{"payload":{"allShortcutsEnabled":true,"fileTree":{"":{"items":[{"name":"configs","path":"configs","contentType":"directory"},{"name":"demo","path":"demo","contentType":"directory"},{"name":"denseclip","path":"denseclip","contentType":"directory"},{"name":"docker","path":"docker","contentType":"directory"},{"name":"extra_function","path":"extra_function","contentType":"directory"},{"name":"maskrcnn_benchmark","path":"maskrcnn_benchmark","contentType":"directory"},{"name":".flake8","path":".flake8","contentType":"file"},{"name":".gitignore","path":".gitignore","contentType":"file"},{"name":"11111111111.py","path":"11111111111.py","contentType":"file"},{"name":"ABSTRACTIONS.md","path":"ABSTRACTIONS.md","contentType":"file"},{"name":"CODE_OF_CONDUCT.md","path":"CODE_OF_CONDUCT.md","contentType":"file"},{"name":"DATASET.md","path":"DATASET.md","contentType":"file"},{"name":"GQA_200_ID_Info.json","path":"GQA_200_ID_Info.json","contentType":"file"},{"name":"GQA_200_Test.json","path":"GQA_200_Test.json","contentType":"file"},{"name":"INSTALL.md","path":"INSTALL.md","contentType":"file"},{"name":"LICENSE","path":"LICENSE","contentType":"file"},{"name":"README.md","path":"README.md","contentType":"file"},{"name":"Setup.ipynb","path":"Setup.ipynb","contentType":"file"},{"name":"TROUBLESHOOTING.md","path":"TROUBLESHOOTING.md","contentType":"file"},{"name":"apex-master.zip","path":"apex-master.zip","contentType":"file"},{"name":"cmd.cache","path":"cmd.cache","contentType":"file"},{"name":"cocoapi-master.zip","path":"cocoapi-master.zip","contentType":"file"},{"name":"requirements.txt","path":"requirements.txt","contentType":"file"},{"name":"run_VG.sh","path":"run_VG.sh","contentType":"file"},{"name":"setup.py","path":"setup.py","contentType":"file"},{"name":"test_binary.py","path":"test_binary.py","contentType":"file"},{"name":"test_main.py","path":"test_main.py","contentType":"file"},{"name":"visualize_sgcl.py","path":"visualize_sgcl.py","contentType":"file"}],"totalCount":28}},"fileTreeProcessingTime":3.003224,"foldersToFetch":[],"repo":{"id":678224775,"defaultBranch":"main","name":"EICR","ownerLogin":"myukzzz","currentUserCanPush":true,"isFork":false,"isEmpty":false,"createdAt":"2023-08-14T11:56:57.000+08:00","ownerAvatar":"https://avatars.githubusercontent.com/u/68174757?v=4","public":true,"private":false,"isOrgOwned":false},"symbolsExpanded":true,"treeExpanded":false,"refInfo":{"name":"main","listCacheKey":"v0:1708998767.0","canEdit":true,"refType":"branch","currentOid":"e16a9334c1679a0a89e5830fe3ee027cb9c31946"},"path":"README.md","currentUser":{"id":68174757,"login":"myukzzz","userEmail":"[email protected]"},"blob":{"rawLines":null,"stylingDirectives":null,"csv":null,"csvError":null,"dependabotInfo":{"showConfigurationBanner":null,"configFilePath":null,"networkDependabotPath":"/myukzzz/EICR/network/updates","dismissConfigurationNoticePath":"/settings/dismiss-notice/dependabot_configuration_notice","configurationNoticeDismissed":false},"displayName":"README.md","displayUrl":"https://github.com/myukzzz/EICR/blob/main/README.md?raw=true","headerInfo":{"blobSize":"6.18 KB","deleteTooltip":"Delete this file","editTooltip":"Edit this file","deleteInfo":{"deleteTooltip":"Delete this file"},"editInfo":{"editTooltip":"Edit this file"},"ghDesktopPath":"https://desktop.github.com","isGitLfs":false,"gitLfsPath":null,"onBranch":true,"shortPath":"524bd51","siteNavLoginPath":"/login?return_to=https%3A%2F%2Fgithub.com%2Fmyukzzz%2FEICR%2Fblob%2Fmain%2FREADME.md","isCSV":false,"isRichtext":true,"toc":[{"level":1,"text":"Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation in Pytorch","anchor":"environment-invariant-curriculum-relation-learning-for-fine-grained-scene-graph-generation-in-pytorch","htmlText":"Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation in Pytorch"},{"level":2,"text":"Installation","anchor":"installation","htmlText":"Installation"},{"level":2,"text":"Dataset","anchor":"dataset","htmlText":"Dataset"},{"level":2,"text":"Pretrained Models","anchor":"pretrained-models","htmlText":"Pretrained Models"},{"level":2,"text":"Perform training on Scene Graph Generation","anchor":"perform-training-on-scene-graph-generation","htmlText":"Perform training on Scene Graph Generation"},{"level":3,"text":"Set the dataset path","anchor":"set-the-dataset-path","htmlText":"Set the dataset path"},{"level":3,"text":"Choose a dataset","anchor":"choose-a-dataset","htmlText":"Choose a dataset"},{"level":3,"text":"Choose a task","anchor":"choose-a-task","htmlText":"Choose a task"},{"level":3,"text":"Choose your model","anchor":"choose-your-model","htmlText":"Choose your model"},{"level":3,"text":"Choose your Encoder","anchor":"choose-your-encoder","htmlText":"Choose your Encoder"},{"level":3,"text":"Examples of the Training Command","anchor":"examples-of-the-training-command","htmlText":"Examples of the Training Command"},{"level":2,"text":"Evaluation","anchor":"evaluation","htmlText":"Evaluation"},{"level":2,"text":"Citation","anchor":"citation","htmlText":"Citation"},{"level":2,"text":"Acknowledgment","anchor":"acknowledgment","htmlText":"Acknowledgment"}],"lineInfo":{"truncatedLoc":"125","truncatedSloc":"88"},"mode":"file"},"image":false,"isCodeownersFile":null,"isPlain":false,"isValidLegacyIssueTemplate":false,"issueTemplateHelpUrl":"https://docs.github.com/articles/about-issue-and-pull-request-templates","issueTemplate":null,"discussionTemplate":null,"language":"Markdown","languageID":222,"large":false,"loggedIn":true,"planSupportInfo":{"repoIsFork":null,"repoOwnedByCurrentUser":null,"requestFullPath":"/myukzzz/EICR/blob/main/README.md","showFreeOrgGatedFeatureMessage":null,"showPlanSupportBanner":null,"upgradeDataAttributes":null,"upgradePath":null},"publishBannersInfo":{"dismissActionNoticePath":"/settings/dismiss-notice/publish_action_from_dockerfile","releasePath":"/myukzzz/EICR/releases/new?marketplace=true","showPublishActionBanner":false},"rawBlobUrl":"https://github.com/myukzzz/EICR/raw/main/README.md","renderImageOrRaw":false,"richText":"<article class="markdown-body entry-content container-lg" itemprop="text"><div class="markdown-heading" dir="auto"><h1 tabindex="-1" class="heading-element" dir="auto">Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation in Pytorch<a id="user-content-environment-invariant-curriculum-relation-learning-for-fine-grained-scene-graph-generation-in-pytorch" class="anchor-element" aria-label="Permalink: Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation in Pytorch" href="#environment-invariant-curriculum-relation-learning-for-fine-grained-scene-graph-generation-in-pytorch"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z">\n<div class="markdown-heading" dir="auto"><h2 tabindex="-1" class="heading-element" dir="auto">Installation<a id="user-content-installation" class="anchor-element" aria-label="Permalink: Installation" href="#installation"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z">\n<p dir="auto">Check <a href="/myukzzz/EICR/blob/main/INSTALL.md">INSTALL.md for installation instructions, the recommended configuration is cuda-10.1 & pytorch-1.7.1.
\n<div class="markdown-heading" dir="auto"><h2 tabindex="-1" class="heading-element" dir="auto">Dataset<a id="user-content-dataset" class="anchor-element" aria-label="Permalink: Dataset" href="#dataset"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z">\n<p dir="auto">Check <a href="/myukzzz/EICR/blob/main/DATASET.md">DATASET.md for instructions of dataset preprocessing (VG & GQA).\n<div class="markdown-heading" dir="auto"><h2 tabindex="-1" class="heading-element" dir="auto">Pretrained Models<a id="user-content-pretrained-models" class="anchor-element" aria-label="Permalink: Pretrained Models" href="#pretrained-models"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z">\n<p dir="auto">For VG dataset, the pretrained object detector we used is provided by <a href="https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch\">Scene-Graph-Benchmark\n<div class="markdown-heading" dir="auto"><h2 tabindex="-1" class="heading-element" dir="auto">Perform training on Scene Graph Generation<a id="user-content-perform-training-on-scene-graph-generation" class="anchor-element" aria-label="Permalink: Perform training on Scene Graph Generation" href="#perform-training-on-scene-graph-generation"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z">\n<div class="markdown-heading" dir="auto"><h3 tabindex="-1" class="heading-element" dir="auto">Set the dataset path<a id="user-content-set-the-dataset-path" class="anchor-element" aria-label="Permalink: Set the dataset path" href="#set-the-dataset-path"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z">\n<p dir="auto">First, organize all the files like this:\n<div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" data-snippet-clipboard-copy-content="datasets\n |-- vg\n |--detector_model\n |--pretrained_faster_rcnn\n |--model_final.pth\n |--GQA\n |--model_final_from_vg.pth \n |--glove\n |--.... (glove files, will autoly download)\n |--VG_100K\n |--.... (images)\n |--VG-SGG-with-attri.h5 \n |--VG-SGG-dicts-with-attri.json\n |--image_data.json \n |--gqa\n |--images\n |--.... (images)\n |--GQA_200_ID_Info.json\n |--GQA_200_Train.json\n |--GQA_200_Test.json">datasets\n <span class="pl-k">|-- vg\n <span class="pl-k">|--detector_model\n <span class="pl-k">|--pretrained_faster_rcnn\n <span class="pl-k">|--model_final.pth\n <span class="pl-k">|--GQA\n <span class="pl-k">|--model_final_from_vg.pth \n <span class="pl-k">|--glove\n <span class="pl-k">|--.... (glove files, will autoly download)\n <span class="pl-k">|--VG_100K\n <span class="pl-k">|--.... (images)\n <span class="pl-k">|--VG-SGG-with-attri.h5 \n <span class="pl-k">|--VG-SGG-dicts-with-attri.json\n <span class="pl-k">|--image_data.json \n <span class="pl-k">|--gqa\n <span class="pl-k">|--images\n <span class="pl-k">|--.... (images)\n <span class="pl-k">|--GQA_200_ID_Info.json\n <span class="pl-k">|--GQA_200_Train.json\n <span class="pl-k">|--GQA_200_Test.json\n<div class="markdown-heading" dir="auto"><h3 tabindex="-1" class="heading-element" dir="auto">Choose a dataset<a id="user-content-choose-a-dataset" class="anchor-element" aria-label="Permalink: Choose a dataset" href="#choose-a-dataset"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z">\n<p dir="auto">You can choose the training/testing dataset by setting the following parameter:\n<div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" data-snippet-clipboard-copy-content="GLOBAL_SETTING.DATASET_CHOICE 'VG' #['VG', 'GQA']">
GLOBAL_SETTING.DATASET_CHOICE <span class="pl-s"><span class="pl-pds">'VG<span class="pl-pds">' <span class="pl-c"><span class="pl-c">#['VG', 'GQA']\n<div class="markdown-heading" dir="auto"><h3 tabindex="-1" class="heading-element" dir="auto">Choose a task<a id="user-content-choose-a-task" class="anchor-element" aria-label="Permalink: Choose a task" href="#choose-a-task"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z">\n<p dir="auto">To comprehensively evaluate the performance, we follow three conventional tasks: 1) Predicate Classification (PredCls) predicts the relationships of all the pairwise objects by employing the given ground-truth bounding boxes and classes; 2) Scene Graph Classification (SGCls) predicts the objects classes and their pairwise relationships by employing the given ground-truth object bounding boxes; and 3) Scene Graph Detection (SGDet) detects all the objects in an image, and predicts their bounding boxes, classes, and pairwise relationships.\n<p dir="auto">For Predicate Classification (PredCls), you need to set:\n<div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" data-snippet-clipboard-copy-content="MODEL.ROI_RELATION_HEAD.USE_GT_BOX True MODEL.ROI_RELATION_HEAD.USE_GT_OBJECT_LABEL True">
MODEL.ROI_RELATION_HEAD.USE_GT_BOX True MODEL.ROI_RELATION_HEAD.USE_GT_OBJECT_LABEL True\n<p dir="auto">For Scene Graph Classification (SGCls):\n<div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" data-snippet-clipboard-copy-content="MODEL.ROI_RELATION_HEAD.USE_GT_BOX True MODEL.ROI_RELATION_HEAD.USE_GT_OBJECT_LABEL False">
MODEL.ROI_RELATION_HEAD.USE_GT_BOX True MODEL.ROI_RELATION_HEAD.USE_GT_OBJECT_LABEL False\n<p dir="auto">For Scene Graph Detection (SGDet):\n<div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" data-snippet-clipboard-copy-content="MODEL.ROI_RELATION_HEAD.USE_GT_BOX False MODEL.ROI_RELATION_HEAD.USE_GT_OBJECT_LABEL False">
MODEL.ROI_RELATION_HEAD.USE_GT_BOX False MODEL.ROI_RELATION_HEAD.USE_GT_OBJECT_LABEL False\n<div class="markdown-heading" dir="auto"><h3 tabindex="-1" class="heading-element" dir="auto">Choose your model<a id="user-content-choose-your-model" class="anchor-element" aria-label="Permalink: Choose your model" href="#choose-your-model"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z">\n<p dir="auto">We abstract various SGG models to be different
relation-head predictors in the file roi_heads/relation_head/roi_relation_predictors.py, which are independent of the Faster R-CNN backbone and relation-head feature extractor. You can use GLOBAL_SETTING.RELATION_PREDICTOR to select one of them:\n<div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" data-snippet-clipboard-copy-content="GLOBAL_SETTING.RELATION_PREDICTOR 'EICR_model'">GLOBAL_SETTING.RELATION_PREDICTOR <span class="pl-s"><span class="pl-pds">'EICR_model<span class="pl-pds">'\n<p dir="auto">The default settings are under
configs/SHA_GCL_e2e_relation_X_101_32_8_FPN_1x.yaml and maskrcnn_benchmark/config/defaults.py. The priority is command > yaml > defaults.py.\n<div class="markdown-heading" dir="auto"><h3 tabindex="-1" class="heading-element" dir="auto">Choose your Encoder<a id="user-content-choose-your-encoder" class="anchor-element" aria-label="Permalink: Choose your Encoder" href="#choose-your-encoder"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z">\n<p dir="auto">You need to further choose an object/relation encoder for "Motifs" or "VCTree" or "Self-Attention" predictor, by setting the following parameter:\n<div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" data-snippet-clipboard-copy-content="GLOBAL_SETTING.BASIC_ENCODER 'Motifs'">GLOBAL_SETTING.BASIC_ENCODER <span class="pl-s"><span class="pl-pds">'Motifs<span class="pl-pds">'\n<div class="markdown-heading" dir="auto"><h3 tabindex="-1" class="heading-element" dir="auto">Examples of the Training Command<a id="user-content-examples-of-the-training-command" class="anchor-element" aria-label="Permalink: Examples of the Training Command" href="#examples-of-the-training-command"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z">\n<p dir="auto">Training Example 1 : (VG, Motifs, PredCls)\n<div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" data-snippet-clipboard-copy-content="CUDA_VISIBLE_DEVICES=0 python -m torch.distributed.launch --master_port 10050 --nproc_per_node=1 ./tools/relation_train_net.py --config-file "configs/SHA_GCL_e2e_relation_X_101_32_8_FPN_1x.yaml" GLOBAL_SETTING.DATASET_CHOICE 'VG' GLOBAL_SETTING.RELATION_PREDICTOR 'EICR_model' GLOBAL_SETTING.BASIC_ENCODER 'Motifs' GLOBAL_SETTING.GCL_SETTING.GROUP_SPLIT_MODE 'divide4' GLOBAL_SETTING.GCL_SETTING.KNOWLEDGE_TRANSFER_MODE 'KL_logit_TopDown' MODEL.ROI_RELATION_HEAD.USE_GT_BOX True MODEL.ROI_RELATION_HEAD.USE_GT_OBJECT_LABEL True SOLVER.IMS_PER_BATCH 4 TEST.IMS_PER_BATCH 1 DTYPE "float16" SOLVER.MAX_ITER 120000 SOLVER.VAL_PERIOD 10000 SOLVER.CHECKPOINT_PERIOD 10000 GLOVE_DIR /data/myk/newreason/SHA/datasets/vg OUTPUT_DIR /data/myk/newreason/ICCV23/SHA/output/VG_predcls_EICR SOLVER.SCHEDULE.TYPE WarmupMultiStepLR SOLVER.STEPS "(56000, 96000)"">
CUDA_VISIBLE_DEVICES=0 python -m torch.distributed.launch --master_port 10050 --nproc_per_node=1 ./tools/relation_train_net.py --config-file <span class="pl-s"><span class="pl-pds">"configs/SHA_GCL_e2e_relation_X_101_32_8_FPN_1x.yaml<span class="pl-pds">" GLOBAL_SETTING.DATASET_CHOICE <span class="pl-s"><span class="pl-pds">'VG<span class="pl-pds">' GLOBAL_SETTING.RELATION_PREDICTOR <span class="pl-s"><span class="pl-pds">'EICR_model<span class="pl-pds">' GLOBAL_SETTING.BASIC_ENCODER <span class="pl-s"><span class="pl-pds">'Motifs<span class="pl-pds">' GLOBAL_SETTING.GCL_SETTING.GROUP_SPLIT_MODE <span class="pl-s"><span class="pl-pds">'divide4<span class="pl-pds">' GLOBAL_SETTING.GCL_SETTING.KNOWLEDGE_TRANSFER_MODE <span class="pl-s"><span class="pl-pds">'KL_logit_TopDown<span class="pl-pds">' MODEL.ROI_RELATION_HEAD.USE_GT_BOX True MODEL.ROI_RELATION_HEAD.USE_GT_OBJECT_LABEL True SOLVER.IMS_PER_BATCH 4 TEST.IMS_PER_BATCH 1 DTYPE <span class="pl-s"><span class="pl-pds">"float16<span class="pl-pds">" SOLVER.MAX_ITER 120000 SOLVER.VAL_PERIOD 10000 SOLVER.CHECKPOINT_PERIOD 10000 GLOVE_DIR /data/myk/newreason/SHA/datasets/vg OUTPUT_DIR /data/myk/newreason/ICCV23/SHA/output/VG_predcls_EICR SOLVER.SCHEDULE.TYPE WarmupMultiStepLR SOLVER.STEPS <span class="pl-s"><span class="pl-pds">"(56000, 96000)<span class="pl-pds">"\n<p dir="auto">Training Example 2 : (GQA_200, Motifs, SGCls)\n<div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" data-snippet-clipboard-copy-content="CUDA_VISIBLE_DEVICES=0 python -m torch.distributed.launch --master_port 10050 --nproc_per_node=1 ./tools/relation_train_net.py --config-file "configs/SHA_GCL_e2e_relation_X_101_32_8_FPN_1x.yaml" GLOBAL_SETTING.DATASET_CHOICE 'GQA_200' GLOBAL_SETTING.RELATION_PREDICTOR 'EICR_model' GLOBAL_SETTING.BASIC_ENCODER 'Motifs' GLOBAL_SETTING.GCL_SETTING.GROUP_SPLIT_MODE 'divide4' GLOBAL_SETTING.GCL_SETTING.KNOWLEDGE_TRANSFER_MODE 'KL_logit_TopDown' MODEL.ROI_RELATION_HEAD.USE_GT_BOX True MODEL.ROI_RELATION_HEAD.USE_GT_OBJECT_LABEL False SOLVER.IMS_PER_BATCH 4 TEST.IMS_PER_BATCH 1 DTYPE "float16" SOLVER.MAX_ITER 120000 SOLVER.VAL_PERIOD 10000 SOLVER.CHECKPOINT_PERIOD 10000 GLOVE_DIR /data/myk/newreason/SHA/datasets/vg OUTPUT_DIR /data/myk/newreason/ICCV23/SHA/output/VG_predcls_EICR SOLVER.SCHEDULE.TYPE WarmupMultiStepLR SOLVER.STEPS "(56000, 96000)"">
CUDA_VISIBLE_DEVICES=0 python -m torch.distributed.launch --master_port 10050 --nproc_per_node=1 ./tools/relation_train_net.py --config-file <span class="pl-s"><span class="pl-pds">"configs/SHA_GCL_e2e_relation_X_101_32_8_FPN_1x.yaml<span class="pl-pds">" GLOBAL_SETTING.DATASET_CHOICE <span class="pl-s"><span class="pl-pds">'GQA_200<span class="pl-pds">' GLOBAL_SETTING.RELATION_PREDICTOR <span class="pl-s"><span class="pl-pds">'EICR_model<span class="pl-pds">' GLOBAL_SETTING.BASIC_ENCODER <span class="pl-s"><span class="pl-pds">'Motifs<span class="pl-pds">' GLOBAL_SETTING.GCL_SETTING.GROUP_SPLIT_MODE <span class="pl-s"><span class="pl-pds">'divide4<span class="pl-pds">' GLOBAL_SETTING.GCL_SETTING.KNOWLEDGE_TRANSFER_MODE <span class="pl-s"><span class="pl-pds">'KL_logit_TopDown<span class="pl-pds">' MODEL.ROI_RELATION_HEAD.USE_GT_BOX True MODEL.ROI_RELATION_HEAD.USE_GT_OBJECT_LABEL False SOLVER.IMS_PER_BATCH 4 TEST.IMS_PER_BATCH 1 DTYPE <span class="pl-s"><span class="pl-pds">"float16<span class="pl-pds">" SOLVER.MAX_ITER 120000 SOLVER.VAL_PERIOD 10000 SOLVER.CHECKPOINT_PERIOD 10000 GLOVE_DIR /data/myk/newreason/SHA/datasets/vg OUTPUT_DIR /data/myk/newreason/ICCV23/SHA/output/VG_predcls_EICR SOLVER.SCHEDULE.TYPE WarmupMultiStepLR SOLVER.STEPS <span class="pl-s"><span class="pl-pds">"(56000, 96000)<span class="pl-pds">"\n<div class="markdown-heading" dir="auto"><h2 tabindex="-1" class="heading-element" dir="auto">Evaluation<a id="user-content-evaluation" class="anchor-element" aria-label="Permalink: Evaluation" href="#evaluation"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z">\n<p dir="auto">You can evaluate it by running the following command.\n<div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" data-snippet-clipboard-copy-content="CUDA_VISIBLE_DEVICES=0 python -m torch.distributed.launch --master_port 10083 --nproc_per_node=1 tools/relation_test_net.py --config-file "configs/SHA_GCL_e2e_relation_X_101_32_8_FPN_1x.yaml" GLOBAL_SETTING.DATASET_CHOICE 'GQA_200' GLOBAL_SETTING.RELATION_PREDICTOR 'EICR_model' GLOBAL_SETTING.BASIC_ENCODER 'Motifs' GLOBAL_SETTING.GCL_SETTING.GROUP_SPLIT_MODE 'divide4' GLOBAL_SETTING.GCL_SETTING.KNOWLEDGE_TRANSFER_MODE 'KL_logit_TopDown' MODEL.ROI_RELATION_HEAD.USE_GT_BOX True MODEL.ROI_RELATION_HEAD.USE_GT_OBJECT_LABEL False TEST.IMS_PER_BATCH 1 DTYPE "float16" GLOVE_DIR /home/myk/home/reason/newreason/SHA/datasets/vg/glove OUTPUT_DIR /home/myk/home/reason/newreason/SHA/output/GQA_precl_motif3samples_09aplha_start30000end60000/">
CUDA_VISIBLE_DEVICES=0 python -m torch.distributed.launch --master_port 10083 --nproc_per_node=1 tools/relation_test_net.py --config-file <span class="pl-s"><span class="pl-pds">"configs/SHA_GCL_e2e_relation_X_101_32_8_FPN_1x.yaml<span class="pl-pds">" GLOBAL_SETTING.DATASET_CHOICE <span class="pl-s"><span class="pl-pds">'GQA_200<span class="pl-pds">' GLOBAL_SETTING.RELATION_PREDICTOR <span class="pl-s"><span class="pl-pds">'EICR_model<span class="pl-pds">' GLOBAL_SETTING.BASIC_ENCODER <span class="pl-s"><span class="pl-pds">'Motifs<span class="pl-pds">' GLOBAL_SETTING.GCL_SETTING.GROUP_SPLIT_MODE <span class="pl-s"><span class="pl-pds">'divide4<span class="pl-pds">' GLOBAL_SETTING.GCL_SETTING.KNOWLEDGE_TRANSFER_MODE <span class="pl-s"><span class="pl-pds">'KL_logit_TopDown<span class="pl-pds">' MODEL.ROI_RELATION_HEAD.USE_GT_BOX True MODEL.ROI_RELATION_HEAD.USE_GT_OBJECT_LABEL False TEST.IMS_PER_BATCH 1 DTYPE <span class="pl-s"><span class="pl-pds">"float16<span class="pl-pds">" GLOVE_DIR /home/myk/home/reason/newreason/SHA/datasets/vg/glove OUTPUT_DIR /home/myk/home/reason/newreason/SHA/output/GQA_precl_motif3samples_09aplha_start30000end60000/\n<div class="markdown-heading" dir="auto"><h2 tabindex="-1" class="heading-element" dir="auto">Citation<a id="user-content-citation" class="anchor-element" aria-label="Permalink: Citation" href="#citation"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z">\n<div class="highlight highlight-source-shell notranslate position-relative overflow-auto" dir="auto" data-snippet-clipboard-copy-content="@inproceedings{min2023environment,\n title={Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation},\n author={Min, Yukuan and Wu, Aming and Deng, Cheng},\n booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},\n pages={13296--13307},\n year={2023}\n}">
@inproceedings{min2023environment,\n title={Environment-Invariant Curriculum Relation Learning <span class="pl-k">for Fine-Grained Scene Graph Generation},\n author={Min, Yukuan and Wu, Aming and Deng, Cheng},\n booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},\n pages={13296--13307},\n year={2023}\n}\n<div class="markdown-heading" dir="auto"><h2 tabindex="-1" class="heading-element" dir="auto">Acknowledgment<a id="user-content-acknowledgment" class="anchor-element" aria-label="Permalink: Acknowledgment" href="#acknowledgment"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z">\n<p dir="auto">Our code is on top of <a href="https://github.com/dongxingning/SHA-GCL-for-SGG\">SHA-GCL-for-SGG, we sincerely thank them for their well-designed codebase.\n","renderedFileInfo":null,"shortPath":null,"symbolsEnabled":true,"tabSize":8,"topBannersInfo":{"overridingGlobalFundingFile":false,"globalPreferredFundingPath":null,"repoOwner":"myukzzz","repoName":"EICR","showInvalidCitationWarning":false,"citationHelpUrl":"https://docs.github.com/github/creating-cloning-and-archiving-repositories/creating-a-repository-on-github/about-citation-files","actionsOnboardingTip":null},"truncated":false,"viewable":true,"workflowRedirectUrl":null,"symbols":{"timed_out":false,"not_analyzed":false,"symbols":[{"name":"Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation in Pytorch","kind":"section_1","ident_start":2,"ident_end":103,"extent_start":0,"extent_end":6324,"fully_qualified_name":"Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation in Pytorch","ident_utf16":{"start":{"line_number":0,"utf16_col":2},"end":{"line_number":0,"utf16_col":103}},"extent_utf16":{"start":{"line_number":0,"utf16_col":0},"end":{"line_number":125,"utf16_col":0}}},{"name":"Installation","kind":"section_2","ident_start":109,"ident_end":121,"extent_start":106,"extent_end":248,"fully_qualified_name":"Installation","ident_utf16":{"start":{"line_number":3,"utf16_col":3},"end":{"line_number":3,"utf16_col":15}},"extent_utf16":{"start":{"line_number":3,"utf16_col":0},"end":{"line_number":7,"utf16_col":0}}},{"name":"Dataset","kind":"section_2","ident_start":251,"ident_end":258,"extent_start":248,"extent_end":346,"fully_qualified_name":"Dataset","ident_utf16":{"start":{"line_number":7,"utf16_col":3},"end":{"line_number":7,"utf16_col":10}},"extent_utf16":{"start":{"line_number":7,"utf16_col":0},"end":{"line_number":11,"utf16_col":0}}},{"name":"Pretrained Models","kind":"section_2","ident_start":349,"ident_end":366,"extent_start":346,"extent_end":524,"fully_qualified_name":"Pretrained Models","ident_utf16":{"start":{"line_number":11,"utf16_col":3},"end":{"line_number":11,"utf16_col":20}},"extent_utf16":{"start":{"line_number":11,"utf16_col":0},"end":{"line_number":15,"utf16_col":0}}},{"name":"Perform training on Scene Graph Generation","kind":"section_2","ident_start":527,"ident_end":569,"extent_start":524,"extent_end":4989,"fully_qualified_name":"Perform training on Scene Graph Generation","ident_utf16":{"start":{"line_number":15,"utf16_col":3},"end":{"line_number":15,"utf16_col":45}},"extent_utf16":{"start":{"line_number":15,"utf16_col":0},"end":{"line_number":99,"utf16_col":0}}},{"name":"Set the dataset path","kind":"section_3","ident_start":575,"ident_end":595,"extent_start":571,"extent_end":1124,"fully_qualified_name":"Set the dataset path","ident_utf16":{"start":{"line_number":17,"utf16_col":4},"end":{"line_number":17,"utf16_col":24}},"extent_utf16":{"start":{"line_number":17,"utf16_col":0},"end":{"line_number":43,"utf16_col":0}}},{"name":"Choose a dataset","kind":"section_3","ident_start":1128,"ident_end":1144,"extent_start":1124,"extent_end":1291,"fully_qualified_name":"Choose a dataset","ident_utf16":{"start":{"line_number":43,"utf16_col":4},"end":{"line_number":43,"utf16_col":20}},"extent_utf16":{"start":{"line_number":43,"utf16_col":0},"end":{"line_number":50,"utf16_col":0}}},{"name":"Choose a task","kind":"section_3","ident_start":1295,"ident_end":1308,"extent_start":1291,"extent_end":2320,"fully_qualified_name":"Choose a task","ident_utf16":{"start":{"line_number":50,"utf16_col":4},"end":{"line_number":50,"utf16_col":17}},"extent_utf16":{"start":{"line_number":50,"utf16_col":0},"end":{"line_number":67,"utf16_col":0}}},{"name":"Choose your model","kind":"section_3","ident_start":2324,"ident_end":2341,"extent_start":2320,"extent_end":2907,"fully_qualified_name":"Choose your model","ident_utf16":{"start":{"line_number":67,"utf16_col":4},"end":{"line_number":67,"utf16_col":21}},"extent_utf16":{"start":{"line_number":67,"utf16_col":0},"end":{"line_number":78,"utf16_col":0}}},{"name":"Choose your Encoder","kind":"section_3","ident_start":2911,"ident_end":2930,"extent_start":2907,"extent_end":3133,"fully_qualified_name":"Choose your Encoder","ident_utf16":{"start":{"line_number":78,"utf16_col":4},"end":{"line_number":78,"utf16_col":23}},"extent_utf16":{"start":{"line_number":78,"utf16_col":0},"end":{"line_number":88,"utf16_col":0}}},{"name":"Examples of the Training Command","kind":"section_3","ident_start":3137,"ident_end":3169,"extent_start":3133,"extent_end":4989,"fully_qualified_name":"Examples of the Training Command","ident_utf16":{"start":{"line_number":88,"utf16_col":4},"end":{"line_number":88,"utf16_col":36}},"extent_utf16":{"start":{"line_number":88,"utf16_col":0},"end":{"line_number":99,"utf16_col":0}}},{"name":"Evaluation","kind":"section_2","ident_start":4992,"ident_end":5002,"extent_start":4989,"extent_end":5812,"fully_qualified_name":"Evaluation","ident_utf16":{"start":{"line_number":99,"utf16_col":3},"end":{"line_number":99,"utf16_col":13}},"extent_utf16":{"start":{"line_number":99,"utf16_col":0},"end":{"line_number":109,"utf16_col":0}}},{"name":"Citation","kind":"section_2","ident_start":5815,"ident_end":5823,"extent_start":5812,"extent_end":6157,"fully_qualified_name":"Citation","ident_utf16":{"start":{"line_number":109,"utf16_col":3},"end":{"line_number":109,"utf16_col":11}},"extent_utf16":{"start":{"line_number":109,"utf16_col":0},"end":{"line_number":122,"utf16_col":0}}},{"name":"Acknowledgment","kind":"section_2","ident_start":6160,"ident_end":6174,"extent_start":6157,"extent_end":6324,"fully_qualified_name":"Acknowledgment","ident_utf16":{"start":{"line_number":122,"utf16_col":3},"end":{"line_number":122,"utf16_col":17}},"extent_utf16":{"start":{"line_number":122,"utf16_col":0},"end":{"line_number":125,"utf16_col":0}}}]}},"copilotInfo":{"documentationUrl":"https://docs.github.com/copilot/overview-of-github-copilot/about-github-copilot-for-individuals","notices":{"codeViewPopover":{"dismissed":false,"dismissPath":"/settings/dismiss-notice/code_view_copilot_popover"}},"userAccess":{"hasSubscriptionEnded":false,"orgHasCFBAccess":false,"userHasCFIAccess":false,"userHasOrgs":false,"userIsOrgAdmin":false,"userIsOrgMember":false,"business":null,"featureRequestInfo":null}},"copilotAccessAllowed":false,"csrf_tokens":{"/myukzzz/EICR/branches":{"post":"zaUiFk1C3PZgpHKXYDsToNfQaPJUOLxN5KREDc-bl_FBqtmgkG13uH-HHnCl9TOQawtPH8EAkRpoo-C531ZeRg"},"/repos/preferences":{"post":"_WWAOcCC0dF3W8pkVWid291yT6IauEDZqwIW9zvGYI0pDq_96RNLW83dPaaXKDMrG-IL125IyPJhoksqC6L77Q"}}},"title":"EICR/README.md at main · myukzzz/EICR"}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent