{"id":87,"date":"2024-08-08T10:22:51","date_gmt":"2024-08-08T02:22:51","guid":{"rendered":"http:\/\/110.42.248.92\/onsite-learning-center\/?page_id=87"},"modified":"2024-08-12T12:03:18","modified_gmt":"2024-08-12T04:03:18","slug":"%e5%8a%9f%e8%83%bd%e5%87%bd%e6%95%b0%e8%af%a6%e6%83%85-%e6%a8%a1%e5%9e%8b%e8%af%84%e4%bc%b0","status":"publish","type":"page","link":"http:\/\/110.42.248.92\/onsite-learning-center\/en\/%e8%b5%84%e6%ba%90%e5%ba%93\/%e5%8a%9f%e8%83%bd%e5%87%bd%e6%95%b0%e6%a6%82%e8%bf%b0\/%e5%8a%9f%e8%83%bd%e5%87%bd%e6%95%b0%e8%af%a6%e6%83%85-%e6%a8%a1%e5%9e%8b%e8%af%84%e4%bc%b0\/","title":{"rendered":"Utility Function Details \u2014 Model Evaluation"},"content":{"rendered":"<div class=\"fusion-fullwidth fullwidth-box fusion-builder-row-1 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling\" style=\"--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-flex-wrap:wrap;\" ><div class=\"fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap\" style=\"max-width:1248px;margin-left: calc(-4% \/ 2 );margin-right: calc(-4% \/ 2 );\"><div class=\"fusion-layout-column fusion_builder_column fusion-builder-column-0 fusion_builder_column_1_4 1_4 fusion-flex-column\" style=\"--awb-bg-size:cover;--awb-width-large:25%;--awb-margin-top-large:0px;--awb-spacing-right-large:7.68%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:7.68%;--awb-width-medium:25%;--awb-order-medium:0;--awb-spacing-right-medium:7.68%;--awb-spacing-left-medium:7.68%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;\"><div class=\"fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column\"><div class=\"fusion-text fusion-text-1\"><\/div><nav class=\"awb-menu awb-menu_column awb-menu_em-click mobile-mode-collapse-to-button awb-menu_icons-left awb-menu_dc-yes mobile-trigger-fullwidth-off awb-menu_mobile-toggle mobile-size-full-absolute loading mega-menu-loading awb-menu_desktop awb-menu_v-stacked awb-menu_em-always\" style=\"--awb-font-size:var(--awb-typography3-font-size);--awb-line-height:var(--awb-typography3-line-height);--awb-margin-top:80px;--awb-margin-bottom:80px;--awb-text-transform:var(--awb-typography3-text-transform);--awb-bg:hsla(var(--awb-color5-h),var(--awb-color5-s),var(--awb-color5-l),calc(var(--awb-color5-a) - 95%));--awb-border-radius-top-left:5px;--awb-border-radius-top-right:5px;--awb-border-radius-bottom-right:5px;--awb-border-radius-bottom-left:5px;--awb-gap:40px;--awb-items-padding-top:20px;--awb-items-padding-bottom:20px;--awb-items-padding-left:25px;--awb-color:var(--awb-color8);--awb-letter-spacing:var(--awb-typography3-letter-spacing);--awb-active-color:var(--awb-color5);--awb-active-bg:hsla(var(--awb-color4-h),var(--awb-color4-s),var(--awb-color4-l),calc(var(--awb-color4-a) - 95%));--awb-submenu-sep-color:hsla(var(--awb-color2-h),var(--awb-color2-s),calc(var(--awb-color2-l) - 3%),var(--awb-color2-a));--awb-submenu-items-padding-top:15px;--awb-submenu-items-padding-bottom:15px;--awb-submenu-items-padding-left:35px;--awb-submenu-font-size:var(--awb-typography5-font-size);--awb-submenu-text-transform:var(--awb-typography5-text-transform);--awb-submenu-line-height:var(--awb-typography5-line-height);--awb-submenu-letter-spacing:var(--awb-typography5-letter-spacing);--awb-main-justify-content:flex-start;--awb-sub-justify-content:flex-start;--awb-mobile-nav-button-align-hor:center;--awb-mobile-bg:hsla(var(--awb-color5-h),var(--awb-color5-s),var(--awb-color5-l),calc(var(--awb-color5-a) - 98%));--awb-mobile-trigger-font-size:22px;--awb-mobile-trigger-color:var(--awb-color8);--awb-mobile-nav-trigger-bottom-margin:10px;--awb-mobile-font-size:var(--awb-typography3-font-size);--awb-mobile-text-transform:var(--awb-typography3-text-transform);--awb-mobile-line-height:var(--awb-typography3-line-height);--awb-mobile-letter-spacing:var(--awb-typography3-letter-spacing);--awb-mobile-justify:center;--awb-mobile-caret-left:auto;--awb-mobile-caret-right:0;--awb-fusion-font-family-typography:var(--awb-typography3-font-family);--awb-fusion-font-weight-typography:var(--awb-typography3-font-weight);--awb-fusion-font-style-typography:var(--awb-typography3-font-style);--awb-fusion-font-family-submenu-typography:var(--awb-typography5-font-family);--awb-fusion-font-weight-submenu-typography:var(--awb-typography5-font-weight);--awb-fusion-font-style-submenu-typography:var(--awb-typography5-font-style);--awb-fusion-font-family-mobile-typography:var(--awb-typography3-font-family);--awb-fusion-font-weight-mobile-typography:var(--awb-typography3-font-weight);--awb-fusion-font-style-mobile-typography:var(--awb-typography3-font-style);\" aria-label=\"utility functions\" data-breakpoint=\"640\" data-count=\"0\" data-transition-type=\"fade\" data-transition-time=\"300\"><button type=\"button\" class=\"awb-menu__m-toggle\" aria-expanded=\"false\" aria-controls=\"menu-%e5%8a%9f%e8%83%bd%e5%87%bd%e6%95%b0\"><span class=\"awb-menu__m-toggle-inner\"><span class=\"collapsed-nav-text\">Menu<\/span><span class=\"awb-menu__m-collapse-icon\"><span class=\"awb-menu__m-collapse-icon-open fa-bars fas\"><\/span><span class=\"awb-menu__m-collapse-icon-close fa-times fas\"><\/span><\/span><\/span><\/button><ul id=\"menu-%e5%8a%9f%e8%83%bd%e5%87%bd%e6%95%b0\" class=\"fusion-menu awb-menu__main-ul awb-menu__main-ul_column\"><li  id=\"menu-item-151\"  class=\"menu-item menu-item-type-post_type menu-item-object-page menu-item-151 awb-menu__li awb-menu__main-li awb-menu__main-li_regular\"  data-item-id=\"151\"><span class=\"awb-menu__main-background-default awb-menu__main-background-default_fade\"><\/span><span class=\"awb-menu__main-background-active awb-menu__main-background-active_fade\"><\/span><a  href=\"http:\/\/110.42.248.92\/onsite-learning-center\/en\/%e8%b5%84%e6%ba%90%e5%ba%93\/%e5%8a%9f%e8%83%bd%e5%87%bd%e6%95%b0%e6%a6%82%e8%bf%b0\/\" class=\"awb-menu__main-a awb-menu__main-a_regular\"><span class=\"menu-text\">Function overview<\/span><\/a><\/li><li  id=\"menu-item-283\"  class=\"menu-item menu-item-type-post_type menu-item-object-page menu-item-283 awb-menu__li awb-menu__main-li awb-menu__main-li_regular\"  data-item-id=\"283\"><span class=\"awb-menu__main-background-default awb-menu__main-background-default_fade\"><\/span><span class=\"awb-menu__main-background-active awb-menu__main-background-active_fade\"><\/span><a  href=\"http:\/\/110.42.248.92\/onsite-learning-center\/en\/%e8%b5%84%e6%ba%90%e5%ba%93\/%e5%8a%9f%e8%83%bd%e5%87%bd%e6%95%b0%e6%a6%82%e8%bf%b0\/%e5%8a%9f%e8%83%bd%e5%87%bd%e6%95%b0%e8%af%a6%e6%83%85-%e7%8e%af%e5%a2%83%e9%85%8d%e7%bd%ae\/\" class=\"awb-menu__main-a awb-menu__main-a_regular\"><span class=\"menu-text\">Utility Function Details \u2014 Environment Setup<\/span><\/a><\/li><li  id=\"menu-item-280\"  class=\"menu-item menu-item-type-post_type menu-item-object-page menu-item-280 awb-menu__li awb-menu__main-li awb-menu__main-li_regular\"  data-item-id=\"280\"><span class=\"awb-menu__main-background-default awb-menu__main-background-default_fade\"><\/span><span class=\"awb-menu__main-background-active awb-menu__main-background-active_fade\"><\/span><a  href=\"http:\/\/110.42.248.92\/onsite-learning-center\/en\/%e8%b5%84%e6%ba%90%e5%ba%93\/%e5%8a%9f%e8%83%bd%e5%87%bd%e6%95%b0%e6%a6%82%e8%bf%b0\/%e5%8a%9f%e8%83%bd%e5%87%bd%e6%95%b0%e8%af%a6%e6%83%85-%e6%95%b0%e6%8d%ae%e7%ad%9b%e9%80%89\/\" class=\"awb-menu__main-a awb-menu__main-a_regular\"><span class=\"menu-text\">Utility Function Details \u2014 Data Filtering<\/span><\/a><\/li><li  id=\"menu-item-281\"  class=\"menu-item menu-item-type-post_type menu-item-object-page menu-item-281 awb-menu__li awb-menu__main-li awb-menu__main-li_regular\"  data-item-id=\"281\"><span class=\"awb-menu__main-background-default awb-menu__main-background-default_fade\"><\/span><span class=\"awb-menu__main-background-active awb-menu__main-background-active_fade\"><\/span><a  href=\"http:\/\/110.42.248.92\/onsite-learning-center\/en\/%e8%b5%84%e6%ba%90%e5%ba%93\/%e5%8a%9f%e8%83%bd%e5%87%bd%e6%95%b0%e6%a6%82%e8%bf%b0\/%e5%8a%9f%e8%83%bd%e5%87%bd%e6%95%b0%e8%af%a6%e6%83%85-%e6%95%b0%e6%8d%ae%e5%88%92%e5%88%86\/\" class=\"awb-menu__main-a awb-menu__main-a_regular\"><span class=\"menu-text\">Utility Function Details \u2014 Data Split<\/span><\/a><\/li><li  id=\"menu-item-282\"  class=\"menu-item menu-item-type-post_type menu-item-object-page menu-item-282 awb-menu__li awb-menu__main-li awb-menu__main-li_regular\"  data-item-id=\"282\"><span class=\"awb-menu__main-background-default awb-menu__main-background-default_fade\"><\/span><span class=\"awb-menu__main-background-active awb-menu__main-background-active_fade\"><\/span><a  href=\"http:\/\/110.42.248.92\/onsite-learning-center\/en\/%e8%b5%84%e6%ba%90%e5%ba%93\/%e5%8a%9f%e8%83%bd%e5%87%bd%e6%95%b0%e6%a6%82%e8%bf%b0\/%e5%8a%9f%e8%83%bd%e5%87%bd%e6%95%b0%e8%af%a6%e6%83%85-%e6%a8%a1%e5%9e%8b%e8%af%84%e4%bc%b0\/\" class=\"awb-menu__main-a awb-menu__main-a_regular\"><span class=\"menu-text\">Utility Function Details \u2014 Model Evaluation<\/span><\/a><\/li><\/ul><\/nav><\/div><\/div><div class=\"fusion-layout-column fusion_builder_column fusion-builder-column-1 fusion_builder_column_3_4 3_4 fusion-flex-column\" style=\"--awb-bg-size:cover;--awb-width-large:75%;--awb-margin-top-large:0px;--awb-spacing-right-large:2.56%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:2.56%;--awb-width-medium:75%;--awb-order-medium:0;--awb-spacing-right-medium:2.56%;--awb-spacing-left-medium:2.56%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;\"><div class=\"fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column\"><div class=\"fusion-text fusion-text-2\" style=\"--awb-font-size:var(--awb-typography1-font-size);--awb-line-height:var(--awb-typography1-line-height);--awb-letter-spacing:var(--awb-typography1-letter-spacing);--awb-text-transform:var(--awb-typography1-text-transform);--awb-text-font-family:var(--awb-typography1-font-family);--awb-text-font-weight:var(--awb-typography1-font-weight);--awb-text-font-style:var(--awb-typography1-font-style);\"><p>Model Evaluation<\/p>\n<\/div><div class=\"fusion-text fusion-text-3\" style=\"--awb-content-alignment:left;--awb-font-size:18px;--awb-line-height:2;--awb-letter-spacing:var(--awb-typography3-letter-spacing);--awb-text-transform:var(--awb-typography3-text-transform);--awb-text-font-family:&quot;Outfit&quot;;--awb-text-font-style:normal;--awb-text-font-weight:400;\"><p style=\"text-align: left\">Model Evaluation is central to ensuring the quality and value of research results on the OnSite Learning Center. Standardized metrics and visualization tools help users understand model performance across datasets, including Precision, Recall, and F1 score. They also support parameter optimization, identification of bias or variance issues, and continuous model improvement.<\/p>\n<\/div><div class=\"fusion-separator fusion-full-width-sep\" style=\"align-self: center;margin-left: auto;margin-right: auto;margin-bottom:30px;width:100%;\"><div class=\"fusion-separator-border sep-double sep-solid\" style=\"--awb-height:20px;--awb-amount:20px;border-color:var(--awb-color3);border-top-width:1px;border-bottom-width:1px;\"><\/div><\/div><div class=\"fusion-content-boxes content-boxes columns row fusion-columns-1 fusion-columns-total-1 fusion-content-boxes-1 content-boxes-icon-with-title content-left\" style=\"--awb-hover-accent-color:var(--awb-color4);--awb-circle-hover-accent-color:var(--awb-color4);--awb-item-margin-bottom:40px;\" data-animationoffset=\"top-into-view\"><div style=\"--awb-backgroundcolor:rgba(255,255,255,0);\" class=\"fusion-column content-box-column content-box-column content-box-column-1 col-lg-12 col-md-12 col-sm-12 fusion-content-box-hover content-box-column-last content-box-column-last-in-row\"><div class=\"col content-box-wrapper content-wrapper link-area-link-icon content-icon-wrapper-yes icon-hover-animation-fade\" data-animationoffset=\"top-into-view\"><div class=\"heading heading-with-icon icon-left\"><div class=\"icon\"><span style=\"height:42px;width:42px;line-height:22px;border-color:rgba(255,255,255,0);border-width:1px;border-style:solid;background-color:var(--awb-color8);box-sizing:content-box;border-radius:50%;\"><i style=\"border-color:var(--awb-color8);border-width:1px;background-color:var(--awb-color7);box-sizing:content-box;height:40px;width:40px;line-height:40px;border-radius:50%;position:relative;top:auto;left:auto;margin:0;border-radius:50%;font-size:20px;\" aria-hidden=\"true\" class=\"fontawesome-icon fa-route fas circle-yes\"><\/i><\/span><\/div><h2 class=\"content-box-heading\" style=\"--h2_typography-font-size:24px;line-height:29px;\">Perception<\/h2><\/div><div class=\"fusion-clearfix\"><\/div><div class=\"content-container\">\n<p style=\"line-height: 2;font-size: 18px\">\nFor Perception, Model Evaluation metrics include mean average precision, Precision, and Recall. Note that not every task supports all of these metrics.\n<\/p>\n<\/div><\/div><\/div><div class=\"fusion-clearfix\"><\/div><\/div><div class=\"accordian fusion-accordian\" style=\"margin-top:-12%;--awb-margin-top:-12%;--awb-border-size:2px;--awb-icon-size:21px;--awb-content-font-size:16px;--awb-content-letter-spacing:0px;--awb-content-text-transform:var(--awb-typography2-text-transform);--awb-content-line-height:24px;--awb-icon-alignment:right;--awb-hover-color:#90f4d5;--awb-border-color:#90f4d5;--awb-background-color:#eff9f9;--awb-divider-color:var(--awb-color3);--awb-divider-hover-color:var(--awb-color3);--awb-icon-color:#141617;--awb-title-color:#141617;--awb-content-color:#141617;--awb-icon-box-color:#141617;--awb-toggle-hover-accent-color:#141617;--awb-toggle-active-accent-color:#141617;--awb-title-font-family:&quot;Red Hat Mono&quot;;--awb-title-font-weight:500;--awb-title-font-style:normal;--awb-title-font-size:16px;--awb-title-line-height:24px;--awb-title-text-transform:var(--awb-typography2-text-transform);--awb-content-font-family:&quot;Red Hat Mono&quot;;--awb-content-font-style:normal;--awb-content-font-weight:500;\"><div class=\"panel-group fusion-toggle-icon-right fusion-toggle-icon-unboxed\" id=\"accordion-87-1\"><div class=\"fusion-panel panel-default panel-7b1388fd59ee03509 fusion-toggle-no-divider fusion-toggle-boxed-mode\" style=\"--awb-title-color:var(--awb-color8);\"><div class=\"panel-heading\"><h4 class=\"panel-title toggle\" id=\"toggle_7b1388fd59ee03509\"><a aria-expanded=\"false\" aria-controls=\"7b1388fd59ee03509\" role=\"button\" data-toggle=\"collapse\" data-parent=\"#accordion-87-1\" data-target=\"#7b1388fd59ee03509\" href=\"#7b1388fd59ee03509\"><span class=\"fusion-toggle-icon-wrapper\" aria-hidden=\"true\"><i class=\"fa-fusion-box active-icon fa-arrow-alt-circle-down far\" aria-hidden=\"true\"><\/i><i class=\"fa-fusion-box inactive-icon fa-arrow-alt-circle-up far\" aria-hidden=\"true\"><\/i><\/span><span class=\"fusion-toggle-heading\">mAP(dataset, y_true, y_model)<\/span><\/a><\/h4><\/div><div id=\"7b1388fd59ee03509\" class=\"panel-collapse collapse\" aria-labelledby=\"toggle_7b1388fd59ee03509\"><div class=\"panel-body toggle-content fusion-clearfix\">\n<p>Calculate the results of the dataset data set after the perception task<strong data-spm-anchor-id=\"5176.28103460.0.i8.297c572cYuZUMq\">Mean Average Precision (mAP)<\/strong>. This is one of the most commonly used metrics in object detection tasks, and it takes into account the precision and recall of the model. mAP is often calculated at multiple overlapping thresholds to evaluate the model's consistent performance in different situations.<\/p>\n<\/div><\/div><\/div><div class=\"fusion-panel panel-default panel-606a4f790bce75959 fusion-toggle-no-divider fusion-toggle-boxed-mode\" style=\"--awb-title-color:var(--awb-color8);\"><div class=\"panel-heading\"><h4 class=\"panel-title toggle\" id=\"toggle_606a4f790bce75959\"><a aria-expanded=\"false\" aria-controls=\"606a4f790bce75959\" role=\"button\" data-toggle=\"collapse\" data-parent=\"#accordion-87-1\" data-target=\"#606a4f790bce75959\" href=\"#606a4f790bce75959\"><span class=\"fusion-toggle-icon-wrapper\" aria-hidden=\"true\"><i class=\"fa-fusion-box active-icon fa-arrow-alt-circle-down far\" aria-hidden=\"true\"><\/i><i class=\"fa-fusion-box inactive-icon fa-arrow-alt-circle-up far\" aria-hidden=\"true\"><\/i><\/span><span class=\"fusion-toggle-heading\">Precision(dataset, y_true, y_model)<\/span><\/a><\/h4><\/div><div id=\"606a4f790bce75959\" class=\"panel-collapse collapse\" aria-labelledby=\"toggle_606a4f790bce75959\"><div class=\"panel-body toggle-content fusion-clearfix\">\n<p>Calculate the results of the dataset data set for perception problems<strong data-spm-anchor-id=\"5176.28103460.0.i13.297c572cYuZUMq\">Precision.<\/strong>Precision is measured as the ratio of positive examples correctly identified by the model to all positive examples identified as true positives divided by the sum of true positives and false positives.<\/p>\n<\/div><\/div><\/div><div class=\"fusion-panel panel-default panel-64a80ca2c61ea8cb7 fusion-toggle-no-divider fusion-toggle-boxed-mode\" style=\"--awb-title-color:var(--awb-color8);\"><div class=\"panel-heading\"><h4 class=\"panel-title toggle\" id=\"toggle_64a80ca2c61ea8cb7\"><a aria-expanded=\"false\" aria-controls=\"64a80ca2c61ea8cb7\" role=\"button\" data-toggle=\"collapse\" data-parent=\"#accordion-87-1\" data-target=\"#64a80ca2c61ea8cb7\" href=\"#64a80ca2c61ea8cb7\"><span class=\"fusion-toggle-icon-wrapper\" aria-hidden=\"true\"><i class=\"fa-fusion-box active-icon fa-arrow-alt-circle-down far\" aria-hidden=\"true\"><\/i><i class=\"fa-fusion-box inactive-icon fa-arrow-alt-circle-up far\" aria-hidden=\"true\"><\/i><\/span><span class=\"fusion-toggle-heading\">Recall(dataset, y_true, y_model)<\/span><\/a><\/h4><\/div><div id=\"64a80ca2c61ea8cb7\" class=\"panel-collapse collapse\" aria-labelledby=\"toggle_64a80ca2c61ea8cb7\"><div class=\"panel-body toggle-content fusion-clearfix\">\n<p>Calculate the results of the dataset data set for perception problems<strong data-spm-anchor-id=\"5176.28103460.0.i11.297c572cYuZUMq\">Recall<\/strong><strong data-spm-anchor-id=\"5176.28103460.0.i13.297c572cYuZUMq\">\u3002<\/strong>Recall rate refers to the ratio of positive cases correctly identified by the model to all actual positive cases, that is, true positives divided by the sum of true positives and false negatives.<\/p>\n<\/div><\/div><\/div><div class=\"fusion-panel panel-default panel-b4a7839178f0e4fef fusion-toggle-no-divider fusion-toggle-boxed-mode\" style=\"--awb-title-color:var(--awb-color8);\"><div class=\"panel-heading\"><h4 class=\"panel-title toggle\" id=\"toggle_b4a7839178f0e4fef\"><a aria-expanded=\"false\" aria-controls=\"b4a7839178f0e4fef\" role=\"button\" data-toggle=\"collapse\" data-parent=\"#accordion-87-1\" data-target=\"#b4a7839178f0e4fef\" href=\"#b4a7839178f0e4fef\"><span class=\"fusion-toggle-icon-wrapper\" aria-hidden=\"true\"><i class=\"fa-fusion-box active-icon fa-arrow-alt-circle-down far\" aria-hidden=\"true\"><\/i><i class=\"fa-fusion-box inactive-icon fa-arrow-alt-circle-up far\" aria-hidden=\"true\"><\/i><\/span><span class=\"fusion-toggle-heading\">F1(dataset, y_true, y_model)<\/span><\/a><\/h4><\/div><div id=\"b4a7839178f0e4fef\" class=\"panel-collapse collapse\" aria-labelledby=\"toggle_b4a7839178f0e4fef\"><div class=\"panel-body toggle-content fusion-clearfix\">\n<p>Calculate the results of the dataset data set for perception problems<strong data-spm-anchor-id=\"5176.28103460.0.i16.297c572cYuZUMq\">F1 Score<\/strong><strong data-spm-anchor-id=\"5176.28103460.0.i13.297c572cYuZUMq\">\u3002<\/strong>The F1 score is the harmonic mean of precision and recall, providing a single metric that balances the relationship between the two.<\/p>\n<\/div><\/div><\/div><div class=\"fusion-panel panel-default panel-207dd81ba66ad3ca5 fusion-toggle-no-divider fusion-toggle-boxed-mode\" style=\"--awb-title-color:var(--awb-color8);\"><div class=\"panel-heading\"><h4 class=\"panel-title toggle\" id=\"toggle_207dd81ba66ad3ca5\"><a aria-expanded=\"false\" aria-controls=\"207dd81ba66ad3ca5\" role=\"button\" data-toggle=\"collapse\" data-parent=\"#accordion-87-1\" data-target=\"#207dd81ba66ad3ca5\" href=\"#207dd81ba66ad3ca5\"><span class=\"fusion-toggle-icon-wrapper\" aria-hidden=\"true\"><i class=\"fa-fusion-box active-icon fa-arrow-alt-circle-down far\" aria-hidden=\"true\"><\/i><i class=\"fa-fusion-box inactive-icon fa-arrow-alt-circle-up far\" aria-hidden=\"true\"><\/i><\/span><span class=\"fusion-toggle-heading\">IoU(dataset, y_true, y_model)<\/span><\/a><\/h4><\/div><div id=\"207dd81ba66ad3ca5\" class=\"panel-collapse collapse\" aria-labelledby=\"toggle_207dd81ba66ad3ca5\"><div class=\"panel-body toggle-content fusion-clearfix\">\n<p>Calculate the results of the dataset data set for perception problems<strong data-spm-anchor-id=\"5176.28103460.0.i27.297c572cYuZUMq\">Overlap Threshold.<\/strong>In target detection, an overlap threshold is set to determine whether the matching degree between the predicted box and the real box is sufficient. IoU (Intersection over Union) is usually used as a metric.<\/p>\n<\/div><\/div><\/div><div class=\"fusion-panel panel-default panel-d86dcb83b0f49e62f fusion-toggle-no-divider fusion-toggle-boxed-mode\" style=\"--awb-title-color:var(--awb-color8);\"><div class=\"panel-heading\"><h4 class=\"panel-title toggle\" id=\"toggle_d86dcb83b0f49e62f\"><a aria-expanded=\"false\" aria-controls=\"d86dcb83b0f49e62f\" role=\"button\" data-toggle=\"collapse\" data-parent=\"#accordion-87-1\" data-target=\"#d86dcb83b0f49e62f\" href=\"#d86dcb83b0f49e62f\"><span class=\"fusion-toggle-icon-wrapper\" aria-hidden=\"true\"><i class=\"fa-fusion-box active-icon fa-arrow-alt-circle-down far\" aria-hidden=\"true\"><\/i><i class=\"fa-fusion-box inactive-icon fa-arrow-alt-circle-up far\" aria-hidden=\"true\"><\/i><\/span><span class=\"fusion-toggle-heading\">mIoU(dataset, y_true, y_model)<\/span><\/a><\/h4><\/div><div id=\"d86dcb83b0f49e62f\" class=\"panel-collapse collapse\" aria-labelledby=\"toggle_d86dcb83b0f49e62f\"><div class=\"panel-body toggle-content fusion-clearfix\">\n<p>Calculate the results of the dataset data set for perception problems<strong data-spm-anchor-id=\"5176.28103460.0.i15.297c572cYuZUMq\">Mean Intersection over Union (mIoU).<\/strong>In semantic segmentation tasks, mIoU is used to evaluate the degree of overlap between predicted pixels and actual pixels, which is the average of the ratio of the intersection and union of the predicted area and the actual area.<\/p>\n<\/div><\/div><\/div><\/div><\/div><div class=\"fusion-separator fusion-full-width-sep\" style=\"align-self: center;margin-left: auto;margin-right: auto;margin-bottom:30px;width:100%;\"><div class=\"fusion-separator-border sep-single sep-solid\" style=\"--awb-height:20px;--awb-amount:20px;border-color:var(--awb-color3);border-top-width:1px;\"><\/div><\/div><div class=\"fusion-content-boxes content-boxes columns row fusion-columns-1 fusion-columns-total-1 fusion-content-boxes-2 content-boxes-icon-with-title content-left\" style=\"--awb-hover-accent-color:var(--awb-color4);--awb-circle-hover-accent-color:var(--awb-color4);--awb-item-margin-bottom:40px;\" data-animationoffset=\"top-into-view\"><div style=\"--awb-backgroundcolor:rgba(255,255,255,0);\" class=\"fusion-column content-box-column content-box-column content-box-column-1 col-lg-12 col-md-12 col-sm-12 fusion-content-box-hover content-box-column-last content-box-column-last-in-row\"><div class=\"col content-box-wrapper content-wrapper link-area-link-icon content-icon-wrapper-yes icon-hover-animation-fade\" data-animationoffset=\"top-into-view\"><div class=\"heading heading-with-icon icon-left\"><div class=\"icon\"><span style=\"height:42px;width:42px;line-height:22px;border-color:rgba(255,255,255,0);border-width:1px;border-style:solid;background-color:var(--awb-color8);box-sizing:content-box;border-radius:50%;\"><i style=\"border-color:var(--awb-color8);border-width:1px;background-color:var(--awb-color7);box-sizing:content-box;height:40px;width:40px;line-height:40px;border-radius:50%;position:relative;top:auto;left:auto;margin:0;border-radius:50%;font-size:20px;\" aria-hidden=\"true\" class=\"fontawesome-icon fa-route fas circle-yes\"><\/i><\/span><\/div><h2 class=\"content-box-heading\" style=\"--h2_typography-font-size:24px;line-height:29px;\">Prediction<\/h2><\/div><div class=\"fusion-clearfix\"><\/div><div class=\"content-container\">\n<p style=\"line-height: 2;font-size: 18px\">\nFor Prediction, Model Evaluation metrics include ADE, FDE, MR, and others.\n<\/p>\n<\/div><\/div><\/div><div class=\"fusion-clearfix\"><\/div><\/div><div class=\"accordian fusion-accordian\" style=\"margin-top:-12%;--awb-margin-top:-12%;--awb-border-size:2px;--awb-icon-size:21px;--awb-content-font-size:16px;--awb-content-letter-spacing:0px;--awb-content-text-transform:var(--awb-typography2-text-transform);--awb-content-line-height:24px;--awb-icon-alignment:right;--awb-hover-color:#90f4d5;--awb-border-color:#90f4d5;--awb-background-color:#eff9f9;--awb-divider-color:var(--awb-color3);--awb-divider-hover-color:var(--awb-color3);--awb-icon-color:#141617;--awb-title-color:#141617;--awb-content-color:#141617;--awb-icon-box-color:#141617;--awb-toggle-hover-accent-color:#141617;--awb-toggle-active-accent-color:#141617;--awb-title-font-family:&quot;Red Hat Mono&quot;;--awb-title-font-weight:500;--awb-title-font-style:normal;--awb-title-font-size:16px;--awb-title-line-height:24px;--awb-title-text-transform:var(--awb-typography2-text-transform);--awb-content-font-family:&quot;Red Hat Mono&quot;;--awb-content-font-style:normal;--awb-content-font-weight:500;\"><div class=\"panel-group fusion-toggle-icon-right fusion-toggle-icon-unboxed\" id=\"accordion-87-2\"><div class=\"fusion-panel panel-default panel-c85cda4213d8de33c fusion-toggle-no-divider fusion-toggle-boxed-mode\" style=\"--awb-title-color:var(--awb-color8);\"><div class=\"panel-heading\"><h4 class=\"panel-title toggle\" id=\"toggle_c85cda4213d8de33c\"><a aria-expanded=\"false\" aria-controls=\"c85cda4213d8de33c\" role=\"button\" data-toggle=\"collapse\" data-parent=\"#accordion-87-2\" data-target=\"#c85cda4213d8de33c\" href=\"#c85cda4213d8de33c\"><span class=\"fusion-toggle-icon-wrapper\" aria-hidden=\"true\"><i class=\"fa-fusion-box active-icon fa-arrow-alt-circle-down far\" aria-hidden=\"true\"><\/i><i class=\"fa-fusion-box inactive-icon fa-arrow-alt-circle-up far\" aria-hidden=\"true\"><\/i><\/span><span class=\"fusion-toggle-heading\">RMSE(dataset, y_true, y_model)<\/span><\/a><\/h4><\/div><div id=\"c85cda4213d8de33c\" class=\"panel-collapse collapse\" aria-labelledby=\"toggle_c85cda4213d8de33c\"><div class=\"panel-body toggle-content fusion-clearfix\">\n<p>Calculate the results of the dataset data set for prediction tasks<strong data-spm-anchor-id=\"5176.28103460.0.i33.297c572cYuZUMq\">Root Mean Square Error (RMSE)<\/strong>: This is a metric widely used in regression tasks that measures the square root of the average squared difference between the predicted value and the true value. In trajectory prediction, it represents the square root of the average Euclidean distance between predicted trajectory points and actual trajectory points.<\/p>\n<\/div><\/div><\/div><div class=\"fusion-panel panel-default panel-757e60f6091b6a2f5 fusion-toggle-no-divider fusion-toggle-boxed-mode\" style=\"--awb-title-color:var(--awb-color8);\"><div class=\"panel-heading\"><h4 class=\"panel-title toggle\" id=\"toggle_757e60f6091b6a2f5\"><a aria-expanded=\"false\" aria-controls=\"757e60f6091b6a2f5\" role=\"button\" data-toggle=\"collapse\" data-parent=\"#accordion-87-2\" data-target=\"#757e60f6091b6a2f5\" href=\"#757e60f6091b6a2f5\"><span class=\"fusion-toggle-icon-wrapper\" aria-hidden=\"true\"><i class=\"fa-fusion-box active-icon fa-arrow-alt-circle-down far\" aria-hidden=\"true\"><\/i><i class=\"fa-fusion-box inactive-icon fa-arrow-alt-circle-up far\" aria-hidden=\"true\"><\/i><\/span><span class=\"fusion-toggle-heading\">NLL(dataset, y_true, y_model)<\/span><\/a><\/h4><\/div><div id=\"757e60f6091b6a2f5\" class=\"panel-collapse collapse\" aria-labelledby=\"toggle_757e60f6091b6a2f5\"><div class=\"panel-body toggle-content fusion-clearfix\">\n<p>Calculate the results of the dataset data set for prediction tasks<strong data-spm-anchor-id=\"5176.28103460.0.i36.297c572cYuZUMq\">Negative Log-Likelihood (NLL).<\/strong>This metric is primarily used in the evaluation of probabilistic models, and it measures the difference between the probability distribution predicted by the model and the actual observations. In trajectory prediction, NLL focuses on evaluating the model's probability estimation accuracy for trajectory prediction, especially for models involving multi-modal prediction.<\/p>\n<\/div><\/div><\/div><div class=\"fusion-panel panel-default panel-82695b3c8ebac25a4 fusion-toggle-no-divider fusion-toggle-boxed-mode\" style=\"--awb-title-color:var(--awb-color8);\"><div class=\"panel-heading\"><h4 class=\"panel-title toggle\" id=\"toggle_82695b3c8ebac25a4\"><a aria-expanded=\"false\" aria-controls=\"82695b3c8ebac25a4\" role=\"button\" data-toggle=\"collapse\" data-parent=\"#accordion-87-2\" data-target=\"#82695b3c8ebac25a4\" href=\"#82695b3c8ebac25a4\"><span class=\"fusion-toggle-icon-wrapper\" aria-hidden=\"true\"><i class=\"fa-fusion-box active-icon fa-arrow-alt-circle-down far\" aria-hidden=\"true\"><\/i><i class=\"fa-fusion-box inactive-icon fa-arrow-alt-circle-up far\" aria-hidden=\"true\"><\/i><\/span><span class=\"fusion-toggle-heading\">ADE(dataset, y_true, y_model)<\/span><\/a><\/h4><\/div><div id=\"82695b3c8ebac25a4\" class=\"panel-collapse collapse\" aria-labelledby=\"toggle_82695b3c8ebac25a4\"><div class=\"panel-body toggle-content fusion-clearfix\">\n<p>Calculate the results of the dataset data set for prediction tasks<strong data-spm-anchor-id=\"5176.28103460.0.i38.297c572cYuZUMq\">Average Displacement Error (ADE).<\/strong>ADE calculates the average Euclidean distance between each predicted point and the actual point in the entire predicted trajectory. It provides an overall error measure indicating how much the predicted trajectory deviates from the true trajectory on average over the entire sequence.<\/p>\n<\/div><\/div><\/div><div class=\"fusion-panel panel-default panel-76a60c76ef52dc69a fusion-toggle-no-divider fusion-toggle-boxed-mode\" style=\"--awb-title-color:var(--awb-color8);\"><div class=\"panel-heading\"><h4 class=\"panel-title toggle\" id=\"toggle_76a60c76ef52dc69a\"><a aria-expanded=\"false\" aria-controls=\"76a60c76ef52dc69a\" role=\"button\" data-toggle=\"collapse\" data-parent=\"#accordion-87-2\" data-target=\"#76a60c76ef52dc69a\" href=\"#76a60c76ef52dc69a\"><span class=\"fusion-toggle-icon-wrapper\" aria-hidden=\"true\"><i class=\"fa-fusion-box active-icon fa-arrow-alt-circle-down far\" aria-hidden=\"true\"><\/i><i class=\"fa-fusion-box inactive-icon fa-arrow-alt-circle-up far\" aria-hidden=\"true\"><\/i><\/span><span class=\"fusion-toggle-heading\">FDE(dataset, y_true, y_model)<\/span><\/a><\/h4><\/div><div id=\"76a60c76ef52dc69a\" class=\"panel-collapse collapse\" aria-labelledby=\"toggle_76a60c76ef52dc69a\"><div class=\"panel-body toggle-content fusion-clearfix\">\n<p>Calculate the results of the dataset data set for prediction tasks<strong data-spm-anchor-id=\"5176.28103460.0.i40.297c572cYuZUMq\">Final Displacement Error (FDE).<\/strong>FDE specifically focuses on the Euclidean distance between the last point of the predicted trajectory and the end point of the actual trajectory. It measures the accuracy of the model at the predicted end moment, which is especially important for scenarios that require accurate stopping points.<\/p>\n<\/div><\/div><\/div><div class=\"fusion-panel panel-default panel-aea3fa7304d27f5eb fusion-toggle-no-divider fusion-toggle-boxed-mode\" style=\"--awb-title-color:var(--awb-color8);\"><div class=\"panel-heading\"><h4 class=\"panel-title toggle\" id=\"toggle_aea3fa7304d27f5eb\"><a aria-expanded=\"false\" aria-controls=\"aea3fa7304d27f5eb\" role=\"button\" data-toggle=\"collapse\" data-parent=\"#accordion-87-2\" data-target=\"#aea3fa7304d27f5eb\" href=\"#aea3fa7304d27f5eb\"><span class=\"fusion-toggle-icon-wrapper\" aria-hidden=\"true\"><i class=\"fa-fusion-box active-icon fa-arrow-alt-circle-down far\" aria-hidden=\"true\"><\/i><i class=\"fa-fusion-box inactive-icon fa-arrow-alt-circle-up far\" aria-hidden=\"true\"><\/i><\/span><span class=\"fusion-toggle-heading\">MR(dataset, y_true, y_model)<\/span><\/a><\/h4><\/div><div id=\"aea3fa7304d27f5eb\" class=\"panel-collapse collapse\" aria-labelledby=\"toggle_aea3fa7304d27f5eb\"><div class=\"panel-body toggle-content fusion-clearfix\">\n<p>Calculate the results of the dataset data set for prediction tasks<strong data-spm-anchor-id=\"5176.28103460.0.i42.297c572cYuZUMq\">Miss Rate (MR).<\/strong>MR calculates the ratio of the Euclidean distance between the end point of the predicted trajectory and the end point of the actual trajectory that is greater than a given threshold (usually 2.0 meters). It reveals the overall accuracy of the model in predicting the end position of the trajectory.<\/p>\n<\/div><\/div><\/div><div class=\"fusion-panel panel-default panel-4b29dc69e5c77fa87 fusion-toggle-no-divider fusion-toggle-boxed-mode\" style=\"--awb-title-color:var(--awb-color8);\"><div class=\"panel-heading\"><h4 class=\"panel-title toggle\" id=\"toggle_4b29dc69e5c77fa87\"><a aria-expanded=\"false\" aria-controls=\"4b29dc69e5c77fa87\" role=\"button\" data-toggle=\"collapse\" data-parent=\"#accordion-87-2\" data-target=\"#4b29dc69e5c77fa87\" href=\"#4b29dc69e5c77fa87\"><span class=\"fusion-toggle-icon-wrapper\" aria-hidden=\"true\"><i class=\"fa-fusion-box active-icon fa-arrow-alt-circle-down far\" aria-hidden=\"true\"><\/i><i class=\"fa-fusion-box inactive-icon fa-arrow-alt-circle-up far\" aria-hidden=\"true\"><\/i><\/span><span class=\"fusion-toggle-heading\">OffRoadRate(dataset, y_true, y_model)<\/span><\/a><\/h4><\/div><div id=\"4b29dc69e5c77fa87\" class=\"panel-collapse collapse\" aria-labelledby=\"toggle_4b29dc69e5c77fa87\"><div class=\"panel-body toggle-content fusion-clearfix\">\n<p>Calculate the results of the dataset data set for prediction tasks<strong data-spm-anchor-id=\"5176.28103460.0.i43.297c572cYuZUMq\">Off-Road Rate (OffRoadRate)<\/strong>: When the dataset contains map information, this metric counts the proportion of predicted trajectories that are not on a valid road network. It evaluates the model's performance in adhering to road rules.<\/p>\n<\/div><\/div><\/div><div class=\"fusion-panel panel-default panel-b55aa07ba3563793e fusion-toggle-no-divider fusion-toggle-boxed-mode\" style=\"--awb-title-color:var(--awb-color8);\"><div class=\"panel-heading\"><h4 class=\"panel-title toggle\" id=\"toggle_b55aa07ba3563793e\"><a aria-expanded=\"false\" aria-controls=\"b55aa07ba3563793e\" role=\"button\" data-toggle=\"collapse\" data-parent=\"#accordion-87-2\" data-target=\"#b55aa07ba3563793e\" href=\"#b55aa07ba3563793e\"><span class=\"fusion-toggle-icon-wrapper\" aria-hidden=\"true\"><i class=\"fa-fusion-box active-icon fa-arrow-alt-circle-down far\" aria-hidden=\"true\"><\/i><i class=\"fa-fusion-box inactive-icon fa-arrow-alt-circle-up far\" aria-hidden=\"true\"><\/i><\/span><span class=\"fusion-toggle-heading\">mAPH(dataset, y_true, y_model)<\/span><\/a><\/h4><\/div><div id=\"b55aa07ba3563793e\" class=\"panel-collapse collapse\" aria-labelledby=\"toggle_b55aa07ba3563793e\"><div class=\"panel-body toggle-content fusion-clearfix\">\n<p>Calculate the results of the dataset data set for prediction tasks<strong data-spm-anchor-id=\"5176.28103460.0.i46.297c572cYuZUMq\">Mean average precision weighted by heading (mAPH)<\/strong>: Derived from the Waymo data set, mAPH considers the predicted heading angle (direction) and position accuracy, and evaluates the overall performance of the model by calculating the area under the Precision-Recall curve. At the same time, the predicted heading angle is used as a weighting factor, which is suitable for tasks that require accurate direction prediction.<\/p>\n<\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/div>","protected":false},"excerpt":{"rendered":"","protected":false},"author":5,"featured_media":0,"parent":78,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"100-width.php","meta":{"inline_featured_image":false,"iawp_total_views":78,"footnotes":""},"class_list":["post-87","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"http:\/\/110.42.248.92\/onsite-learning-center\/en\/wp-json\/wp\/v2\/pages\/87"}],"collection":[{"href":"http:\/\/110.42.248.92\/onsite-learning-center\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/110.42.248.92\/onsite-learning-center\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/110.42.248.92\/onsite-learning-center\/en\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"http:\/\/110.42.248.92\/onsite-learning-center\/en\/wp-json\/wp\/v2\/comments?post=87"}],"version-history":[{"count":8,"href":"http:\/\/110.42.248.92\/onsite-learning-center\/en\/wp-json\/wp\/v2\/pages\/87\/revisions"}],"predecessor-version":[{"id":488,"href":"http:\/\/110.42.248.92\/onsite-learning-center\/en\/wp-json\/wp\/v2\/pages\/87\/revisions\/488"}],"up":[{"embeddable":true,"href":"http:\/\/110.42.248.92\/onsite-learning-center\/en\/wp-json\/wp\/v2\/pages\/78"}],"wp:attachment":[{"href":"http:\/\/110.42.248.92\/onsite-learning-center\/en\/wp-json\/wp\/v2\/media?parent=87"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}