f7f\u7528\u7279\u5b9a\u4e8e\u4efb\u52a1\u7684\u5c42\u3002<\/li>\n<\/ol>\n<h2>\u5fae\u8c03\u4e0e\u76f8\u5173\u6982\u5ff5\u7684\u6bd4\u8f83<\/h2>\n<p>\u5fae\u8c03\u901a\u5e38\u4e0e\u76f8\u5173\u6982\u5ff5\u8fdb\u884c\u6bd4\u8f83\uff0c\u4f8b\u5982\uff1a<\/p>\n<ul>\n<li><strong>\u7279\u5f81\u63d0\u53d6<\/strong>\uff1a\u8fd9\u91cc\uff0c\u57fa\u7840\u6a21\u578b\u7eaf\u7cb9\u7528\u4f5c\u7279\u5f81\u63d0\u53d6\u5668\uff0c\u65e0\u9700\u4efb\u4f55\u8fdb\u4e00\u6b65\u7684\u8bad\u7ec3\u3002\u76f8\u53cd\uff0c\u5fae\u8c03\u7ee7\u7eed\u65b0\u4efb\u52a1\u7684\u8bad\u7ec3\u8fc7\u7a0b\u3002<\/li>\n<li><strong>\u8fc1\u79fb\u5b66\u4e60<\/strong>\uff1a\u867d\u7136\u5fae\u8c03\u662f\u8fc1\u79fb\u5b66\u4e60\u7684\u4e00\u79cd\u5f62\u5f0f\uff0c\u4f46\u5e76\u975e\u6240\u6709\u8fc1\u79fb\u5b66\u4e60\u90fd\u6d89\u53ca\u5fae\u8c03\u3002\u5728\u67d0\u4e9b\u60c5\u51b5\u4e0b\uff0c\u4ec5\u4f7f\u7528\u9884\u5148\u8bad\u7ec3\u7684\u6a21\u578b\u7684\u67b6\u6784\uff0c\u5e76\u9488\u5bf9\u65b0\u4efb\u52a1\u4ece\u5934\u5f00\u59cb\u8bad\u7ec3\u6a21\u578b\u3002<\/li>\n<\/ul>\n<table>\n<thead>\n<tr>\n<th>\u6982\u5ff5<\/th>\n<th>\u63cf\u8ff0<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>\u7279\u5f81\u63d0\u53d6<\/td>\n<td>\u7eaf\u7cb9\u4f7f\u7528\u57fa\u7840\u6a21\u578b\u4f5c\u4e3a\u7279\u5f81\u63d0\u53d6\u5668<\/td>\n<\/tr>\n<tr>\n<td>\u8fc1\u79fb\u5b66\u4e60<\/td>\n<td>\u91cd\u7528\u9884\u5148\u8bad\u7ec3\u7684\u6a21\u578b\u7684\u67b6\u6784\u6216\u6743\u91cd<\/td>\n<\/tr>\n<tr>\n<td>\u5fae\u8c03<\/td>\n<td>\u7ee7\u7eed\u9488\u5bf9\u65b0\u4efb\u52a1\u8bad\u7ec3\u9884\u8bad\u7ec3\u6a21\u578b<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>\u672a\u6765\u5c55\u671b\u548c\u65b0\u5174\u6280\u672f<\/h2>\n<p>\u5fae\u8c03\u7684\u672a\u6765\u5728\u4e8e\u4ee5\u66f4\u9ad8\u6548\u3001\u66f4\u6709\u6548\u7684\u65b9\u5f0f\u5728\u4efb\u52a1\u4e4b\u95f4\u4f20\u9012\u77e5\u8bc6\u3002\u4eba\u4eec\u6b63\u5728\u5f00\u53d1\u65b0\u6280\u672f\u6765\u89e3\u51b3\u707e\u96be\u6027\u9057\u5fd8\u548c\u8d1f\u8fc1\u79fb\u7b49\u95ee\u9898\uff0c\u4f8b\u5982\u5f39\u6027\u6743\u91cd\u5408\u5e76\u548c\u6e10\u8fdb\u795e\u7ecf\u7f51\u7edc\u3002\u6b64\u5916\uff0c\u5fae\u8c03\u9884\u8ba1\u5c06\u5728\u5f00\u53d1\u66f4\u5f3a\u5927\u3001\u66f4\u9ad8\u6548\u7684\u4eba\u5de5\u667a\u80fd\u6a21\u578b\u4e2d\u53d1\u6325\u5173\u952e\u4f5c\u7528\u3002<\/p>\n<h2>\u5fae\u8c03\u548c\u4ee3\u7406\u670d\u52a1\u5668<\/h2>\n<p>\u867d\u7136\u5fae\u8c03\u4e0e\u673a\u5668\u5b66\u4e60\u66f4\u76f4\u63a5\u76f8\u5173\uff0c\u4f46\u5b83\u4e0e\u4ee3\u7406\u670d\u52a1\u5668\u786e\u5b9e\u6709\u5207\u7ebf\u76f8\u5173\u6027\u3002\u4ee3\u7406\u670d\u52a1\u5668\u901a\u5e38\u91c7\u7528\u673a\u5668\u5b66\u4e60\u6a21\u578b\u6765\u6267\u884c\u6d41\u91cf\u8fc7\u6ee4\u3001\u5a01\u80c1\u68c0\u6d4b\u548c\u6570\u636e\u538b\u7f29\u7b49\u4efb\u52a1\u3002\u5fae\u8c03\u53ef\u4ee5\u4f7f\u8fd9\u4e9b\u6a21\u578b\u66f4\u597d\u5730\u9002\u5e94\u4e0d\u540c\u7f51\u7edc\u7684\u72ec\u7279\u6d41\u91cf\u6a21\u5f0f\u548c\u5a01\u80c1\u6001\u52bf\uff0c\u63d0\u9ad8\u4ee3\u7406\u670d\u52a1\u5668\u7684\u6574\u4f53\u6027\u80fd\u548c\u5b89\u5168\u6027\u3002<\/p>\n<h2>\u76f8\u5173\u94fe\u63a5<\/h2>\n<ul>\n<li><a href=\"https:\/\/www.nature.com\/articles\/s41598-019-52380-8\" target=\"_new\" rel=\"noopener nofollow\">\u4e86\u89e3\u533b\u5b66\u6210\u50cf\u7684\u8fc1\u79fb\u5b66\u4e60<\/a><\/li>\n<li><a href=\"https:\/\/www.tensorflow.org\/tutorials\/images\/transfer_learning\" target=\"_new\" rel=\"noopener nofollow\">\u5fae\u8c03\u9884\u8bad\u7ec3\u6a21\u578b<\/a><\/li>\n<li><a href=\"https:\/\/www.cloudflare.com\/learning\/cdn\/glossary\/reverse-proxy\/\" target=\"_new\" rel=\"noopener nofollow\">\u4ee3\u7406\u670d\u52a1\u5668\u6982\u8ff0<\/a><\/li>\n<\/ul>","protected":false},"featured_media":491207,"menu_order":0,"template":"","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"footnotes":""},"class_list":["post-477239","wiki","type-wiki","status-publish","has-post-thumbnail","hentry"],"acf":{"faq_title":"Frequently Asked Questions about <mark>Fine-Tuning: A Detailed Overview<\/mark>","faq_items":[{"question":"What is Fine-Tuning in the context of machine learning?","answer":"Fine-tuning is a transfer learning technique in machine learning where a pre-trained model is adapted to suit a different, yet related, task. It leverages the pre-trained model's learned features, saving considerable time and computational resources compared to training a model from scratch."},{"question":"What is the history of Fine-tuning?","answer":"Fine-tuning, in the context of machine learning and deep learning, emerged from the concept of transfer learning. It became increasingly popular with the advent of deep learning and big data in the 2010s. The idea is to harness the power of an already trained model to train a new model for a different but related task."},{"question":"How does Fine-tuning work?","answer":"Fine-tuning is typically carried out in two stages. First, feature extraction where the pre-trained model is used as a fixed feature extractor. The output from this model is fed into a new model, which is then trained on the new task. Then, the fine-tuning stage, where specific layers of the model are \"unfrozen\" and the model is trained again on the new task, but with a very low learning rate."},{"question":"What are the key features of Fine-tuning?","answer":"The key features of fine-tuning include transfer of knowledge, computational efficiency, flexibility, and improved performance. It allows effective knowledge transfer from one task to another, is less computationally intensive, flexible in applying to different layers of the pre-trained model, and often leads to improved model performance."},{"question":"What are the types of Fine-tuning?","answer":"There are primarily two types of fine-tuning: Feature-based Fine-Tuning and Full Fine-Tuning. In the former, the pre-trained model is used as a fixed feature extractor while the new model is trained using these extracted features. In the latter, all or specific layers of the pre-trained model are unfrozen and trained on the new task."},{"question":"What are the applications and challenges of Fine-tuning?","answer":"Fine-tuning is used in various machine learning domains like computer vision, natural language processing, and audio processing. However, it can present challenges like Catastrophic Forgetting and Negative Transfer, which refer to the model forgetting the learned features from the base task while fine-tuning on the new task, and the base model's knowledge negatively impacting the performance on the new task, respectively."},{"question":"How does Fine-tuning compare with similar concepts like feature extraction and transfer learning?","answer":"While fine-tuning, feature extraction, and transfer learning are all related, they differ in their processes. Feature extraction uses the base model purely as a feature extractor without any further training. In contrast, fine-tuning continues the training process on the new task. Transfer learning is a broader term that can encompass both fine-tuning and feature extraction."},{"question":"What is the future perspective of Fine-tuning?","answer":"The future of fine-tuning lies in more efficient and effective ways to transfer knowledge between tasks. Emerging technologies are developing new techniques to address challenges like catastrophic forgetting and negative transfer. Fine-tuning is expected to play a pivotal role in the development of more robust and efficient AI models."},{"question":"How is Fine-tuning related to proxy servers?","answer":"Fine-tuning has relevance to proxy servers as these servers often employ machine learning models for tasks such as traffic filtering, threat detection, and data compression. Fine-tuning can enable these models to better adapt to the unique traffic patterns and threat landscapes of different networks, improving the overall performance and security of the proxy server."}]},"_links":{"self":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/wiki\/477239","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/wiki"}],"about":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/types\/wiki"}],"version-history":[{"count":0,"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/wiki\/477239\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/media\/491207"}],"wp:attachment":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/media?parent=477239"}],"curies":[{"name":"\u53ef\u6e7f\u6027\u7c89\u5242","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}