{"id":1185,"date":"2023-08-25T06:41:36","date_gmt":"2023-08-25T06:41:36","guid":{"rendered":"https:\/\/babyai-hub.vizdata.tech\/?p=1185"},"modified":"2023-09-04T14:56:32","modified_gmt":"2023-09-04T14:56:32","slug":"elementor-1185","status":"publish","type":"post","link":"https:\/\/babyai-hub.vizdata.tech\/?p=1185","title":{"rendered":"Person Search With Natural Language Description : Person Description Model"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"1185\" class=\"elementor elementor-1185\" data-elementor-post-type=\"post\">\n\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-e6142bd e-flex e-con-boxed e-con e-parent\" data-id=\"e6142bd\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\" data-core-v316-plus=\"true\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-d36b18f elementor-widget elementor-widget-heading\" data-id=\"d36b18f\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.16.0 - 23-08-2023 *\/\n.elementor-heading-title{padding:0;margin:0;line-height:1}.elementor-widget-heading .elementor-heading-title[class*=elementor-size-]>a{color:inherit;font-size:inherit;line-height:inherit}.elementor-widget-heading .elementor-heading-title.elementor-size-small{font-size:15px}.elementor-widget-heading .elementor-heading-title.elementor-size-medium{font-size:19px}.elementor-widget-heading .elementor-heading-title.elementor-size-large{font-size:29px}.elementor-widget-heading .elementor-heading-title.elementor-size-xl{font-size:39px}.elementor-widget-heading .elementor-heading-title.elementor-size-xxl{font-size:59px}<\/style><h2 class=\"elementor-heading-title elementor-size-default\">Person Description Model<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-b483bd0 elementor-widget elementor-widget-heading\" data-id=\"b483bd0\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\"><b>-Person Search With Natural Language Description-<\/b><\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-0bbb04d elementor-widget elementor-widget-spacer\" data-id=\"0bbb04d\" data-element_type=\"widget\" data-widget_type=\"spacer.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.16.0 - 23-08-2023 *\/\n.elementor-column .elementor-spacer-inner{height:var(--spacer-size)}.e-con{--container-widget-width:100%}.e-con-inner>.elementor-widget-spacer,.e-con>.elementor-widget-spacer{width:var(--container-widget-width,var(--spacer-size));--align-self:var(--container-widget-align-self,initial);--flex-shrink:0}.e-con-inner>.elementor-widget-spacer>.elementor-widget-container,.e-con>.elementor-widget-spacer>.elementor-widget-container{height:100%;width:100%}.e-con-inner>.elementor-widget-spacer>.elementor-widget-container>.elementor-spacer,.e-con>.elementor-widget-spacer>.elementor-widget-container>.elementor-spacer{height:100%}.e-con-inner>.elementor-widget-spacer>.elementor-widget-container>.elementor-spacer>.elementor-spacer-inner,.e-con>.elementor-widget-spacer>.elementor-widget-container>.elementor-spacer>.elementor-spacer-inner{height:var(--container-widget-height,var(--spacer-size))}.e-con-inner>.elementor-widget-spacer.elementor-widget-empty,.e-con>.elementor-widget-spacer.elementor-widget-empty{position:relative;min-height:22px;min-width:22px}.e-con-inner>.elementor-widget-spacer.elementor-widget-empty .elementor-widget-empty-icon,.e-con>.elementor-widget-spacer.elementor-widget-empty .elementor-widget-empty-icon{position:absolute;top:0;bottom:0;left:0;right:0;margin:auto;padding:0;width:22px;height:22px}<\/style>\t\t<div class=\"elementor-spacer\">\n\t\t\t<div class=\"elementor-spacer-inner\"><\/div>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-6386924 e-flex e-con-boxed e-con e-parent\" data-id=\"6386924\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\" data-core-v316-plus=\"true\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-45b9a79 elementor-widget-divider--view-line_text elementor-widget__width-initial elementor-widget-divider--separator-type-pattern elementor-widget-divider--element-align-center elementor-widget elementor-widget-divider\" data-id=\"45b9a79\" data-element_type=\"widget\" data-widget_type=\"divider.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.16.0 - 23-08-2023 *\/\n.elementor-widget-divider{--divider-border-style:none;--divider-border-width:1px;--divider-color:#0c0d0e;--divider-icon-size:20px;--divider-element-spacing:10px;--divider-pattern-height:24px;--divider-pattern-size:20px;--divider-pattern-url:none;--divider-pattern-repeat:repeat-x}.elementor-widget-divider .elementor-divider{display:flex}.elementor-widget-divider .elementor-divider__text{font-size:15px;line-height:1;max-width:95%}.elementor-widget-divider .elementor-divider__element{margin:0 var(--divider-element-spacing);flex-shrink:0}.elementor-widget-divider .elementor-icon{font-size:var(--divider-icon-size)}.elementor-widget-divider .elementor-divider-separator{display:flex;margin:0;direction:ltr}.elementor-widget-divider--view-line_icon .elementor-divider-separator,.elementor-widget-divider--view-line_text .elementor-divider-separator{align-items:center}.elementor-widget-divider--view-line_icon .elementor-divider-separator:after,.elementor-widget-divider--view-line_icon .elementor-divider-separator:before,.elementor-widget-divider--view-line_text .elementor-divider-separator:after,.elementor-widget-divider--view-line_text .elementor-divider-separator:before{display:block;content:\"\";border-bottom:0;flex-grow:1;border-top:var(--divider-border-width) var(--divider-border-style) var(--divider-color)}.elementor-widget-divider--element-align-left .elementor-divider .elementor-divider-separator>.elementor-divider__svg:first-of-type{flex-grow:0;flex-shrink:100}.elementor-widget-divider--element-align-left .elementor-divider-separator:before{content:none}.elementor-widget-divider--element-align-left .elementor-divider__element{margin-left:0}.elementor-widget-divider--element-align-right .elementor-divider .elementor-divider-separator>.elementor-divider__svg:last-of-type{flex-grow:0;flex-shrink:100}.elementor-widget-divider--element-align-right .elementor-divider-separator:after{content:none}.elementor-widget-divider--element-align-right .elementor-divider__element{margin-right:0}.elementor-widget-divider:not(.elementor-widget-divider--view-line_text):not(.elementor-widget-divider--view-line_icon) .elementor-divider-separator{border-top:var(--divider-border-width) var(--divider-border-style) var(--divider-color)}.elementor-widget-divider--separator-type-pattern{--divider-border-style:none}.elementor-widget-divider--separator-type-pattern.elementor-widget-divider--view-line .elementor-divider-separator,.elementor-widget-divider--separator-type-pattern:not(.elementor-widget-divider--view-line) .elementor-divider-separator:after,.elementor-widget-divider--separator-type-pattern:not(.elementor-widget-divider--view-line) .elementor-divider-separator:before,.elementor-widget-divider--separator-type-pattern:not([class*=elementor-widget-divider--view]) .elementor-divider-separator{width:100%;min-height:var(--divider-pattern-height);-webkit-mask-size:var(--divider-pattern-size) 100%;mask-size:var(--divider-pattern-size) 100%;-webkit-mask-repeat:var(--divider-pattern-repeat);mask-repeat:var(--divider-pattern-repeat);background-color:var(--divider-color);-webkit-mask-image:var(--divider-pattern-url);mask-image:var(--divider-pattern-url)}.elementor-widget-divider--no-spacing{--divider-pattern-size:auto}.elementor-widget-divider--bg-round{--divider-pattern-repeat:round}.rtl .elementor-widget-divider .elementor-divider__text{direction:rtl}.e-con-inner>.elementor-widget-divider,.e-con>.elementor-widget-divider{width:var(--container-widget-width,100%);--flex-grow:var(--container-widget-flex-grow)}<\/style>\t\t<div class=\"elementor-divider\" style=\"--divider-pattern-url: url(&quot;data:image\/svg+xml,%3Csvg xmlns=&#039;http:\/\/www.w3.org\/2000\/svg&#039; preserveAspectRatio=&#039;none&#039; overflow=&#039;visible&#039; height=&#039;100%&#039; viewBox=&#039;0 0 20 16&#039; fill=&#039;none&#039; stroke=&#039;black&#039; stroke-width=&#039;1&#039; stroke-linecap=&#039;square&#039; stroke-miterlimit=&#039;10&#039;%3E%3Cg transform=&#039;translate(-12.000000, 0)&#039;%3E%3Cpath d=&#039;M28,0L10,18&#039;\/%3E%3Cpath d=&#039;M18,0L0,18&#039;\/%3E%3Cpath d=&#039;M48,0L30,18&#039;\/%3E%3Cpath d=&#039;M38,0L20,18&#039;\/%3E%3C\/g%3E%3C\/svg%3E&quot;);\">\n\t\t\t<span class=\"elementor-divider-separator\">\n\t\t\t\t\t\t\t<h1 class=\"elementor-divider__text elementor-divider__element\">\n\t\t\t\tDISCRIPTION\t\t\t\t<\/h1>\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-3039e02 elementor-widget elementor-widget-spacer\" data-id=\"3039e02\" data-element_type=\"widget\" data-widget_type=\"spacer.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-spacer\">\n\t\t\t<div class=\"elementor-spacer-inner\"><\/div>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-a4ee7bd e-flex e-con-boxed e-con e-parent\" data-id=\"a4ee7bd\" data-element_type=\"container\" data-settings=\"{&quot;content_width&quot;:&quot;boxed&quot;}\" data-core-v316-plus=\"true\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-90e1fae elementor-widget elementor-widget-heading\" data-id=\"90e1fae\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">ort_inputs = { \"images\": np.zeros([1, 3, 384, 128], dtype=np.float32), \"txt\": np.expand_dims(np.array(tokens[\"input_ids\"], dtype=np.int64), axis=0), \"attention_mask\": np.ones([1,64], dtype=np.int64) }<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-6dc788b elementor-widget elementor-widget-heading\" data-id=\"6dc788b\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">ort_outs = ort_session.run(None, ort_inputs)<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-f8ff780 elementor-widget elementor-widget-heading\" data-id=\"f8ff780\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">text_emb = ort_outs[1] # 1,2048<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-eb9bf4f elementor-widget elementor-widget-heading\" data-id=\"eb9bf4f\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">The example code above shows how to use this model. The <b>ort_session<\/b> is an ONNX inference session.<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-324ede4 elementor-widget elementor-widget-heading\" data-id=\"324ede4\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">During inference, the input image is not needed, because the video to be searched must be pre-indexed. It can be simply an array of all zeros. The <b>txt<\/b> input field is the tokenized search query. The tokenizer is the same as the WangchanBERTa model. Since the model must be able to see the entire query text, <b>attention_mask<\/b> is all ones.<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-d8b65e0 elementor-widget elementor-widget-heading\" data-id=\"d8b65e0\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">The output text_emb is the embedding (numpy array of size 1x2048) of the description text. It can be compared with the pre-calculated image embedding of each person in the video using approximate nearest neighbour search.<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Person Description Model -Person Search With Natural Language Description- DISCRIPTION ort_inputs = { &#8220;images&#8221;: np.zeros([1, 3, 384, 128], dtype=np.float32), &#8220;txt&#8221;: np.expand_dims(np.array(tokens[&#8220;input_ids&#8221;], dtype=np.int64),.<\/p>\n","protected":false},"author":3,"featured_media":1626,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[74,33],"tags":[76,75,50],"class_list":["post-1185","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-model","category-person-search-with-natural-language-description","tag-description","tag-model","tag-person"],"_links":{"self":[{"href":"https:\/\/babyai-hub.vizdata.tech\/index.php?rest_route=\/wp\/v2\/posts\/1185","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/babyai-hub.vizdata.tech\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/babyai-hub.vizdata.tech\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/babyai-hub.vizdata.tech\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/babyai-hub.vizdata.tech\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1185"}],"version-history":[{"count":14,"href":"https:\/\/babyai-hub.vizdata.tech\/index.php?rest_route=\/wp\/v2\/posts\/1185\/revisions"}],"predecessor-version":[{"id":2046,"href":"https:\/\/babyai-hub.vizdata.tech\/index.php?rest_route=\/wp\/v2\/posts\/1185\/revisions\/2046"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/babyai-hub.vizdata.tech\/index.php?rest_route=\/wp\/v2\/media\/1626"}],"wp:attachment":[{"href":"https:\/\/babyai-hub.vizdata.tech\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1185"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/babyai-hub.vizdata.tech\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1185"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/babyai-hub.vizdata.tech\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1185"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}