{"id":479546,"date":"2023-08-09T10:41:56","date_gmt":"2023-08-09T10:41:56","guid":{"rendered":""},"modified":"2023-09-05T11:19:05","modified_gmt":"2023-09-05T11:19:05","slug":"vit-vision-transformer","status":"publish","type":"wiki","link":"https:\/\/oneproxy.pro\/vn\/wiki\/vit-vision-transformer\/","title":{"rendered":"ViT (M\u00e1y bi\u1ebfn \u0111\u1ed5i t\u1ea7m nh\u00ecn)"},"content":{"rendered":"<p>Th\u00f4ng tin t\u00f3m t\u1eaft v\u1ec1 ViT (Vision Transformer)<\/p>\n<p>Vision Transformer (ViT) l\u00e0 m\u1ed9t ki\u1ebfn tr\u00fac m\u1ea1ng th\u1ea7n kinh c\u1ea3i ti\u1ebfn s\u1eed d\u1ee5ng ki\u1ebfn tr\u00fac Transformer, \u0111\u01b0\u1ee3c thi\u1ebft k\u1ebf ch\u1ee7 y\u1ebfu \u0111\u1ec3 x\u1eed l\u00fd ng\u00f4n ng\u1eef t\u1ef1 nhi\u00ean, trong l\u0129nh v\u1ef1c th\u1ecb gi\u00e1c m\u00e1y t\u00ednh. Kh\u00f4ng gi\u1ed1ng nh\u01b0 c\u00e1c m\u1ea1ng th\u1ea7n kinh t\u00edch ch\u1eadp truy\u1ec1n th\u1ed1ng (CNN), ViT s\u1eed d\u1ee5ng c\u00e1c c\u01a1 ch\u1ebf t\u1ef1 ch\u00fa \u00fd \u0111\u1ec3 x\u1eed l\u00fd h\u00ecnh \u1ea3nh song song, \u0111\u1ea1t \u0111\u01b0\u1ee3c hi\u1ec7u su\u1ea5t ti\u00ean ti\u1ebfn trong c\u00e1c t\u00e1c v\u1ee5 th\u1ecb gi\u00e1c m\u00e1y t\u00ednh kh\u00e1c nhau.<\/p>\n<h2>L\u1ecbch s\u1eed ngu\u1ed3n g\u1ed1c c\u1ee7a ViT (Vision Transformer) v\u00e0 l\u1ea7n \u0111\u1ea7u ti\u00ean nh\u1eafc t\u1edbi n\u00f3<\/h2>\n<p>Vision Transformer l\u1ea7n \u0111\u1ea7u ti\u00ean \u0111\u01b0\u1ee3c gi\u1edbi thi\u1ec7u b\u1edfi c\u00e1c nh\u00e0 nghi\u00ean c\u1ee9u c\u1ee7a Google Brain trong m\u1ed9t b\u00e0i b\u00e1o c\u00f3 ti\u00eau \u0111\u1ec1 \u201cM\u1ed9t h\u00ecnh \u1ea3nh c\u00f3 gi\u00e1 tr\u1ecb 16 \u00d7 16 t\u1eeb: Transformers \u0111\u1ec3 nh\u1eadn d\u1ea1ng h\u00ecnh \u1ea3nh \u1edf quy m\u00f4,\u201d xu\u1ea5t b\u1ea3n v\u00e0o n\u0103m 2020. Nghi\u00ean c\u1ee9u n\u00e0y b\u1eaft ngu\u1ed3n t\u1eeb \u00fd t\u01b0\u1edfng \u0111i\u1ec1u ch\u1ec9nh ki\u1ebfn tr\u00fac Transformer, ban \u0111\u1ea7u \u0111\u01b0\u1ee3c t\u1ea1o ra b\u1edfi Vaswani et al. v\u00e0o n\u0103m 2017 \u0111\u1ec3 x\u1eed l\u00fd v\u0103n b\u1ea3n, x\u1eed l\u00fd d\u1eef li\u1ec7u h\u00ecnh \u1ea3nh. K\u1ebft qu\u1ea3 l\u00e0 m\u1ed9t s\u1ef1 thay \u0111\u1ed5i \u0111\u1ed9t ph\u00e1 trong nh\u1eadn d\u1ea1ng h\u00ecnh \u1ea3nh, d\u1eabn \u0111\u1ebfn hi\u1ec7u qu\u1ea3 v\u00e0 \u0111\u1ed9 ch\u00ednh x\u00e1c \u0111\u01b0\u1ee3c c\u1ea3i thi\u1ec7n.<\/p>\n<h2>Th\u00f4ng tin chi ti\u1ebft v\u1ec1 ViT (Vision Transformer): M\u1edf r\u1ed9ng ch\u1ee7 \u0111\u1ec1<\/h2>\n<p>ViT x\u1eed l\u00fd h\u00ecnh \u1ea3nh d\u01b0\u1edbi d\u1ea1ng m\u1ed9t chu\u1ed7i c\u00e1c b\u1ea3n v\u00e1, t\u01b0\u01a1ng t\u1ef1 nh\u01b0 c\u00e1ch x\u1eed l\u00fd v\u0103n b\u1ea3n d\u01b0\u1edbi d\u1ea1ng m\u1ed9t chu\u1ed7i c\u00e1c t\u1eeb trong NLP. N\u00f3 chia h\u00ecnh \u1ea3nh th\u00e0nh c\u00e1c m\u1ea3ng nh\u1ecf c\u00f3 k\u00edch th\u01b0\u1edbc c\u1ed1 \u0111\u1ecbnh v\u00e0 nh\u00fang ch\u00fang m\u1ed9t c\u00e1ch tuy\u1ebfn t\u00ednh v\u00e0o m\u1ed9t chu\u1ed7i vect\u01a1. Sau \u0111\u00f3, m\u00f4 h\u00ecnh x\u1eed l\u00fd c\u00e1c vect\u01a1 n\u00e0y b\u1eb1ng c\u01a1 ch\u1ebf t\u1ef1 ch\u00fa \u00fd v\u00e0 m\u1ea1ng chuy\u1ec3n ti\u1ebfp ngu\u1ed3n c\u1ea5p d\u1eef li\u1ec7u, t\u00ecm hi\u1ec3u c\u00e1c m\u1ed1i quan h\u1ec7 kh\u00f4ng gian v\u00e0 c\u00e1c m\u1eabu ph\u1ee9c t\u1ea1p trong h\u00ecnh \u1ea3nh.<\/p>\n<h3>Th\u00e0nh ph\u1ea7n ch\u00ednh:<\/h3>\n<ul>\n<li><strong>B\u1ea3n v\u00e1 l\u1ed7i:<\/strong> H\u00ecnh \u1ea3nh \u0111\u01b0\u1ee3c chia th\u00e0nh c\u00e1c m\u1ea3ng nh\u1ecf (v\u00ed d\u1ee5: 16\u00d716).<\/li>\n<li><strong>Nh\u00fang:<\/strong> C\u00e1c b\u1ea3n v\u00e1 \u0111\u01b0\u1ee3c chuy\u1ec3n \u0111\u1ed5i th\u00e0nh vect\u01a1 th\u00f4ng qua vi\u1ec7c nh\u00fang tuy\u1ebfn t\u00ednh.<\/li>\n<li><strong>M\u00e3 h\u00f3a v\u1ecb tr\u00ed:<\/strong> Th\u00f4ng tin v\u1ecb tr\u00ed \u0111\u01b0\u1ee3c th\u00eam v\u00e0o c\u00e1c vect\u01a1.<\/li>\n<li><strong>C\u01a1 ch\u1ebf t\u1ef1 ch\u00fa \u00fd:<\/strong> M\u00f4 h\u00ecnh x\u1eed l\u00fd \u0111\u1ed3ng th\u1eddi t\u1ea5t c\u1ea3 c\u00e1c ph\u1ea7n c\u1ee7a h\u00ecnh \u1ea3nh.<\/li>\n<li><strong>M\u1ea1ng chuy\u1ec3n ti\u1ebfp ngu\u1ed3n c\u1ea5p d\u1eef li\u1ec7u:<\/strong> Ch\u00fang \u0111\u01b0\u1ee3c s\u1eed d\u1ee5ng \u0111\u1ec3 x\u1eed l\u00fd c\u00e1c vect\u01a1 tham d\u1ef1.<\/li>\n<\/ul>\n<h2>C\u1ea5u tr\u00fac b\u00ean trong c\u1ee7a ViT (B\u1ed9 bi\u1ebfn \u0111\u1ed5i t\u1ea7m nh\u00ecn)<\/h2>\n<p>C\u1ea5u tr\u00fac c\u1ee7a ViT bao g\u1ed3m l\u1edbp v\u00e1 v\u00e0 nh\u00fang ban \u0111\u1ea7u, sau \u0111\u00f3 l\u00e0 m\u1ed9t lo\u1ea1t c\u00e1c kh\u1ed1i Transformer. M\u1ed7i kh\u1ed1i ch\u1ee9a m\u1ed9t l\u1edbp t\u1ef1 ch\u00fa \u00fd nhi\u1ec1u \u0111\u1ea7u v\u00e0 m\u1ea1ng l\u01b0\u1edbi th\u1ea7n kinh chuy\u1ec3n ti\u1ebfp ngu\u1ed3n c\u1ea5p d\u1eef li\u1ec7u.<\/p>\n<ol>\n<li><strong>L\u1edbp \u0111\u1ea7u v\u00e0o:<\/strong> H\u00ecnh \u1ea3nh \u0111\u01b0\u1ee3c chia th\u00e0nh c\u00e1c m\u1ea3ng v\u00e0 \u0111\u01b0\u1ee3c nh\u00fang d\u01b0\u1edbi d\u1ea1ng vect\u01a1.<\/li>\n<li><strong>Kh\u1ed1i m\u00e1y bi\u1ebfn \u00e1p:<\/strong> Nhi\u1ec1u l\u1edbp bao g\u1ed3m:\n<ul>\n<li>T\u1ef1 ch\u00fa \u00fd nhi\u1ec1u \u0111\u1ea7u<\/li>\n<li>Chu\u1ea9n h\u00f3a<\/li>\n<li>M\u1ea1ng th\u1ea7n kinh chuy\u1ec3n ti\u1ebfp ngu\u1ed3n c\u1ea5p d\u1eef li\u1ec7u<\/li>\n<li>Chu\u1ea9n h\u00f3a b\u1ed5 sung<\/li>\n<\/ul>\n<\/li>\n<li><strong>L\u1edbp \u0111\u1ea7u ra:<\/strong> Ng\u01b0\u1eddi \u0111\u1ee9ng \u0111\u1ea7u ph\u00e2n lo\u1ea1i cu\u1ed1i c\u00f9ng.<\/li>\n<\/ol>\n<h2>Ph\u00e2n t\u00edch c\u00e1c t\u00ednh n\u0103ng ch\u00ednh c\u1ee7a ViT (Vision Transformer)<\/h2>\n<ul>\n<li><strong>Ti\u1ebfn tr\u00ecnh song song:<\/strong> Kh\u00f4ng gi\u1ed1ng nh\u01b0 CNN, ViT x\u1eed l\u00fd th\u00f4ng tin \u0111\u1ed3ng th\u1eddi.<\/li>\n<li><strong>Kh\u1ea3 n\u0103ng m\u1edf r\u1ed9ng:<\/strong> Ho\u1ea1t \u0111\u1ed9ng t\u1ed1t v\u1edbi nhi\u1ec1u k\u00edch c\u1ee1 h\u00ecnh \u1ea3nh kh\u00e1c nhau.<\/li>\n<li><strong>S\u1ef1 kh\u00e1i qu\u00e1t:<\/strong> C\u00f3 th\u1ec3 \u00e1p d\u1ee5ng cho c\u00e1c nhi\u1ec7m v\u1ee5 th\u1ecb gi\u00e1c m\u00e1y t\u00ednh kh\u00e1c nhau.<\/li>\n<li><strong>Hi\u1ec7u qu\u1ea3 d\u1eef li\u1ec7u:<\/strong> Y\u00eau c\u1ea7u d\u1eef li\u1ec7u r\u1ed9ng r\u00e3i cho \u0111\u00e0o t\u1ea1o.<\/li>\n<\/ul>\n<h2>C\u00e1c lo\u1ea1i ViT (Bi\u1ebfn \u00e1p t\u1ea7m nh\u00ecn)<\/h2>\n<table>\n<thead>\n<tr>\n<th>Ki\u1ec3u<\/th>\n<th>S\u1ef1 mi\u00eau t\u1ea3<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>ViT c\u01a1 b\u1ea3n<\/td>\n<td>Model g\u1ed1c v\u1edbi c\u00e0i \u0111\u1eb7t ti\u00eau chu\u1ea9n.<\/td>\n<\/tr>\n<tr>\n<td>ViT lai<\/td>\n<td>K\u1ebft h\u1ee3p v\u1edbi c\u00e1c l\u1edbp CNN \u0111\u1ec3 t\u0103ng th\u00eam t\u00ednh linh ho\u1ea1t.<\/td>\n<\/tr>\n<tr>\n<td>ViT ch\u01b0ng c\u1ea5t<\/td>\n<td>M\u1ed9t phi\u00ean b\u1ea3n nh\u1ecf h\u01a1n v\u00e0 hi\u1ec7u qu\u1ea3 h\u01a1n c\u1ee7a m\u00f4 h\u00ecnh.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>C\u00e1ch s\u1eed d\u1ee5ng ViT (Vision Transformer), c\u00e1c v\u1ea5n \u0111\u1ec1 v\u00e0 gi\u1ea3i ph\u00e1p c\u1ee7a ch\u00fang<\/h2>\n<h3>C\u00f4ng d\u1ee5ng:<\/h3>\n<ul>\n<li>Ph\u00e2n lo\u1ea1i h\u00ecnh \u1ea3nh<\/li>\n<li>Ph\u00e1t hi\u1ec7n \u0111\u1ed1i t\u01b0\u1ee3ng<\/li>\n<li>Ph\u00e2n \u0111o\u1ea1n ng\u1eef ngh\u0129a<\/li>\n<\/ul>\n<h3>C\u00e1c v\u1ea5n \u0111\u1ec1:<\/h3>\n<ul>\n<li>Y\u00eau c\u1ea7u b\u1ed9 d\u1eef li\u1ec7u l\u1edbn<\/li>\n<li>\u0110\u1eaft ti\u1ec1n<\/li>\n<\/ul>\n<h3>C\u00e1c gi\u1ea3i ph\u00e1p:<\/h3>\n<ul>\n<li>T\u0103ng c\u01b0\u1eddng d\u1eef li\u1ec7u<\/li>\n<li>S\u1eed d\u1ee5ng c\u00e1c m\u00f4 h\u00ecnh \u0111\u01b0\u1ee3c \u0111\u00e0o t\u1ea1o tr\u01b0\u1edbc<\/li>\n<\/ul>\n<h2>C\u00e1c \u0111\u1eb7c \u0111i\u1ec3m ch\u00ednh v\u00e0 so s\u00e1nh v\u1edbi c\u00e1c thu\u1eadt ng\u1eef t\u01b0\u01a1ng t\u1ef1<\/h2>\n<table>\n<thead>\n<tr>\n<th>T\u00ednh n\u0103ng<\/th>\n<th>ViT<\/th>\n<th>CNN truy\u1ec1n th\u1ed1ng<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Ng\u00e0nh ki\u1ebfn tr\u00fac<\/td>\n<td>D\u1ef1a tr\u00ean m\u00e1y bi\u1ebfn \u00e1p<\/td>\n<td>D\u1ef1a tr\u00ean t\u00edch ch\u1eadp<\/td>\n<\/tr>\n<tr>\n<td>Ti\u1ebfn tr\u00ecnh song song<\/td>\n<td>\u0110\u00fang<\/td>\n<td>KH\u00d4NG<\/td>\n<\/tr>\n<tr>\n<td>Kh\u1ea3 n\u0103ng m\u1edf r\u1ed9ng<\/td>\n<td>Cao<\/td>\n<td>Kh\u00e1c nhau<\/td>\n<\/tr>\n<tr>\n<td>D\u1eef li\u1ec7u \u0111\u00e0o t\u1ea1o<\/td>\n<td>Y\u00eau c\u1ea7u nhi\u1ec1u h\u01a1n<\/td>\n<td>N\u00f3i chung y\u00eau c\u1ea7u \u00edt h\u01a1n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>Quan \u0111i\u1ec3m v\u00e0 c\u00f4ng ngh\u1ec7 c\u1ee7a t\u01b0\u01a1ng lai li\u00ean quan \u0111\u1ebfn ViT<\/h2>\n<p>ViT m\u1edf \u0111\u01b0\u1eddng cho nghi\u00ean c\u1ee9u trong t\u01b0\u01a1ng lai trong c\u00e1c l\u0129nh v\u1ef1c nh\u01b0 h\u1ecdc t\u1eadp \u0111a ph\u01b0\u01a1ng th\u1ee9c, h\u00ecnh \u1ea3nh 3D v\u00e0 x\u1eed l\u00fd th\u1eddi gian th\u1ef1c. S\u1ef1 \u0111\u1ed5i m\u1edbi li\u00ean t\u1ee5c c\u00f3 th\u1ec3 d\u1eabn \u0111\u1ebfn c\u00e1c m\u00f4 h\u00ecnh hi\u1ec7u qu\u1ea3 h\u01a1n v\u00e0 \u1ee9ng d\u1ee5ng r\u1ed9ng h\u01a1n trong c\u00e1c ng\u00e0nh, bao g\u1ed3m ch\u0103m s\u00f3c s\u1ee9c kh\u1ecfe, an ninh v\u00e0 gi\u1ea3i tr\u00ed.<\/p>\n<h2>C\u00e1ch s\u1eed d\u1ee5ng ho\u1eb7c li\u00ean k\u1ebft m\u00e1y ch\u1ee7 proxy v\u1edbi ViT (Vision Transformer)<\/h2>\n<p>C\u00e1c m\u00e1y ch\u1ee7 proxy, gi\u1ed1ng nh\u01b0 c\u00e1c m\u00e1y ch\u1ee7 do OneProxy cung c\u1ea5p, c\u00f3 th\u1ec3 l\u00e0 c\u00f4ng c\u1ee5 \u0111\u00e0o t\u1ea1o c\u00e1c m\u00f4 h\u00ecnh ViT. Ch\u00fang c\u00f3 th\u1ec3 cho ph\u00e9p truy c\u1eadp v\u00e0o c\u00e1c b\u1ed9 d\u1eef li\u1ec7u \u0111a d\u1ea1ng v\u00e0 \u0111\u01b0\u1ee3c ph\u00e2n b\u1ed5 theo \u0111\u1ecba l\u00fd, t\u0103ng c\u01b0\u1eddng quy\u1ec1n ri\u00eang t\u01b0 d\u1eef li\u1ec7u v\u00e0 \u0111\u1ea3m b\u1ea3o k\u1ebft n\u1ed1i tr\u01a1n tru cho ho\u1ea1t \u0111\u1ed9ng \u0111\u00e0o t\u1ea1o ph\u00e2n t\u00e1n. S\u1ef1 t\u00edch h\u1ee3p n\u00e0y \u0111\u1eb7c bi\u1ec7t quan tr\u1ecdng \u0111\u1ed1i v\u1edbi vi\u1ec7c tri\u1ec3n khai ViT tr\u00ean quy m\u00f4 l\u1edbn.<\/p>\n<h2>Li\u00ean k\u1ebft li\u00ean quan<\/h2>\n<ul>\n<li><a href=\"https:\/\/arxiv.org\/abs\/2010.11929\" target=\"_new\" rel=\"noopener nofollow\">B\u00e0i vi\u1ebft g\u1ed1c c\u1ee7a Google Brain v\u1ec1 ViT<\/a><\/li>\n<li><a href=\"https:\/\/arxiv.org\/abs\/1706.03762\" target=\"_new\" rel=\"noopener nofollow\">Ki\u1ebfn tr\u00fac m\u00e1y bi\u1ebfn \u00e1p<\/a><\/li>\n<li><a href=\"https:\/\/oneproxy.pro\/vn\/\" target=\"_new\" rel=\"noopener\">Trang web OneProxy<\/a> cho c\u00e1c gi\u1ea3i ph\u00e1p m\u00e1y ch\u1ee7 proxy li\u00ean quan \u0111\u1ebfn ViT.<\/li>\n<\/ul>\n<hr>\n<p><em>L\u01b0u \u00fd: B\u00e0i vi\u1ebft n\u00e0y \u0111\u01b0\u1ee3c t\u1ea1o ra nh\u1eb1m m\u1ee5c \u0111\u00edch gi\u00e1o d\u1ee5c v\u00e0 cung c\u1ea5p th\u00f4ng tin v\u00e0 c\u00f3 th\u1ec3 y\u00eau c\u1ea7u c\u1eadp nh\u1eadt th\u00eam \u0111\u1ec3 ph\u1ea3n \u00e1nh nh\u1eefng nghi\u00ean c\u1ee9u v\u00e0 ph\u00e1t tri\u1ec3n m\u1edbi nh\u1ea5t trong l\u0129nh v\u1ef1c ViT (Vision Transformer).<\/em><\/p>","protected":false},"featured_media":470846,"menu_order":0,"template":"","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"footnotes":""},"class_list":["post-479546","wiki","type-wiki","status-publish","has-post-thumbnail","hentry"],"acf":{"faq_title":"Frequently Asked Questions about <mark>ViT (Vision Transformer): An In-Depth Exploration<\/mark>","faq_items":[{"question":"What is the Vision Transformer (ViT)?","answer":"<p>The Vision Transformer (ViT) is a neural network architecture that utilizes the Transformer model, originally designed for natural language processing, to process images. It breaks down images into patches and processes them through self-attention mechanisms, offering parallel processing and state-of-the-art performance in computer vision tasks.<\/p>"},{"question":"How does the Vision Transformer (ViT) differ from traditional Convolutional Neural Networks (CNNs)?","answer":"<p>ViT differs from traditional CNNs by using a Transformer-based architecture instead of convolution-based layers. It processes information simultaneously across the entire image, providing higher scalability. On the downside, it often requires more training data compared to CNNs.<\/p>"},{"question":"What are the different types of ViT?","answer":"<p>There are several types of ViT, including the Base ViT (the original model), Hybrid ViT (combined with CNN layers), and Distilled ViT (a smaller and more efficient version).<\/p>"},{"question":"What are some applications and uses of ViT?","answer":"<p>ViT is used in various computer vision tasks such as image classification, object detection, and semantic segmentation.<\/p>"},{"question":"What are the main challenges in using ViT, and how can they be addressed?","answer":"<p>The main challenges in using ViT include the requirement of large datasets and its computational expense. These challenges can be addressed through data augmentation, utilizing pre-trained models, and leveraging advanced hardware.<\/p>"},{"question":"How do proxy servers, such as those provided by OneProxy, relate to ViT?","answer":"<p>Proxy servers like OneProxy can facilitate the training of ViT models by enabling access to diverse and geographically distributed datasets. They can also enhance data privacy and ensure smooth connectivity for distributed training.<\/p>"},{"question":"What are the future perspectives and technologies related to ViT?","answer":"<p>The future of ViT is promising, with potential developments in areas like multi-modal learning, 3D imaging, and real-time processing. It may lead to broader applications across various industries, including healthcare, security, and entertainment.<\/p>"},{"question":"Where can I find more information and resources related to ViT?","answer":"<p>You can find more information about ViT in the original paper by Google Brain, various academic resources, and through the OneProxy website for proxy server solutions related to ViT. Links to these resources are provided at the end of the main article.<\/p>"}]},"_links":{"self":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/wiki\/479546","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/wiki"}],"about":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/types\/wiki"}],"version-history":[{"count":0,"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/wiki\/479546\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/media\/470846"}],"wp:attachment":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/media?parent=479546"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}