{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"<!DOCTYPE html>\r\n<html lang=\"en\">\r\n\r\n<head>\r\n  <title>YOLO notebook | Kaggle</title>\r\n  <meta charset=\"utf-8\" />\r\n  <meta name=\"robots\" content=\"index, follow\" />\r\n  <meta name=\"description\" content=\"Explore and run machine learning code with Kaggle Notebooks | Using data from multiple data sources\" />\r\n  <meta name=\"turbolinks-cache-control\" content=\"no-cache\" />\r\n    <meta name=\"viewport\" content=\"width=device-width, initial-scale=1.0, maximum-scale=5.0, minimum-scale=1.0\">\r\n  <meta name=\"theme-color\" content=\"#008ABC\" />\r\n  <script nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\" type=\"text/javascript\">\r\n    if ('serviceWorker' in navigator) {\r\n      navigator.serviceWorker.getRegistrations()\r\n        .then(function (registrations) {\r\n          for (let registration of registrations) {\r\n            registration.unregister();\r\n          }\r\n        })\r\n        .catch(function (err) {\r\n          console.error(\"Service worker unregister failed: \", err);\r\n        });\r\n    }\r\n  </script>\r\n  <script nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\" type=\"text/javascript\">\r\n    window[\"pageRequestStartTime\"] = 1624467175132;\r\n    window[\"pageRequestEndTime\"] = 1624467175380;\r\n    window[\"initialPageLoadStartTime\"] = new Date().getTime();\r\n  </script>\r\n  <link rel=\"preconnect\" href=\"https://www.google-analytics.com\" crossorigin=\"anonymous\" /><link rel=\"preconnect\" href=\"https://stats.g.doubleclick.net\" /><link rel=\"preconnect\" href=\"https://storage.googleapis.com\" /><link rel=\"preconnect\" href=\"https://apis.google.com\" />\r\n  <link href=\"/static/images/favicon.ico\" rel=\"shortcut icon\" type=\"image/x-icon\" />\r\n  <link rel=\"manifest\" href=\"/static/json/manifest.json\" crossorigin=\"use-credentials\">\r\n  <link href=\"https://fonts.googleapis.com/icon?family=Google+Material+Icons\" rel=\"stylesheet\" type='text/css' />\r\n    <link rel=\"canonical\" href=\"/ajinkyadeshpande39/yolo-notebook\" />\r\n    <link rel=\"stylesheet\" type=\"text/css\" href=\"/static/assets/vendor.css?v=82cb257701542c806dbc\" />\r\n    <link rel=\"stylesheet\" type=\"text/css\" href=\"/static/assets/app.css?v=019ac85a2d39b03b2270\" />\r\n  \r\n    \r\n \r\n  \r\n    <script nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\">\r\n        try{(function(a,s,y,n,c,h,i,d,e){d=s.createElement(\"style\");\r\n        d.appendChild(s.createTextNode(\"\"));s.head.appendChild(d);d=d.sheet;\r\n        y=y.map(x => d.insertRule(x + \"{ opacity: 0 !important }\"));\r\n        h.start=1*new Date;h.end=i=function(){y.forEach(x => x<d.cssRules.length ? d.deleteRule(x) : {})};\r\n        (a[n]=a[n]||[]).hide=h;setTimeout(function(){i();h.end=null},c);h.timeout=c;\r\n        })(window,document,['.site-header-react__nav'],'dataLayer',2000,{'GTM-52LNT9S':true});}catch(ex){}\r\n    </script>\r\n    <script nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\">\r\n        window.dataLayer = window.dataLayer || [];\r\n        function gtag() { dataLayer.push(arguments); }\r\n        gtag('js', new Date());\r\n        gtag('config', 'UA-12629138-1', {\r\n            'optimize_id': 'GTM-52LNT9S',\r\n            'displayFeaturesTask': null,\r\n            'send_page_view': false,\r\n            'content_group1': 'Notebooks'\r\n        });\r\n    </script>\r\n    <script nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\" async src=\"https://www.googletagmanager.com/gtag/js?id=UA-12629138-1\"></script>\r\n\r\n  \r\n    \r\n    <meta name=\"og:url\" content=\"https://kaggle.com/ajinkyadeshpande39/yolo-notebook\" />\r\n    <meta property=\"og:title\" content=\"YOLO notebook\" />\r\n    <meta property=\"og:description\" content=\"Explore and run machine learning code with Kaggle Notebooks | Using data from multiple data sources\" />\r\n    <meta property=\"og:type\" content=\"website\" />\r\n    <meta name=\"og:image\" content=\"https://storage.googleapis.com/kaggle-avatars/thumbnails/default-thumb.png\" />\r\n\r\n    <meta name=\"twitter:card\" content=\"summary\" />\r\n    <meta name=\"twitter:site\" content=\"@kaggledatasets\" />\r\n\r\n\r\n  <meta name=\"twitter:site\" content=\"@Kaggle\" /> \r\n  \r\n    \r\n    <script nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\" type=\"application/ld+json\">{\"@context\":\"http://schema.org/\",\"@type\":\"Article\",\"author\":{\"@type\":\"Person\",\"name\":\"ajinkyadeshpande39\",\"sameAs\":\"/ajinkyadeshpande39\"},\"headline\":\"YOLO notebook\",\"url\":\"https://www.kaggle.com/ajinkyadeshpande39/yolo-notebook\",\"dateModified\":\"2021-06-23T16:43:13.89\",\"datePublished\":\"2021-06-23T16:43:13.89\",\"mainEntityOfPage\":{\"@type\":\"WebPage\",\"@id\":\"https://www.kaggle.com/ajinkyadeshpande39/yolo-notebook\"},\"publisher\":{\"@type\":\"Organization\",\"name\":\"Kaggle\",\"sameAs\":\"https://www.kaggle.com\",\"logo\":{\"type\":\"ImageObject\",\"url\":\"https://www.kaggle.com/static/images/site-logo.png\"}},\"image\":[\"https://storage.googleapis.com/kaggle-avatars/thumbnails/default-thumb.png\"]}</script>\r\n\r\n\r\n  \r\n    \r\n    \r\n<script nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\" type=\"text/javascript\">\r\n    var Kaggle = window.Kaggle || {};\r\n\r\n    Kaggle.Current = {\r\n        antiForgeryToken: 'CfDJ8LdUzqlsSWBPr4Ce3rb9VL_5oX2HL6-cE8-foejffFnYF_rzU-Ex9aIbwgoThojknU1_Ti-Rwq6SzmAuIAHAj3SXIbAyKshJidevH0RtSdYdU0kVblvqszilPO9DJF8IIvMSg6zxx9ZFnJ7swBrilV0',\r\n        isAnonymous: true,\r\n        analyticsToken: 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJleHAiOjE2MjQ0NjgwNzUsIlVzZXJJZCI6MH0.GfOO-Q5Sqp1lRduh-UWZm9Fbyq-HCR2Y_JOKpoa2UoU',\r\n        analyticsTokenExpiry: 15,\r\n        \r\n        \r\n        \r\n        \r\n        \r\n        \r\n        \r\n        enableRapidash: true, \r\n    }\r\n        Kaggle.Current.log = function(){};\r\n        Kaggle.Current.warn = function(){};\r\n\r\n    var decodeUserDisplayName = function () {\r\n        var escapedUserDisplayName = Kaggle.Current.userDisplayNameEscaped || \"\";\r\n        try {\r\n            var textVersion = new DOMParser().parseFromString(escapedUserDisplayName, \"text/html\").documentElement.textContent;\r\n            if (textVersion) {\r\n                return textVersion;\r\n            }\r\n        } catch(ex) {}\r\n        return escapedUserDisplayName;\r\n    }\r\n    Kaggle.Current.userDisplayName = decodeUserDisplayName();\r\n</script>\r\n\r\n    \r\n\r\n<script nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\" type=\"text/javascript\">\r\n    var Kaggle = window.Kaggle || {};\r\n    Kaggle.PageMessages = [];\r\n</script>\r\n\r\n\r\n\r\n    <script nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\">window['useKaggleAnalytics'] = true;</script>\r\n\r\n  <script id=\"gapi-target\" nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\" src=\"https://apis.google.com/js/api.js\" defer\r\n    async></script>\r\n  <script nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\" src=\"/static/assets/runtime.js?v=e57e31616beaf666186a\" data-turbolinks-track=\"reload\"></script>\r\n  <script nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\" src=\"/static/assets/vendor.js?v=dcd95395462a8b743fd0\" data-turbolinks-track=\"reload\"></script>\r\n  <script nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\" src=\"/static/assets/app.js?v=9787e9ea70e21b784cdf\" data-turbolinks-track=\"reload\"></script>\r\n    <script nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\" type=\"text/javascript\">\r\n      window.kaggleStackdriverConfig = {\r\n        key: 'AIzaSyA4eNqUdRRskJsCZWVz-qL655Xa5JEMreE',\r\n        projectId: 'kaggle-161607',\r\n        service: 'web-fe',\r\n        version: 'ci',\r\n          context: {\r\n        user: '0',\r\n                  },\r\n              };\r\n    </script>\r\n</head>\r\n\r\n<body data-turbolinks=\"false\">\r\n  <main>\r\n    \r\n\r\n\r\n\r\n\r\n\r\n<div id=\"site-container\"></div>\r\n<div data-component-name=\"NavigationContainer\" style=\"display: flex; flex-direction: column; flex: 1 0 auto;\"></div><script class=\"kaggle-component\" nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\">var Kaggle=window.Kaggle||{};Kaggle.State=Kaggle.State||[];Kaggle.State.push({\"navigationType\":\"BOTH_NAV\"});performance && performance.mark && performance.mark(\"NavigationContainer.componentCouldBootstrap\");</script>\r\n<div id=\"site-body\" class=\"hide\">\r\n    \r\n\r\n\r\n\r\n<div data-component-name=\"KernelViewer\" style=\"display: flex; flex-direction: column; flex: 1 0 auto;\"></div><script class=\"kaggle-component\" nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\">var Kaggle=window.Kaggle||{};Kaggle.State=Kaggle.State||[];Kaggle.State.push({\"redirectUrl\":null,\"kernel\":{\"id\":17874202,\"title\":\"YOLO notebook\",\"forkParent\":null,\"currentRunId\":66453229,\"mostRecentRunId\":66453442,\"url\":\"/ajinkyadeshpande39/yolo-notebook\",\"tags\":[],\"commentCount\":0,\"upvoteCount\":1,\"viewCount\":23,\"forkCount\":0,\"bestPublicScore\":null,\"author\":{\"id\":7528647,\"displayName\":\"AJINKYA DESHPANDE\",\"email\":null,\"editedEmail\":null,\"editedEmailCode\":null,\"userName\":\"ajinkyadeshpande39\",\"thumbnailUrl\":\"https://storage.googleapis.com/kaggle-avatars/thumbnails/default-thumb.png\",\"profileUrl\":\"/ajinkyadeshpande39\",\"registerDate\":\"0001-01-01T00:00:00Z\",\"lastVisitDate\":\"0001-01-01T00:00:00Z\",\"statusId\":0,\"performanceTier\":1,\"grandfatheredCompetitionTier\":null,\"userLogins\":null,\"groupIds\":null,\"duplicateUsers\":null,\"hasPhoneVerifications\":false,\"failedNerdchas\":0,\"hasPendingNerdcha\":false,\"deleteRequests\":null,\"isAdmin\":false,\"isKaggleBot\":false,\"isAnonymous\":false,\"canAct\":false,\"canBeSeen\":false,\"thumbnailName\":null,\"isPhoneVerified\":false},\"isPrivate\":false,\"updatedTime\":\"2021-06-23T16:43:13.89Z\",\"selfLink\":\"/kernels/17874202\",\"pinnedDockerImageVersionId\":null,\"dockerImagePinningType\":\"original\",\"originalDockerImageId\":30097,\"isLanguageTemplate\":false,\"medal\":null,\"topicId\":null,\"readGroupId\":null,\"writeGroupId\":null,\"slug\":\"yolo-notebook\",\"hasUsedAccelerator\":false,\"pinnedSessionId\":null,\"disableComments\":false,\"hasLinkedSubmission\":true,\"currentUserHasBookmarked\":false},\"kernelBlob\":{\"id\":661582171,\"settings\":{\"dockerImageVersionId\":null,\"dataSources\":[{\"sourceType\":\"Competition\",\"sourceId\":26680,\"datasetId\":null,\"databundleVersionId\":null,\"mountSlug\":\"siim-covid19-detection\"},{\"sourceType\":\"DatasetVersion\",\"sourceId\":1666454,\"datasetId\":null,\"databundleVersionId\":null,\"mountSlug\":\"kerasapplications\"},{\"sourceType\":\"DatasetVersion\",\"sourceId\":2246642,\"datasetId\":null,\"databundleVersionId\":null,\"mountSlug\":\"siim-covid19-resized-to-512px-png\"}],\"sourceType\":\"notebook\",\"language\":\"python\",\"accelerator\":\"gpu\",\"isInternetEnabled\":true},\"source\":\"{\\u0022metadata\\u0022:{\\u0022kernelspec\\u0022:{\\u0022language\\u0022:\\u0022python\\u0022,\\u0022display_name\\u0022:\\u0022Python 3\\u0022,\\u0022name\\u0022:\\u0022python3\\u0022},\\u0022language_info\\u0022:{\\u0022pygments_lexer\\u0022:\\u0022ipython3\\u0022,\\u0022nbconvert_exporter\\u0022:\\u0022python\\u0022,\\u0022version\\u0022:\\u00223.6.4\\u0022,\\u0022file_extension\\u0022:\\u0022.py\\u0022,\\u0022codemirror_mode\\u0022:{\\u0022name\\u0022:\\u0022ipython\\u0022,\\u0022version\\u0022:3},\\u0022name\\u0022:\\u0022python\\u0022,\\u0022mimetype\\u0022:\\u0022text/x-python\\u0022}},\\u0022nbformat_minor\\u0022:4,\\u0022nbformat\\u0022:4,\\u0022cells\\u0022:[{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# This Python 3 environment comes with many helpful analytics libraries installed\\\\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\\\\n# For example, here\\u0027s several helpful packages to load\\\\n\\\\nimport numpy as np # linear algebra\\\\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\\\\n\\\\n# Input data files are available in the read-only \\\\\\u0022../input/\\\\\\u0022 directory\\\\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\\\\nimport os\\\\n# for dirname, _, filenames in os.walk(\\u0027/kaggle/input\\u0027):\\\\n#     for filename in filenames:\\\\n#         print(os.path.join(dirname, filename))\\\\n\\\\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \\\\\\u0022Save \\u0026 Run All\\\\\\u0022 \\\\n# You can also write temporary files to /kaggle/temp/, but they won\\u0027t be saved outside of the current session\\u0022,\\u0022metadata\\u0022:{\\u0022_uuid\\u0022:\\u00228f2839f25d086af736a60e9eeb907d3b93b6e0e5\\u0022,\\u0022_cell_guid\\u0022:\\u0022b1076dfc-b9ad-4769-8c92-a6c4dae69d19\\u0022,\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:22:53.581661Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:22:53.582035Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:22:53.590494Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:22:53.581937Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:22:53.589481Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022submission = pd.read_csv(\\\\\\u0022../input/siim-covid19-detection/sample_submission.csv\\\\\\u0022)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:22:54.984727Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:22:54.985063Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:22:55.001796Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:22:54.985031Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:22:55.001076Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022submission\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:22:55.242251Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:22:55.242629Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:22:55.266563Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:22:55.242594Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:22:55.265773Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022import glob\\\\ncount = 0\\\\nfor i in glob.glob(\\u0027../input/siim-covid19-detection/test/*\\u0027):\\\\n    count += len(os.listdir(i))\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T13:01:10.064027Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T13:01:10.064402Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T13:01:11.901574Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T13:01:10.064367Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T13:01:11.900708Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022count+len(os.listdir(\\u0027../input/siim-covid19-detection/test\\u0027))\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T10:07:54.392795Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T10:07:54.393167Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T10:07:54.402189Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T10:07:54.393135Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T10:07:54.401179Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022%cd ../\\\\n!mkdir tmp\\\\n%cd tmp\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T13:39:21.828965Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T13:39:21.829587Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T13:39:22.579242Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T13:39:21.829549Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T13:39:22.577954Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022!mkdir tmp\\\\n%cd tmp\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:22:59.40651Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:22:59.406836Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:23:00.040033Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:22:59.406804Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:23:00.039063Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022!git clone https://github.com/ultralytics/yolov5  # clone repo\\\\n%cd yolov5\\\\n# Install dependencies\\\\n%pip install -qr requirements.txt  # install dependencies\\\\n\\\\n%cd ../\\\\nimport torch\\\\nprint(f\\\\\\u0022Setup complete. Using torch {torch.__version__} ({torch.cuda.get_device_properties(0).name if torch.cuda.is_available() else \\u0027CPU\\u0027})\\\\\\u0022)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:23:02.153333Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:23:02.153663Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:23:14.115323Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:23:02.153629Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:23:14.11446Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022!pip install -q --upgrade wandb\\\\n# Login \\\\nimport wandb\\\\nwandb.login()\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:23:14.116926Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:23:14.117294Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:23:30.673974Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:23:14.117253Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:23:30.673121Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022import os\\\\nimport gc\\\\nimport cv2\\\\nimport numpy as np\\\\nimport pandas as pd\\\\nfrom tqdm import tqdm\\\\nfrom shutil import copyfile\\\\nimport matplotlib.pyplot as plt\\\\nfrom sklearn.model_selection import train_test_split\\\\n\\\\n#customize iPython writefile so we can write variables\\\\nfrom IPython.core.magic import register_line_cell_magic\\\\n\\\\n@register_line_cell_magic\\\\ndef writetemplate(line, cell):\\\\n    with open(line, \\u0027w\\u0027) as f:\\\\n        f.write(cell.format(**globals()))\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:23:32.9373Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:23:32.937642Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:23:33.924254Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:23:32.937608Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:23:33.923419Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022TRAIN_PATH = \\u0027input/siim-covid19-resized-to-512px-png/train/\\u0027\\\\nIMG_SIZE = 512\\\\nBATCH_SIZE = 32\\\\nEPOCHS = 30\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:23:50.845596Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:23:50.845956Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:23:50.850769Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:23:50.845918Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:23:50.84929Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T13:32:29.911588Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T13:32:29.911961Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T13:32:29.920095Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T13:32:29.911925Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T13:32:29.918802Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022%cd ../\\\\n%cd ../\\\\n# Load image level csv file\\\\ndf = pd.read_csv(\\u0027input/siim-covid19-detection/train_image_level.csv\\u0027)\\\\n\\\\n# Modify values in the id column\\\\ndf[\\u0027id\\u0027] = df.apply(lambda row: row.id.split(\\u0027_\\u0027)[0], axis=1)\\\\n# Add absolute path\\\\ndf[\\u0027path\\u0027] = df.apply(lambda row: TRAIN_PATH+row.id+\\u0027.png\\u0027, axis=1)\\\\n# Get image level labels\\\\ndf[\\u0027image_level\\u0027] = df.apply(lambda row: row.label.split(\\u0027 \\u0027)[0], axis=1)\\\\n\\\\ndf.head(5)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:23:55.261868Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:23:55.262605Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:23:55.801486Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:23:55.262549Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:23:55.80071Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022meta_df = pd.read_csv(\\u0027input/siim-covid19-resized-to-512px-png/meta.csv\\u0027)\\\\ntrain_meta_df = meta_df.loc[meta_df.split == \\u0027train\\u0027]\\\\ntrain_meta_df = train_meta_df.drop(\\u0027split\\u0027, axis=1)\\\\ntrain_meta_df.columns = [\\u0027id\\u0027, \\u0027dim0\\u0027, \\u0027dim1\\u0027]\\\\n\\\\ntrain_meta_df.head(2)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:24:01.161989Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:24:01.162352Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:24:01.199236Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:24:01.162318Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:24:01.198471Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Merge both the dataframes\\\\ndf = df.merge(train_meta_df, on=\\u0027id\\u0027,how=\\\\\\u0022left\\\\\\u0022)\\\\ndf.head(2)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:24:03.262493Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:24:03.262853Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:24:03.289655Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:24:03.26282Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:24:03.288811Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Create train and validation split.\\\\ntrain_df, valid_df = train_test_split(df, test_size=0.15, random_state=42, stratify=df.image_level.values)\\\\n\\\\ntrain_df.loc[:, \\u0027split\\u0027] = \\u0027train\\u0027\\\\nvalid_df.loc[:, \\u0027split\\u0027] = \\u0027valid\\u0027\\\\n\\\\ndf = pd.concat([train_df, valid_df]).reset_index(drop=True)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:24:05.563262Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:24:05.563585Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:24:05.594924Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:24:05.563553Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:24:05.594085Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022print(f\\u0027Size of dataset: {len(df)}, training images: {len(train_df)}. validation images: {len(valid_df)}\\u0027)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:24:07.863054Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:24:07.863399Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:24:07.868391Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:24:07.863369Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:24:07.867286Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\\\nos.makedirs(\\u0027working/tmp/covid/images/train\\u0027, exist_ok=True)\\\\nos.makedirs(\\u0027working/tmp/covid/images/valid\\u0027, exist_ok=True)\\\\n\\\\nos.makedirs(\\u0027working/tmp/covid/labels/train\\u0027, exist_ok=True)\\\\nos.makedirs(\\u0027working/tmp/covid/labels/valid\\u0027, exist_ok=True)\\\\n\\\\n! ls tmp/covid/images\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:25:55.594975Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:25:55.595341Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:25:56.22716Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:25:55.595309Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:25:56.226264Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022%cd ..\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:27:25.292162Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:27:25.292496Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:27:25.299579Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:27:25.292467Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:27:25.298515Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\u0022,\\u0022metadata\\u0022:{},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Move the images to relevant split folder.\\\\nfor i in tqdm(range(len(df))):\\\\n    row = df.loc[i]\\\\n    if row.split == \\u0027train\\u0027 and row.image_level==\\u0027opacity\\u0027:\\\\n        copyfile(row.path, f\\u0027working/tmp/covid/images/train/{row.id}.jpg\\u0027)\\\\n    elif row.split == \\u0027valid\\u0027 and row.image_level==\\u0027opacity\\u0027:\\\\n        copyfile(row.path, f\\u0027working/tmp/covid/images/valid/{row.id}.jpg\\u0027)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:27:36.281211Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:27:36.281533Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:28:04.897253Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:27:36.281503Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:28:04.896128Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Move the images to relevant split folder.\\\\nfor i in tqdm(range(len(df))):\\\\n    row = df.loc[i]\\\\n    if row.split == \\u0027train\\u0027:\\\\n        copyfile(row.path, f\\u0027tmp/covid/images/train/{row.id}.jpg\\u0027)\\\\n    else:\\\\n        copyfile(row.path, f\\u0027tmp/covid/images/valid/{row.id}.jpg\\u0027)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T13:41:02.291505Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T13:41:02.291934Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T13:41:08.73535Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T13:41:02.291897Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T13:41:08.733502Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Create .yaml file \\\\nimport yaml\\\\n\\\\ndata_yaml = dict(\\\\n    train = \\u0027../covid/images/train\\u0027,\\\\n    val = \\u0027../covid/images/valid\\u0027,\\\\n    nc = 2,\\\\n    names = [\\u0027none\\u0027,\\u0027opacity\\u0027]\\\\n)\\\\n\\\\n# Note that I am creating the file in the yolov5/data/ directory.\\\\nwith open(\\u0027working/tmp/yolov5/data/data.yaml\\u0027, \\u0027w\\u0027) as outfile:\\\\n    yaml.dump(data_yaml, outfile, default_flow_style=True)\\\\n    \\\\n%cat working/tmp/yolov5/data/data.yaml\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:29:28.456491Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:29:28.456831Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:29:29.092099Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:29:28.456799Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:29:29.091136Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022with open(\\u0027/kaggle/working//tmp/covid/labels/train/000a312787f2.txt\\u0027,\\u0027r\\u0027) as f:\\\\n    print(f.read())\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:29:41.703356Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:29:41.703692Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:29:41.728614Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:29:41.703659Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:29:41.726744Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Get the raw bounding box by parsing the row value of the label column.\\\\n# Ref: https://www.kaggle.com/yujiariyasu/plot-3positive-classes\\\\ndef get_bbox(row):\\\\n    bboxes = []\\\\n    bbox = []\\\\n    for i, l in enumerate(row.label.split(\\u0027 \\u0027)):\\\\n        if (i % 6 == 0) | (i % 6 == 1):\\\\n            continue\\\\n        bbox.append(float(l))\\\\n        if i % 6 == 5:\\\\n            bboxes.append(bbox)\\\\n            bbox = []  \\\\n            \\\\n    return bboxes\\\\n\\\\n# Scale the bounding boxes according to the size of the resized image. \\\\ndef scale_bbox(row, bboxes):\\\\n    # Get scaling factor\\\\n    scale_x = IMG_SIZE/row.dim1\\\\n    scale_y = IMG_SIZE/row.dim0\\\\n    \\\\n    scaled_bboxes = []\\\\n    for bbox in bboxes:\\\\n        x = int(np.round(bbox[0]*scale_x, 4))\\\\n        y = int(np.round(bbox[1]*scale_y, 4))\\\\n        x1 = int(np.round(bbox[2]*(scale_x), 4))\\\\n        y1= int(np.round(bbox[3]*scale_y, 4))\\\\n\\\\n        scaled_bboxes.append([x, y, x1, y1]) # xmin, ymin, xmax, ymax\\\\n        \\\\n    return scaled_bboxes\\\\n\\\\n# Convert the bounding boxes in YOLO format.\\\\ndef get_yolo_format_bbox(img_w, img_h, bboxes):\\\\n    yolo_boxes = []\\\\n    for bbox in bboxes:\\\\n        w = bbox[2] - bbox[0] # xmax - xmin\\\\n        h = bbox[3] - bbox[1] # ymax - ymin\\\\n        xc = bbox[0] + int(np.round(w/2)) # xmin + width/2\\\\n        yc = bbox[1] + int(np.round(h/2)) # ymin + height/2\\\\n        \\\\n        yolo_boxes.append([xc/img_w, yc/img_h, w/img_w, h/img_h]) # x_center y_center width height\\\\n    \\\\n    return yolo_boxes\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:29:45.077249Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:29:45.077599Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:29:45.089712Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:29:45.077558Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:29:45.088866Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Prepare the txt files for bounding box\\\\nfor i in tqdm(range(len(df))):\\\\n    row = df.loc[i]\\\\n    # Get image id\\\\n    img_id = row.id\\\\n    # Get split\\\\n    split = row.split\\\\n    # Get image-level label\\\\n    label = row.image_level\\\\n    \\\\n    if row.split==\\u0027train\\u0027:\\\\n        file_name = f\\u0027working/tmp/covid/labels/train/{row.id}.txt\\u0027\\\\n    else:\\\\n        file_name = f\\u0027working/tmp/covid/labels/valid/{row.id}.txt\\u0027\\\\n        \\\\n    \\\\n    if label==\\u0027opacity\\u0027:\\\\n        # Get bboxes\\\\n        bboxes = get_bbox(row)\\\\n        # Scale bounding boxes\\\\n        scale_bboxes = scale_bbox(row, bboxes)\\\\n        # Format for YOLOv5\\\\n        yolo_bboxes = get_yolo_format_bbox(IMG_SIZE, IMG_SIZE, scale_bboxes)\\\\n        \\\\n        with open(file_name, \\u0027w\\u0027) as f:\\\\n            for bbox in yolo_bboxes:\\\\n                bbox = [1]+bbox\\\\n                bbox = [str(i) for i in bbox]\\\\n                bbox = \\u0027 \\u0027.join(bbox)\\\\n                f.write(bbox)\\\\n                f.write(\\u0027\\\\\\\\n\\u0027)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:30:01.664754Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:30:01.665129Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:30:04.361189Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:30:01.665091Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:30:04.360192Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022bbox\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:30:12.10387Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:30:12.104376Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:30:12.109936Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:30:12.104338Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:30:12.108931Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022%cd working/tmp/yolov5/\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:30:49.117336Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:30:49.117668Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:30:49.125257Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:30:49.117635Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:30:49.124137Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022ls\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:30:37.831091Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:30:37.831442Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:30:38.460343Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:30:37.831411Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:30:38.459302Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022!python train.py --img {IMG_SIZE} \\\\\\\\\\\\n                 --batch {BATCH_SIZE} \\\\\\\\\\\\n                 --epochs {EPOCHS} \\\\\\\\\\\\n                 --data data.yaml \\\\\\\\\\\\n                 --weights yolov5l.pt \\\\\\\\\\\\n                 --save_period 1\\\\\\\\\\\\n                 --project kaggle-siim-covid-yolov5l-t3-clas2\\\\n                 \\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T10:27:33.521412Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T10:27:33.521782Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T11:35:12.529821Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T10:27:33.521735Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T11:35:12.528857Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022os.listdir(\\u0027kaggle-siim-covid-yolov5l-t3-clas2/exp/weights\\u0027)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T11:36:03.55081Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T11:36:03.551188Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T11:36:03.558177Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T11:36:03.551151Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T11:36:03.557174Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022%cd ..\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:36:15.843947Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:36:15.844313Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:36:15.851046Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:36:15.84428Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:36:15.850111Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022%cd yolov5\\\\n%ls\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:40:12.528277Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:40:12.528625Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:40:13.168792Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:40:12.52859Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:40:13.167776Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022MODEL_PATH = \\\\\\u0022artifacts/run_2xb4vetk_model:v29/best.pt\\\\\\u0022\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:40:17.366627Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:40:17.366966Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:40:17.373637Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:40:17.366932Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:40:17.372853Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# MODEL_PATH = \\u0027kaggle-siim-covid-yolov5l-t3-clas2/exp/weights/best.pt\\u0027\\\\nTEST_PATH = \\u0027../../../input/siim-covid19-resized-to-512px-png/test/\\u0027\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:40:17.611852Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:40:17.612212Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:40:17.616189Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:40:17.61218Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:40:17.615038Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022!python detect.py --weights {MODEL_PATH} \\\\\\\\\\\\n                  --source {TEST_PATH} \\\\\\\\\\\\n                  --img {IMG_SIZE} \\\\\\\\\\\\n                  --conf 0.3 \\\\\\\\\\\\n                  --iou-thres 0.5 \\\\\\\\\\\\n                  --max-det 3 \\\\\\\\\\\\n                  --save-txt \\\\\\\\\\\\n                  --save-conf\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:40:20.354618Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:40:20.354948Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:41:42.486417Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:40:20.354917Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:41:42.48547Z\\u0022},\\u0022collapsed\\u0022:true,\\u0022jupyter\\u0022:{\\u0022outputs_hidden\\u0022:true},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022!python train.py --resume wandb-artifact://39ajinkya/kaggle-siim-covid-yolov5l-t3-clas2/2xb4vetk\\\\n                 \\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:36:18.982488Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:36:18.982817Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:36:45.626952Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:36:18.982784Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:36:45.62601Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022os.listdir(\\u0027/kaggle/tmp/yolov5/runs/detect/exp/labels\\u0027)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T11:59:09.57632Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T11:59:09.576675Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T11:59:09.585789Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T11:59:09.576639Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T11:59:09.584295Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022PRED_PATH = \\u0027runs/detect/exp3/labels\\u0027\\\\n!ls {PRED_PATH}\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:42:22.617996Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:42:22.618384Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:42:23.256272Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:42:22.618347Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:42:23.2553Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Visualize predicted coordinates.\\\\n%cat runs/detect/exp3/labels/ba91d37ee459.txt\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:42:33.85355Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:42:33.853914Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:42:34.489431Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:42:33.853881Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:42:34.488496Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022prediction_files = os.listdir(PRED_PATH)\\\\nprint(\\u0027Number of test images predicted as opaque: \\u0027, len(prediction_files))\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:42:42.542727Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:42:42.543087Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:42:42.54904Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:42:42.543046Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:42:42.548178Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# The submisison requires xmin, ymin, xmax, ymax format. \\\\n# YOLOv5 returns x_center, y_center, width, height\\\\ndef correct_bbox_format(bboxes):\\\\n    correct_bboxes = []\\\\n    for b in bboxes:\\\\n        xc, yc = int(np.round(b[0]*IMG_SIZE)), int(np.round(b[1]*IMG_SIZE))\\\\n        w, h = int(np.round(b[2]*IMG_SIZE)), int(np.round(b[3]*IMG_SIZE))\\\\n\\\\n        xmin = xc - int(np.round(w/2))\\\\n        xmax = xc + int(np.round(w/2))\\\\n        ymin = yc - int(np.round(h/2))\\\\n        ymax = yc + int(np.round(h/2))\\\\n        \\\\n        correct_bboxes.append([xmin, xmax, ymin, ymax])\\\\n        \\\\n    return correct_bboxes\\\\n\\\\n# Read the txt file generated by YOLOv5 during inference and extract \\\\n# confidence and bounding box coordinates.\\\\ndef get_conf_bboxes(file_path):\\\\n    confidence = []\\\\n    bboxes = []\\\\n    with open(file_path, \\u0027r\\u0027) as file:\\\\n        for line in file:\\\\n            preds = line.strip(\\u0027\\\\\\\\n\\u0027).split(\\u0027 \\u0027)\\\\n            preds = list(map(float, preds))\\\\n            confidence.append(preds[-1])\\\\n            bboxes.append(preds[1:-1])\\\\n    return confidence, bboxes\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:42:45.485146Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:42:45.485484Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:42:45.494345Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:42:45.485456Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:42:45.493511Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Read the submisison file\\\\nsub_df = pd.read_csv(\\u0027/kaggle/input/siim-covid19-detection/sample_submission.csv\\u0027)\\\\nsub_df.tail()\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:42:48.556204Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:42:48.556524Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:42:48.576854Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:42:48.556495Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:42:48.575884Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Prediction loop for submission\\\\npredictions = []\\\\n\\\\nfor i in tqdm(range(len(sub_df))):\\\\n    row = sub_df.loc[i]\\\\n    id_name = row.id.split(\\u0027_\\u0027)[0]\\\\n    id_level = row.id.split(\\u0027_\\u0027)[-1]\\\\n    \\\\n    if id_level == \\u0027study\\u0027:\\\\n        # do study-level classification\\\\n        predictions.append(\\\\\\u0022Negative 1 0 0 1 1\\\\\\u0022) # dummy prediction\\\\n        \\\\n    elif id_level == \\u0027image\\u0027:\\\\n        # we can do image-level classification here.\\\\n        # also we can rely on the object detector\\u0027s classification head.\\\\n        # for this example submisison we will use YOLO\\u0027s classification head. \\\\n        # since we already ran the inference we know which test images belong to opacity.\\\\n        if f\\u0027{id_name}.txt\\u0027 in prediction_files:\\\\n            # opacity label\\\\n            confidence, bboxes = get_conf_bboxes(f\\u0027{PRED_PATH}/{id_name}.txt\\u0027)\\\\n            bboxes = correct_bbox_format(bboxes)\\\\n            pred_string = \\u0027\\u0027\\\\n            for j, conf in enumerate(confidence):\\\\n                pred_string += f\\u0027opacity {conf} \\u0027 + \\u0027 \\u0027.join(map(str, bboxes[j])) + \\u0027 \\u0027\\\\n            predictions.append(pred_string[:-1]) \\\\n        else:\\\\n            predictions.append(\\\\\\u0022None 1 0 0 1 1\\\\\\u0022)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:42:54.048202Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:42:54.048521Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:42:54.491177Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:42:54.048491Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:42:54.490171Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022sub_df[\\u0027PredictionString\\u0027] = predictions\\\\nsub_df.to_csv(\\u0027/kaggle/working/submission.csv\\u0027, index=False)\\\\nsub_df.tail()\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:43:03.759536Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:43:03.759873Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:43:04.110805Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:43:03.759841Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:43:04.109982Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022sub_df.loc[sub_df[\\u0027PredictionString\\u0027] == \\\\\\u0022None 1 0 0 1 1\\\\\\u0022]\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T13:23:13.229827Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T13:23:13.230283Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T13:23:13.304521Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T13:23:13.230246Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T13:23:13.302739Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022os.listdir(\\u0027/kaggle/working\\u0027)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T12:48:15.82343Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T12:48:15.823801Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T12:48:15.828991Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T12:48:15.82375Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T12:48:15.82814Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022markdown\\u0022,\\u0022source\\u0022:\\u0022creating a coco format dataset.\\u0022,\\u0022metadata\\u0022:{}},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# #creating a coco format dataset.\\\\n# df.iloc[0].path\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:02:16.034664Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:02:16.03501Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:02:16.041594Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:02:16.034979Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:02:16.040506Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# annotation = dict()\\\\n\\\\n# for i in tqdm(range(len(df))):\\\\n#     row = df.loc[i]\\\\n#     # Get image id\\\\n#     img_id = row.id\\\\n#     # Get split\\\\n#     split = row.split\\\\n#     # Get image-level label\\\\n#     label = row.image_level\\\\n    \\\\n#     file_name = row.path\\\\n        \\\\n    \\\\n#     if label==\\u0027opacity\\u0027:\\\\n#         # Get bboxes\\\\n#         bboxes = get_bbox(row)\\\\n#         # Scale bounding boxes\\\\n#         scale_bboxes = scale_bbox(row, bboxes)\\\\n#         # Format for YOLOv5\\\\n#         yolo_bboxes = get_yolo_format_bbox(IMG_SIZE, IMG_SIZE, scale_bboxes)\\\\n        \\\\n#         l = []\\\\n#         for bbox in yolo_bboxes:\\\\n#             l.append({\\u0027bbox\\u0027:bbox,\\u0027label\\u0027:\\u0027opacity\\u0027})\\\\n#         annotation[file_name] = l\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:23:25.924899Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:23:25.925238Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:23:27.853252Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:23:25.925209Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:23:27.852401Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# annotation\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:23:29.554938Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:23:29.55525Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:23:29.793865Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:23:29.555218Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:23:29.793033Z\\u0022},\\u0022collapsed\\u0022:true,\\u0022jupyter\\u0022:{\\u0022outputs_hidden\\u0022:true},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# del dataset\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:10:27.635044Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:10:27.635371Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:10:27.63875Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:10:27.63534Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:10:27.637847Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:17:22.02986Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:17:22.030192Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:17:22.035232Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:17:22.030161Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:17:22.034351Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# image_path = \\u0027kaggle/input/siim-covid19-resized-to-256px-jpg/train/*\\u0027\\\\n# glob.glob(image_path)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:19:32.579709Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:19:32.580021Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:19:32.624363Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:19:32.579991Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:19:32.623434Z\\u0022},\\u0022collapsed\\u0022:true,\\u0022jupyter\\u0022:{\\u0022outputs_hidden\\u0022:true},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# import glob\\\\n# import fiftyone as fo\\\\n\\\\n# image_path = \\u0027kaggle/input/siim-covid19-resized-to-256px-jpg/train/*\\u0027\\\\n\\\\n# # Ex: your custom label format\\\\n\\\\n# # Create dataset\\\\n# dataset = fo.Dataset(name=\\\\\\u0022siim-covid-19-6\\\\\\u0022)\\\\n\\\\n# # Persist the dataset on disk in order to \\\\n# # be able to load it in one line in the future\\\\n# dataset.persistent = True\\\\n\\\\n# # Add your samples to the dataset\\\\n# for filepath in annotation:\\\\n#     sample = fo.Sample(filepath=filepath)\\\\n#     sample.tags.append(\\u0027images\\u0027)\\\\n#     # Convert detections to FiftyOne format\\\\n#     detections = []\\\\n#     for obj in annotation[filepath]:\\\\n#         label = obj[\\\\\\u0022label\\\\\\u0022]\\\\n\\\\n#         # Bounding box coordinates should be relative values\\\\n#         # in [0, 1] in the following format:\\\\n#         # [top-left-x, top-left-y, width, height]\\\\n#         bounding_box = obj[\\\\\\u0022bbox\\\\\\u0022]\\\\n        \\\\n#         detections.append(\\\\n#             fo.Detection(label=label, bounding_box=bounding_box)\\\\n#         )\\\\n\\\\n#     # Store detections in a field name of your choice\\\\n#     sample[\\\\\\u0022train\\\\\\u0022] = fo.Detections(detections=detections)\\\\n\\\\n#     dataset.add_sample(sample)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:25:35.59564Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:25:35.595953Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:25:45.163808Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:25:35.595917Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:25:45.162775Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# view = dataset.match_tags(\\u0027images\\u0027)\\\\n# for sample in view:\\\\n#     print(sample)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:25:49.03443Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:25:49.034752Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:26:10.008087Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:25:49.034721Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:26:10.007317Z\\u0022},\\u0022collapsed\\u0022:true,\\u0022jupyter\\u0022:{\\u0022outputs_hidden\\u0022:true},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# export_dir = \\\\\\u0022/path/for/coco-detection-dataset-1\\\\\\u0022\\\\n# label_field = \\\\\\u0022ground_truth\\\\\\u0022  # for example\\\\n\\\\n# # Export the dataset\\\\n# dataset.export(\\\\n#     export_dir=export_dir,\\\\n#     dataset_type=fo.types.COCODetectionDataset,\\\\n#     label_field=label_field,\\\\n# )\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:06:03.990294Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:06:03.99067Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:06:04.001856Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:06:03.990638Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:06:04.000818Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# !pip install fiftyone\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T12:50:53.42484Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T12:50:53.42518Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T12:51:19.961086Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T12:50:53.425148Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T12:51:19.960121Z\\u0022},\\u0022collapsed\\u0022:true,\\u0022jupyter\\u0022:{\\u0022outputs_hidden\\u0022:true},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\u0022,\\u0022metadata\\u0022:{\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\u0022,\\u0022metadata\\u0022:{},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\u0022,\\u0022metadata\\u0022:{},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\u0022,\\u0022metadata\\u0022:{},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]}]}\",\"dateCreated\":\"2021-06-23T16:43:10.6254824Z\"},\"kernelRun\":{\"id\":66453229,\"kernelId\":17874202,\"status\":\"complete\",\"kernelVersionType\":\"batch\",\"sourceType\":\"notebook\",\"language\":\"python\",\"title\":\"YOLO notebook\",\"dateCreated\":\"2021-06-23T16:43:11.29Z\",\"dateEvaluated\":\"2021-06-23T16:43:13.89Z\",\"dateCancelled\":null,\"workerContainerPort\":null,\"workerUptimeSeconds\":2690,\"workerIPAddress\":\"172.23.1.58    \",\"workerIPAddressExternal\":\"35.204.132.172 \",\"scriptLanguageId\":9,\"scriptLanguageName\":\"IPython Notebook HTML\",\"renderedOutputUrl\":\"https://www.kaggleusercontent.com/kf/66453229/eyJhbGciOiJkaXIiLCJlbmMiOiJBMTI4Q0JDLUhTMjU2In0..GVD1ySf3kLlq6DS3ViRCGA.0TEAfQ8bmaEyXtyN1W5LCtPRJQ8KLT07bdx0nc_BB_m0RaCRrOsuev8J6r-ovnh95tuBr7YsnN8QBPP16Ej0etKHBbqj4IcqIfUhJeR7AS-ffCh995MnJQJ8iXbgXMd5L6ZTzyVkdqSUMPUy57P564j32WKz4plY4n-pq0V9gHADX-rZHaf1Smgnf5GnzylHDQvjep0x9QcZfwpkvC8UXozSy34mWyNKJKbNKpcEh8nvvfjj6oNlZXPppsvM6cS9Ort7MASiB3cFpX-0ok7xHrBfvS3aembZB_R7vKgPTp93AnFiqmfo6cRm-dgEsUkiuZfV7TFsG5YoGlaNVrtHMA-1PtxLFU5CL-RoY7tE_pU5tKK3hMkB5IlL4SXbV-loz3cnxOmZDRBuZrO4Vrq-EMGM0LfHJSlcSAIKjYcpkxdfXcT13nnBth0PxoHqJoSIcIq9fgOHDn6Uj7cvUq1ifoxHzsaBQF5741dqgxB7SW2OSUlWNyQxzoSn4Yahe7JA0tBTl8sv6RQ2vOrejfNrdnWlMmmsTi_pLk92w4DfHor-8T3eXpPODyCwPnLE33WswqfBSfC6XzIQGDp0s8TlERBP2b7a2i3zHY3Z9cU1dkVO2TviwhJ4oyDS7znUzUcYdwUcwSGnrtwSHs6ZCdRxw4JTtlaj4cpJOvIGI6NuTgA.xsgHHmp-J6Hww3geJcKr8Q/__results__.html?sharingControls=true\",\"commit\":{\"id\":661582171,\"settings\":{\"dockerImageVersionId\":null,\"dataSources\":[{\"sourceType\":\"Competition\",\"sourceId\":26680,\"datasetId\":null,\"databundleVersionId\":null,\"mountSlug\":\"siim-covid19-detection\"},{\"sourceType\":\"DatasetVersion\",\"sourceId\":1666454,\"datasetId\":null,\"databundleVersionId\":null,\"mountSlug\":\"kerasapplications\"},{\"sourceType\":\"DatasetVersion\",\"sourceId\":2246642,\"datasetId\":null,\"databundleVersionId\":null,\"mountSlug\":\"siim-covid19-resized-to-512px-png\"}],\"sourceType\":\"notebook\",\"language\":\"python\",\"accelerator\":\"gpu\",\"isInternetEnabled\":true},\"source\":\"{\\u0022metadata\\u0022:{\\u0022kernelspec\\u0022:{\\u0022language\\u0022:\\u0022python\\u0022,\\u0022display_name\\u0022:\\u0022Python 3\\u0022,\\u0022name\\u0022:\\u0022python3\\u0022},\\u0022language_info\\u0022:{\\u0022pygments_lexer\\u0022:\\u0022ipython3\\u0022,\\u0022nbconvert_exporter\\u0022:\\u0022python\\u0022,\\u0022version\\u0022:\\u00223.6.4\\u0022,\\u0022file_extension\\u0022:\\u0022.py\\u0022,\\u0022codemirror_mode\\u0022:{\\u0022name\\u0022:\\u0022ipython\\u0022,\\u0022version\\u0022:3},\\u0022name\\u0022:\\u0022python\\u0022,\\u0022mimetype\\u0022:\\u0022text/x-python\\u0022}},\\u0022nbformat_minor\\u0022:4,\\u0022nbformat\\u0022:4,\\u0022cells\\u0022:[{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# This Python 3 environment comes with many helpful analytics libraries installed\\\\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\\\\n# For example, here\\u0027s several helpful packages to load\\\\n\\\\nimport numpy as np # linear algebra\\\\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\\\\n\\\\n# Input data files are available in the read-only \\\\\\u0022../input/\\\\\\u0022 directory\\\\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\\\\nimport os\\\\n# for dirname, _, filenames in os.walk(\\u0027/kaggle/input\\u0027):\\\\n#     for filename in filenames:\\\\n#         print(os.path.join(dirname, filename))\\\\n\\\\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \\\\\\u0022Save \\u0026 Run All\\\\\\u0022 \\\\n# You can also write temporary files to /kaggle/temp/, but they won\\u0027t be saved outside of the current session\\u0022,\\u0022metadata\\u0022:{\\u0022_uuid\\u0022:\\u00228f2839f25d086af736a60e9eeb907d3b93b6e0e5\\u0022,\\u0022_cell_guid\\u0022:\\u0022b1076dfc-b9ad-4769-8c92-a6c4dae69d19\\u0022,\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:22:53.581661Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:22:53.582035Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:22:53.590494Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:22:53.581937Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:22:53.589481Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022submission = pd.read_csv(\\\\\\u0022../input/siim-covid19-detection/sample_submission.csv\\\\\\u0022)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:22:54.984727Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:22:54.985063Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:22:55.001796Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:22:54.985031Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:22:55.001076Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022submission\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:22:55.242251Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:22:55.242629Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:22:55.266563Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:22:55.242594Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:22:55.265773Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022import glob\\\\ncount = 0\\\\nfor i in glob.glob(\\u0027../input/siim-covid19-detection/test/*\\u0027):\\\\n    count += len(os.listdir(i))\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T13:01:10.064027Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T13:01:10.064402Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T13:01:11.901574Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T13:01:10.064367Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T13:01:11.900708Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022count+len(os.listdir(\\u0027../input/siim-covid19-detection/test\\u0027))\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T10:07:54.392795Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T10:07:54.393167Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T10:07:54.402189Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T10:07:54.393135Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T10:07:54.401179Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022%cd ../\\\\n!mkdir tmp\\\\n%cd tmp\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T13:39:21.828965Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T13:39:21.829587Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T13:39:22.579242Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T13:39:21.829549Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T13:39:22.577954Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022!mkdir tmp\\\\n%cd tmp\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:22:59.40651Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:22:59.406836Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:23:00.040033Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:22:59.406804Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:23:00.039063Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022!git clone https://github.com/ultralytics/yolov5  # clone repo\\\\n%cd yolov5\\\\n# Install dependencies\\\\n%pip install -qr requirements.txt  # install dependencies\\\\n\\\\n%cd ../\\\\nimport torch\\\\nprint(f\\\\\\u0022Setup complete. Using torch {torch.__version__} ({torch.cuda.get_device_properties(0).name if torch.cuda.is_available() else \\u0027CPU\\u0027})\\\\\\u0022)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:23:02.153333Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:23:02.153663Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:23:14.115323Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:23:02.153629Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:23:14.11446Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022!pip install -q --upgrade wandb\\\\n# Login \\\\nimport wandb\\\\nwandb.login()\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:23:14.116926Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:23:14.117294Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:23:30.673974Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:23:14.117253Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:23:30.673121Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022import os\\\\nimport gc\\\\nimport cv2\\\\nimport numpy as np\\\\nimport pandas as pd\\\\nfrom tqdm import tqdm\\\\nfrom shutil import copyfile\\\\nimport matplotlib.pyplot as plt\\\\nfrom sklearn.model_selection import train_test_split\\\\n\\\\n#customize iPython writefile so we can write variables\\\\nfrom IPython.core.magic import register_line_cell_magic\\\\n\\\\n@register_line_cell_magic\\\\ndef writetemplate(line, cell):\\\\n    with open(line, \\u0027w\\u0027) as f:\\\\n        f.write(cell.format(**globals()))\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:23:32.9373Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:23:32.937642Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:23:33.924254Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:23:32.937608Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:23:33.923419Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022TRAIN_PATH = \\u0027input/siim-covid19-resized-to-512px-png/train/\\u0027\\\\nIMG_SIZE = 512\\\\nBATCH_SIZE = 32\\\\nEPOCHS = 30\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:23:50.845596Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:23:50.845956Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:23:50.850769Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:23:50.845918Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:23:50.84929Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T13:32:29.911588Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T13:32:29.911961Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T13:32:29.920095Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T13:32:29.911925Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T13:32:29.918802Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022%cd ../\\\\n%cd ../\\\\n# Load image level csv file\\\\ndf = pd.read_csv(\\u0027input/siim-covid19-detection/train_image_level.csv\\u0027)\\\\n\\\\n# Modify values in the id column\\\\ndf[\\u0027id\\u0027] = df.apply(lambda row: row.id.split(\\u0027_\\u0027)[0], axis=1)\\\\n# Add absolute path\\\\ndf[\\u0027path\\u0027] = df.apply(lambda row: TRAIN_PATH+row.id+\\u0027.png\\u0027, axis=1)\\\\n# Get image level labels\\\\ndf[\\u0027image_level\\u0027] = df.apply(lambda row: row.label.split(\\u0027 \\u0027)[0], axis=1)\\\\n\\\\ndf.head(5)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:23:55.261868Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:23:55.262605Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:23:55.801486Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:23:55.262549Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:23:55.80071Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022meta_df = pd.read_csv(\\u0027input/siim-covid19-resized-to-512px-png/meta.csv\\u0027)\\\\ntrain_meta_df = meta_df.loc[meta_df.split == \\u0027train\\u0027]\\\\ntrain_meta_df = train_meta_df.drop(\\u0027split\\u0027, axis=1)\\\\ntrain_meta_df.columns = [\\u0027id\\u0027, \\u0027dim0\\u0027, \\u0027dim1\\u0027]\\\\n\\\\ntrain_meta_df.head(2)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:24:01.161989Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:24:01.162352Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:24:01.199236Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:24:01.162318Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:24:01.198471Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Merge both the dataframes\\\\ndf = df.merge(train_meta_df, on=\\u0027id\\u0027,how=\\\\\\u0022left\\\\\\u0022)\\\\ndf.head(2)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:24:03.262493Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:24:03.262853Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:24:03.289655Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:24:03.26282Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:24:03.288811Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Create train and validation split.\\\\ntrain_df, valid_df = train_test_split(df, test_size=0.15, random_state=42, stratify=df.image_level.values)\\\\n\\\\ntrain_df.loc[:, \\u0027split\\u0027] = \\u0027train\\u0027\\\\nvalid_df.loc[:, \\u0027split\\u0027] = \\u0027valid\\u0027\\\\n\\\\ndf = pd.concat([train_df, valid_df]).reset_index(drop=True)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:24:05.563262Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:24:05.563585Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:24:05.594924Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:24:05.563553Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:24:05.594085Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022print(f\\u0027Size of dataset: {len(df)}, training images: {len(train_df)}. validation images: {len(valid_df)}\\u0027)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:24:07.863054Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:24:07.863399Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:24:07.868391Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:24:07.863369Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:24:07.867286Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\\\nos.makedirs(\\u0027working/tmp/covid/images/train\\u0027, exist_ok=True)\\\\nos.makedirs(\\u0027working/tmp/covid/images/valid\\u0027, exist_ok=True)\\\\n\\\\nos.makedirs(\\u0027working/tmp/covid/labels/train\\u0027, exist_ok=True)\\\\nos.makedirs(\\u0027working/tmp/covid/labels/valid\\u0027, exist_ok=True)\\\\n\\\\n! ls tmp/covid/images\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:25:55.594975Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:25:55.595341Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:25:56.22716Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:25:55.595309Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:25:56.226264Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022%cd ..\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:27:25.292162Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:27:25.292496Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:27:25.299579Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:27:25.292467Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:27:25.298515Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\u0022,\\u0022metadata\\u0022:{},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Move the images to relevant split folder.\\\\nfor i in tqdm(range(len(df))):\\\\n    row = df.loc[i]\\\\n    if row.split == \\u0027train\\u0027 and row.image_level==\\u0027opacity\\u0027:\\\\n        copyfile(row.path, f\\u0027working/tmp/covid/images/train/{row.id}.jpg\\u0027)\\\\n    elif row.split == \\u0027valid\\u0027 and row.image_level==\\u0027opacity\\u0027:\\\\n        copyfile(row.path, f\\u0027working/tmp/covid/images/valid/{row.id}.jpg\\u0027)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:27:36.281211Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:27:36.281533Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:28:04.897253Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:27:36.281503Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:28:04.896128Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Move the images to relevant split folder.\\\\nfor i in tqdm(range(len(df))):\\\\n    row = df.loc[i]\\\\n    if row.split == \\u0027train\\u0027:\\\\n        copyfile(row.path, f\\u0027tmp/covid/images/train/{row.id}.jpg\\u0027)\\\\n    else:\\\\n        copyfile(row.path, f\\u0027tmp/covid/images/valid/{row.id}.jpg\\u0027)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T13:41:02.291505Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T13:41:02.291934Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T13:41:08.73535Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T13:41:02.291897Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T13:41:08.733502Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Create .yaml file \\\\nimport yaml\\\\n\\\\ndata_yaml = dict(\\\\n    train = \\u0027../covid/images/train\\u0027,\\\\n    val = \\u0027../covid/images/valid\\u0027,\\\\n    nc = 2,\\\\n    names = [\\u0027none\\u0027,\\u0027opacity\\u0027]\\\\n)\\\\n\\\\n# Note that I am creating the file in the yolov5/data/ directory.\\\\nwith open(\\u0027working/tmp/yolov5/data/data.yaml\\u0027, \\u0027w\\u0027) as outfile:\\\\n    yaml.dump(data_yaml, outfile, default_flow_style=True)\\\\n    \\\\n%cat working/tmp/yolov5/data/data.yaml\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:29:28.456491Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:29:28.456831Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:29:29.092099Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:29:28.456799Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:29:29.091136Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022with open(\\u0027/kaggle/working//tmp/covid/labels/train/000a312787f2.txt\\u0027,\\u0027r\\u0027) as f:\\\\n    print(f.read())\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:29:41.703356Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:29:41.703692Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:29:41.728614Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:29:41.703659Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:29:41.726744Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Get the raw bounding box by parsing the row value of the label column.\\\\n# Ref: https://www.kaggle.com/yujiariyasu/plot-3positive-classes\\\\ndef get_bbox(row):\\\\n    bboxes = []\\\\n    bbox = []\\\\n    for i, l in enumerate(row.label.split(\\u0027 \\u0027)):\\\\n        if (i % 6 == 0) | (i % 6 == 1):\\\\n            continue\\\\n        bbox.append(float(l))\\\\n        if i % 6 == 5:\\\\n            bboxes.append(bbox)\\\\n            bbox = []  \\\\n            \\\\n    return bboxes\\\\n\\\\n# Scale the bounding boxes according to the size of the resized image. \\\\ndef scale_bbox(row, bboxes):\\\\n    # Get scaling factor\\\\n    scale_x = IMG_SIZE/row.dim1\\\\n    scale_y = IMG_SIZE/row.dim0\\\\n    \\\\n    scaled_bboxes = []\\\\n    for bbox in bboxes:\\\\n        x = int(np.round(bbox[0]*scale_x, 4))\\\\n        y = int(np.round(bbox[1]*scale_y, 4))\\\\n        x1 = int(np.round(bbox[2]*(scale_x), 4))\\\\n        y1= int(np.round(bbox[3]*scale_y, 4))\\\\n\\\\n        scaled_bboxes.append([x, y, x1, y1]) # xmin, ymin, xmax, ymax\\\\n        \\\\n    return scaled_bboxes\\\\n\\\\n# Convert the bounding boxes in YOLO format.\\\\ndef get_yolo_format_bbox(img_w, img_h, bboxes):\\\\n    yolo_boxes = []\\\\n    for bbox in bboxes:\\\\n        w = bbox[2] - bbox[0] # xmax - xmin\\\\n        h = bbox[3] - bbox[1] # ymax - ymin\\\\n        xc = bbox[0] + int(np.round(w/2)) # xmin + width/2\\\\n        yc = bbox[1] + int(np.round(h/2)) # ymin + height/2\\\\n        \\\\n        yolo_boxes.append([xc/img_w, yc/img_h, w/img_w, h/img_h]) # x_center y_center width height\\\\n    \\\\n    return yolo_boxes\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:29:45.077249Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:29:45.077599Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:29:45.089712Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:29:45.077558Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:29:45.088866Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Prepare the txt files for bounding box\\\\nfor i in tqdm(range(len(df))):\\\\n    row = df.loc[i]\\\\n    # Get image id\\\\n    img_id = row.id\\\\n    # Get split\\\\n    split = row.split\\\\n    # Get image-level label\\\\n    label = row.image_level\\\\n    \\\\n    if row.split==\\u0027train\\u0027:\\\\n        file_name = f\\u0027working/tmp/covid/labels/train/{row.id}.txt\\u0027\\\\n    else:\\\\n        file_name = f\\u0027working/tmp/covid/labels/valid/{row.id}.txt\\u0027\\\\n        \\\\n    \\\\n    if label==\\u0027opacity\\u0027:\\\\n        # Get bboxes\\\\n        bboxes = get_bbox(row)\\\\n        # Scale bounding boxes\\\\n        scale_bboxes = scale_bbox(row, bboxes)\\\\n        # Format for YOLOv5\\\\n        yolo_bboxes = get_yolo_format_bbox(IMG_SIZE, IMG_SIZE, scale_bboxes)\\\\n        \\\\n        with open(file_name, \\u0027w\\u0027) as f:\\\\n            for bbox in yolo_bboxes:\\\\n                bbox = [1]+bbox\\\\n                bbox = [str(i) for i in bbox]\\\\n                bbox = \\u0027 \\u0027.join(bbox)\\\\n                f.write(bbox)\\\\n                f.write(\\u0027\\\\\\\\n\\u0027)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:30:01.664754Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:30:01.665129Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:30:04.361189Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:30:01.665091Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:30:04.360192Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022bbox\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:30:12.10387Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:30:12.104376Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:30:12.109936Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:30:12.104338Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:30:12.108931Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022%cd working/tmp/yolov5/\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:30:49.117336Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:30:49.117668Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:30:49.125257Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:30:49.117635Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:30:49.124137Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022ls\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:30:37.831091Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:30:37.831442Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:30:38.460343Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:30:37.831411Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:30:38.459302Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022!python train.py --img {IMG_SIZE} \\\\\\\\\\\\n                 --batch {BATCH_SIZE} \\\\\\\\\\\\n                 --epochs {EPOCHS} \\\\\\\\\\\\n                 --data data.yaml \\\\\\\\\\\\n                 --weights yolov5l.pt \\\\\\\\\\\\n                 --save_period 1\\\\\\\\\\\\n                 --project kaggle-siim-covid-yolov5l-t3-clas2\\\\n                 \\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T10:27:33.521412Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T10:27:33.521782Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T11:35:12.529821Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T10:27:33.521735Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T11:35:12.528857Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022os.listdir(\\u0027kaggle-siim-covid-yolov5l-t3-clas2/exp/weights\\u0027)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T11:36:03.55081Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T11:36:03.551188Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T11:36:03.558177Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T11:36:03.551151Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T11:36:03.557174Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022%cd ..\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:36:15.843947Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:36:15.844313Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:36:15.851046Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:36:15.84428Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:36:15.850111Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022%cd yolov5\\\\n%ls\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:40:12.528277Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:40:12.528625Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:40:13.168792Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:40:12.52859Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:40:13.167776Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022MODEL_PATH = \\\\\\u0022artifacts/run_2xb4vetk_model:v29/best.pt\\\\\\u0022\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:40:17.366627Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:40:17.366966Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:40:17.373637Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:40:17.366932Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:40:17.372853Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# MODEL_PATH = \\u0027kaggle-siim-covid-yolov5l-t3-clas2/exp/weights/best.pt\\u0027\\\\nTEST_PATH = \\u0027../../../input/siim-covid19-resized-to-512px-png/test/\\u0027\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:40:17.611852Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:40:17.612212Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:40:17.616189Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:40:17.61218Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:40:17.615038Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022!python detect.py --weights {MODEL_PATH} \\\\\\\\\\\\n                  --source {TEST_PATH} \\\\\\\\\\\\n                  --img {IMG_SIZE} \\\\\\\\\\\\n                  --conf 0.3 \\\\\\\\\\\\n                  --iou-thres 0.5 \\\\\\\\\\\\n                  --max-det 3 \\\\\\\\\\\\n                  --save-txt \\\\\\\\\\\\n                  --save-conf\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:40:20.354618Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:40:20.354948Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:41:42.486417Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:40:20.354917Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:41:42.48547Z\\u0022},\\u0022collapsed\\u0022:true,\\u0022jupyter\\u0022:{\\u0022outputs_hidden\\u0022:true},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022!python train.py --resume wandb-artifact://39ajinkya/kaggle-siim-covid-yolov5l-t3-clas2/2xb4vetk\\\\n                 \\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:36:18.982488Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:36:18.982817Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:36:45.626952Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:36:18.982784Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:36:45.62601Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022os.listdir(\\u0027/kaggle/tmp/yolov5/runs/detect/exp/labels\\u0027)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T11:59:09.57632Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T11:59:09.576675Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T11:59:09.585789Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T11:59:09.576639Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T11:59:09.584295Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022PRED_PATH = \\u0027runs/detect/exp3/labels\\u0027\\\\n!ls {PRED_PATH}\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:42:22.617996Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:42:22.618384Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:42:23.256272Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:42:22.618347Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:42:23.2553Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Visualize predicted coordinates.\\\\n%cat runs/detect/exp3/labels/ba91d37ee459.txt\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:42:33.85355Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:42:33.853914Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:42:34.489431Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:42:33.853881Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:42:34.488496Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022prediction_files = os.listdir(PRED_PATH)\\\\nprint(\\u0027Number of test images predicted as opaque: \\u0027, len(prediction_files))\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:42:42.542727Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:42:42.543087Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:42:42.54904Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:42:42.543046Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:42:42.548178Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# The submisison requires xmin, ymin, xmax, ymax format. \\\\n# YOLOv5 returns x_center, y_center, width, height\\\\ndef correct_bbox_format(bboxes):\\\\n    correct_bboxes = []\\\\n    for b in bboxes:\\\\n        xc, yc = int(np.round(b[0]*IMG_SIZE)), int(np.round(b[1]*IMG_SIZE))\\\\n        w, h = int(np.round(b[2]*IMG_SIZE)), int(np.round(b[3]*IMG_SIZE))\\\\n\\\\n        xmin = xc - int(np.round(w/2))\\\\n        xmax = xc + int(np.round(w/2))\\\\n        ymin = yc - int(np.round(h/2))\\\\n        ymax = yc + int(np.round(h/2))\\\\n        \\\\n        correct_bboxes.append([xmin, xmax, ymin, ymax])\\\\n        \\\\n    return correct_bboxes\\\\n\\\\n# Read the txt file generated by YOLOv5 during inference and extract \\\\n# confidence and bounding box coordinates.\\\\ndef get_conf_bboxes(file_path):\\\\n    confidence = []\\\\n    bboxes = []\\\\n    with open(file_path, \\u0027r\\u0027) as file:\\\\n        for line in file:\\\\n            preds = line.strip(\\u0027\\\\\\\\n\\u0027).split(\\u0027 \\u0027)\\\\n            preds = list(map(float, preds))\\\\n            confidence.append(preds[-1])\\\\n            bboxes.append(preds[1:-1])\\\\n    return confidence, bboxes\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:42:45.485146Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:42:45.485484Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:42:45.494345Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:42:45.485456Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:42:45.493511Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Read the submisison file\\\\nsub_df = pd.read_csv(\\u0027/kaggle/input/siim-covid19-detection/sample_submission.csv\\u0027)\\\\nsub_df.tail()\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:42:48.556204Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:42:48.556524Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:42:48.576854Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:42:48.556495Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:42:48.575884Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# Prediction loop for submission\\\\npredictions = []\\\\n\\\\nfor i in tqdm(range(len(sub_df))):\\\\n    row = sub_df.loc[i]\\\\n    id_name = row.id.split(\\u0027_\\u0027)[0]\\\\n    id_level = row.id.split(\\u0027_\\u0027)[-1]\\\\n    \\\\n    if id_level == \\u0027study\\u0027:\\\\n        # do study-level classification\\\\n        predictions.append(\\\\\\u0022Negative 1 0 0 1 1\\\\\\u0022) # dummy prediction\\\\n        \\\\n    elif id_level == \\u0027image\\u0027:\\\\n        # we can do image-level classification here.\\\\n        # also we can rely on the object detector\\u0027s classification head.\\\\n        # for this example submisison we will use YOLO\\u0027s classification head. \\\\n        # since we already ran the inference we know which test images belong to opacity.\\\\n        if f\\u0027{id_name}.txt\\u0027 in prediction_files:\\\\n            # opacity label\\\\n            confidence, bboxes = get_conf_bboxes(f\\u0027{PRED_PATH}/{id_name}.txt\\u0027)\\\\n            bboxes = correct_bbox_format(bboxes)\\\\n            pred_string = \\u0027\\u0027\\\\n            for j, conf in enumerate(confidence):\\\\n                pred_string += f\\u0027opacity {conf} \\u0027 + \\u0027 \\u0027.join(map(str, bboxes[j])) + \\u0027 \\u0027\\\\n            predictions.append(pred_string[:-1]) \\\\n        else:\\\\n            predictions.append(\\\\\\u0022None 1 0 0 1 1\\\\\\u0022)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:42:54.048202Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:42:54.048521Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:42:54.491177Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:42:54.048491Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:42:54.490171Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022sub_df[\\u0027PredictionString\\u0027] = predictions\\\\nsub_df.to_csv(\\u0027/kaggle/working/submission.csv\\u0027, index=False)\\\\nsub_df.tail()\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T15:43:03.759536Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T15:43:03.759873Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T15:43:04.110805Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T15:43:03.759841Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T15:43:04.109982Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022sub_df.loc[sub_df[\\u0027PredictionString\\u0027] == \\\\\\u0022None 1 0 0 1 1\\\\\\u0022]\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T13:23:13.229827Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T13:23:13.230283Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T13:23:13.304521Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T13:23:13.230246Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T13:23:13.302739Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022os.listdir(\\u0027/kaggle/working\\u0027)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-23T12:48:15.82343Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-23T12:48:15.823801Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-23T12:48:15.828991Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-23T12:48:15.82375Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-23T12:48:15.82814Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022markdown\\u0022,\\u0022source\\u0022:\\u0022creating a coco format dataset.\\u0022,\\u0022metadata\\u0022:{}},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# #creating a coco format dataset.\\\\n# df.iloc[0].path\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:02:16.034664Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:02:16.03501Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:02:16.041594Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:02:16.034979Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:02:16.040506Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# annotation = dict()\\\\n\\\\n# for i in tqdm(range(len(df))):\\\\n#     row = df.loc[i]\\\\n#     # Get image id\\\\n#     img_id = row.id\\\\n#     # Get split\\\\n#     split = row.split\\\\n#     # Get image-level label\\\\n#     label = row.image_level\\\\n    \\\\n#     file_name = row.path\\\\n        \\\\n    \\\\n#     if label==\\u0027opacity\\u0027:\\\\n#         # Get bboxes\\\\n#         bboxes = get_bbox(row)\\\\n#         # Scale bounding boxes\\\\n#         scale_bboxes = scale_bbox(row, bboxes)\\\\n#         # Format for YOLOv5\\\\n#         yolo_bboxes = get_yolo_format_bbox(IMG_SIZE, IMG_SIZE, scale_bboxes)\\\\n        \\\\n#         l = []\\\\n#         for bbox in yolo_bboxes:\\\\n#             l.append({\\u0027bbox\\u0027:bbox,\\u0027label\\u0027:\\u0027opacity\\u0027})\\\\n#         annotation[file_name] = l\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:23:25.924899Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:23:25.925238Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:23:27.853252Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:23:25.925209Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:23:27.852401Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# annotation\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:23:29.554938Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:23:29.55525Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:23:29.793865Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:23:29.555218Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:23:29.793033Z\\u0022},\\u0022collapsed\\u0022:true,\\u0022jupyter\\u0022:{\\u0022outputs_hidden\\u0022:true},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# del dataset\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:10:27.635044Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:10:27.635371Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:10:27.63875Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:10:27.63534Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:10:27.637847Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:17:22.02986Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:17:22.030192Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:17:22.035232Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:17:22.030161Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:17:22.034351Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# image_path = \\u0027kaggle/input/siim-covid19-resized-to-256px-jpg/train/*\\u0027\\\\n# glob.glob(image_path)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:19:32.579709Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:19:32.580021Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:19:32.624363Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:19:32.579991Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:19:32.623434Z\\u0022},\\u0022collapsed\\u0022:true,\\u0022jupyter\\u0022:{\\u0022outputs_hidden\\u0022:true},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# import glob\\\\n# import fiftyone as fo\\\\n\\\\n# image_path = \\u0027kaggle/input/siim-covid19-resized-to-256px-jpg/train/*\\u0027\\\\n\\\\n# # Ex: your custom label format\\\\n\\\\n# # Create dataset\\\\n# dataset = fo.Dataset(name=\\\\\\u0022siim-covid-19-6\\\\\\u0022)\\\\n\\\\n# # Persist the dataset on disk in order to \\\\n# # be able to load it in one line in the future\\\\n# dataset.persistent = True\\\\n\\\\n# # Add your samples to the dataset\\\\n# for filepath in annotation:\\\\n#     sample = fo.Sample(filepath=filepath)\\\\n#     sample.tags.append(\\u0027images\\u0027)\\\\n#     # Convert detections to FiftyOne format\\\\n#     detections = []\\\\n#     for obj in annotation[filepath]:\\\\n#         label = obj[\\\\\\u0022label\\\\\\u0022]\\\\n\\\\n#         # Bounding box coordinates should be relative values\\\\n#         # in [0, 1] in the following format:\\\\n#         # [top-left-x, top-left-y, width, height]\\\\n#         bounding_box = obj[\\\\\\u0022bbox\\\\\\u0022]\\\\n        \\\\n#         detections.append(\\\\n#             fo.Detection(label=label, bounding_box=bounding_box)\\\\n#         )\\\\n\\\\n#     # Store detections in a field name of your choice\\\\n#     sample[\\\\\\u0022train\\\\\\u0022] = fo.Detections(detections=detections)\\\\n\\\\n#     dataset.add_sample(sample)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:25:35.59564Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:25:35.595953Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:25:45.163808Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:25:35.595917Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:25:45.162775Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# view = dataset.match_tags(\\u0027images\\u0027)\\\\n# for sample in view:\\\\n#     print(sample)\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:25:49.03443Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:25:49.034752Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:26:10.008087Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:25:49.034721Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:26:10.007317Z\\u0022},\\u0022collapsed\\u0022:true,\\u0022jupyter\\u0022:{\\u0022outputs_hidden\\u0022:true},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# export_dir = \\\\\\u0022/path/for/coco-detection-dataset-1\\\\\\u0022\\\\n# label_field = \\\\\\u0022ground_truth\\\\\\u0022  # for example\\\\n\\\\n# # Export the dataset\\\\n# dataset.export(\\\\n#     export_dir=export_dir,\\\\n#     dataset_type=fo.types.COCODetectionDataset,\\\\n#     label_field=label_field,\\\\n# )\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T13:06:03.990294Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T13:06:03.99067Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T13:06:04.001856Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T13:06:03.990638Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T13:06:04.000818Z\\u0022},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022# !pip install fiftyone\\u0022,\\u0022metadata\\u0022:{\\u0022execution\\u0022:{\\u0022iopub.status.busy\\u0022:\\u00222021-06-18T12:50:53.42484Z\\u0022,\\u0022iopub.execute_input\\u0022:\\u00222021-06-18T12:50:53.42518Z\\u0022,\\u0022iopub.status.idle\\u0022:\\u00222021-06-18T12:51:19.961086Z\\u0022,\\u0022shell.execute_reply.started\\u0022:\\u00222021-06-18T12:50:53.425148Z\\u0022,\\u0022shell.execute_reply\\u0022:\\u00222021-06-18T12:51:19.960121Z\\u0022},\\u0022collapsed\\u0022:true,\\u0022jupyter\\u0022:{\\u0022outputs_hidden\\u0022:true},\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\u0022,\\u0022metadata\\u0022:{\\u0022trusted\\u0022:true},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\u0022,\\u0022metadata\\u0022:{},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\u0022,\\u0022metadata\\u0022:{},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]},{\\u0022cell_type\\u0022:\\u0022code\\u0022,\\u0022source\\u0022:\\u0022\\u0022,\\u0022metadata\\u0022:{},\\u0022execution_count\\u0022:null,\\u0022outputs\\u0022:[]}]}\",\"dateCreated\":\"2021-06-23T16:43:10.6254824Z\"},\"resources\":null,\"isolatorResults\":\"\\u003cresults\\u003e\\u003cexit_code\\u003e0\\u003c/exit_code\\u003e\\u003cinvalid_path_errors\\u003eFalse\\u003c/invalid_path_errors\\u003e\\u003cout_of_memory\\u003eFalse\\u003c/out_of_memory\\u003e\\u003crun_time_seconds\\u003e56.2550055\\u003c/run_time_seconds\\u003e\\u003csucceeded\\u003eTrue\\u003c/succeeded\\u003e\\u003ctimeout_exceeded\\u003eFalse\\u003c/timeout_exceeded\\u003e\\u003cused_all_space\\u003eFalse\\u003c/used_all_space\\u003e\\u003cwas_killed\\u003eFalse\\u003c/was_killed\\u003e\\u003cdocker_image_name\\u003egcr.io/kaggle-private-byod/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794\\u003c/docker_image_name\\u003e\\u003cdocker_image_digest\\u003e046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794\\u003c/docker_image_digest\\u003e\\u003cdocker_image_id\\u003esha256:f8509c5954373e53c6dcd069dca18ab94cfea4c5755c493c0b504a7e50a409ac\\u003c/docker_image_id\\u003e\\u003coutput_size_bytes\\u003e0\\u003c/output_size_bytes\\u003e\\u003c/results\\u003e\",\"runInfo\":{\"dockerfileUrl\":\"https://github.com/Kaggle/docker-python/blob/master/gpu.Dockerfile\",\"dockerHubUrl\":\"https://gcr.io/kaggle-gpu-images/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794\",\"dockerImageDigest\":\"046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794\",\"dockerImageId\":\"sha256:f8509c5954373e53c6dcd069dca18ab94cfea4c5755c493c0b504a7e50a409ac\",\"dockerImageName\":\"gcr.io/kaggle-gpu-images/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794\",\"diskKbFree\":0,\"failureMessage\":null,\"exitCode\":0,\"queuedSeconds\":0,\"outputSizeBytes\":0,\"runTimeSeconds\":56.2550055,\"usedAllSpace\":false,\"timeoutExceeded\":false,\"isValidStatus\":false,\"wasGpuEnabled\":false,\"wasInternetEnabled\":false,\"outOfMemory\":false,\"invalidPathErrors\":false,\"succeeded\":true,\"wasKilled\":false},\"dockerImageVersionId\":30097,\"usedCustomDockerImage\":false,\"dataSources\":[{\"sourceType\":\"Competition\",\"sourceId\":26680,\"datasetId\":null,\"databundleVersionId\":2283525,\"mountSlug\":\"siim-covid19-detection\"},{\"sourceType\":\"DatasetVersion\",\"sourceId\":1666454,\"datasetId\":986800,\"databundleVersionId\":null,\"mountSlug\":\"kerasapplications\"},{\"sourceType\":\"DatasetVersion\",\"sourceId\":2246642,\"datasetId\":1351041,\"databundleVersionId\":null,\"mountSlug\":\"siim-covid19-resized-to-512px-png\"}],\"useNewKernelsBackend\":true,\"isGpuEnabled\":true,\"isTpuEnabled\":false,\"acceleratorType\":\"gpu\",\"isInternetEnabled\":true,\"userPlan\":\"free\"},\"author\":{\"id\":7528647,\"displayName\":\"AJINKYA DESHPANDE\",\"email\":null,\"editedEmail\":null,\"editedEmailCode\":null,\"userName\":\"ajinkyadeshpande39\",\"thumbnailUrl\":\"https://storage.googleapis.com/kaggle-avatars/thumbnails/default-thumb.png\",\"profileUrl\":\"/ajinkyadeshpande39\",\"registerDate\":\"0001-01-01T00:00:00Z\",\"lastVisitDate\":\"0001-01-01T00:00:00Z\",\"statusId\":0,\"performanceTier\":1,\"grandfatheredCompetitionTier\":null,\"userLogins\":null,\"groupIds\":null,\"duplicateUsers\":null,\"hasPhoneVerifications\":false,\"failedNerdchas\":0,\"hasPendingNerdcha\":false,\"deleteRequests\":null,\"isAdmin\":false,\"isKaggleBot\":false,\"isAnonymous\":false,\"canAct\":false,\"canBeSeen\":false,\"thumbnailName\":null,\"isPhoneVerified\":false},\"baseUrl\":\"/ajinkyadeshpande39/yolo-notebook\",\"collaborators\":{\"owner\":{\"userId\":7528647,\"groupId\":null,\"groupMemberCount\":null,\"profileUrl\":\"/ajinkyadeshpande39\",\"thumbnailUrl\":\"https://storage.googleapis.com/kaggle-avatars/thumbnails/default-thumb.png\",\"name\":\"AJINKYA DESHPANDE\",\"slug\":\"ajinkyadeshpande39\",\"userTier\":1,\"joinDate\":null,\"type\":\"owner\",\"isUser\":true,\"isGroup\":false},\"collaborators\":[]},\"initialTab\":\"\",\"log\":\"[{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:12.362944073,\\u0022data\\u0022:\\u0022/kaggle\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:12.79057057,\\u0022data\\u0022:\\u0022/kaggle/tmp\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:13.53163512,\\u0022data\\u0022:\\u0022/kaggle/tmp/tmp\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:14.368295166,\\u0022data\\u0022:\\u0022Cloning into \\u0027yolov5\\u0027...\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:15.485036397,\\u0022data\\u0022:\\u0022remote: Enumerating objects: 7297, done.\\\\u001b[K\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:15.485075115,\\u0022data\\u0022:\\u0022remote: Counting objects:   0% (1/419)\\\\u001b[K\\\\rremote: Counting objects:   1% (5/419)\\\\u001b[K\\\\rremote: Counting objects:   2% (9/419)\\\\u001b[K\\\\rremote: Counting objects:   3% (13/419)\\\\u001b[K\\\\rremote: Counting objects:   4% (17/419)\\\\u001b[K\\\\rremote: Counting objects:   5% (21/419)\\\\u001b[K\\\\rremote: Counting objects:   6% (26/419)\\\\u001b[K\\\\rremote: Counting objects:   7% (30/419)\\\\u001b[K\\\\rremote: Counting objects:   8% (34/419)\\\\u001b[K\\\\rremote: Counting objects:   9% (38/419)\\\\u001b[K\\\\rremote: Counting objects:  10% (42/419)\\\\u001b[K\\\\rremote: Counting objects:  11% (47/419)\\\\u001b[K\\\\rremote: Counting objects:  12% (51/419)\\\\u001b[K\\\\rremote: Counting objects:  13% (55/419)\\\\u001b[K\\\\rremote: Counting objects:  14% (59/419)\\\\u001b[K\\\\rremote: Counting objects:  15% (63/419)\\\\u001b[K\\\\rremote: Counting objects:  16% (68/419)\\\\u001b[K\\\\rremote: Counting objects:  17% (72/419)\\\\u001b[K\\\\rremote: Counting objects:  18% (76/419)\\\\u001b[K\\\\rremote: Counting objects:  19% (80/419)\\\\u001b[K\\\\rremote: Counting objects:  20% (84/419)\\\\u001b[K\\\\rremote: Counting objects:  21% (88/419)\\\\u001b[K\\\\rremote: Counting objects:  22% (93/419)\\\\u001b[K\\\\rremote: Counting objects:  23% (97/419)\\\\u001b[K\\\\rremote: Counting objects:  24% (101/419)\\\\u001b[K\\\\rremote: Counting objects:  25% (105/419)\\\\u001b[K\\\\rremote: Counting objects:  26% (109/419)\\\\u001b[K\\\\rremote: Counting objects:  27% (114/419)\\\\u001b[K\\\\rremote: Counting objects:  28% (118/419)\\\\u001b[K\\\\rremote: Counting objects:  29% (122/419)\\\\u001b[K\\\\rremote: Counting objects:  30% (126/419)\\\\u001b[K\\\\rremote: Counting objects:  31% (130/419)\\\\u001b[K\\\\rremote: Counting objects:  32% (135/419)\\\\u001b[K\\\\rremote: Counting objects:  33% (139/419)\\\\u001b[K\\\\rremote: Counting objects:  34% (143/419)\\\\u001b[K\\\\rremote: Counting objects:  35% (147/419)\\\\u001b[K\\\\rremote: Counting objects:  36% (151/419)\\\\u001b[K\\\\rremote: Counting objects:  37% (156/419)\\\\u001b[K\\\\rremote: Counting objects:  38% (160/419)\\\\u001b[K\\\\rremote: Counting objects:  39% (164/419)\\\\u001b[K\\\\rremote: Counting objects:  40% (168/419)\\\\u001b[K\\\\rremote: Counting objects:  41% (172/419)\\\\u001b[K\\\\rremote: Counting objects:  42% (176/419)\\\\u001b[K\\\\rremote: Counting objects:  43% (181/419)\\\\u001b[K\\\\rremote: Counting objects:  44% (185/419)\\\\u001b[K\\\\rremote: Counting objects:  45% (189/419)\\\\u001b[K\\\\rremote: Counting objects:  46% (193/419)\\\\u001b[K\\\\rremote: Counting objects:  47% (197/419)\\\\u001b[K\\\\rremote: Counting objects:  48% (202/419)\\\\u001b[K\\\\rremote: Counting objects:  49% (206/419)\\\\u001b[K\\\\rremote: Counting objects:  50% (210/419)\\\\u001b[K\\\\rremote: Counting objects:  51% (214/419)\\\\u001b[K\\\\rremote: Counting objects:  52% (218/419)\\\\u001b[K\\\\rremote: Counting objects:  53% (223/419)\\\\u001b[K\\\\rremote: Counting objects:  54% (227/419)\\\\u001b[K\\\\rremote: Counting objects:  55% (231/419)\\\\u001b[K\\\\rremote: Counting objects:  56% (235/419)\\\\u001b[K\\\\rremote: Counting objects:  57% (239/419)\\\\u001b[K\\\\rremote: Counting objects:  58% (244/419)\\\\u001b[K\\\\rremote: Counting objects:  59% (248/419)\\\\u001b[K\\\\rremote: Counting objects:  60% (252/419)\\\\u001b[K\\\\rremote: Counting objects:  61% (256/419)\\\\u001b[K\\\\rremote: Counting objects:  62% (260/419)\\\\u001b[K\\\\rremote: Counting objects:  63% (264/419)\\\\u001b[K\\\\rremote: Counting objects:  64% (269/419)\\\\u001b[K\\\\rremote: Counting objects:  65% (273/419)\\\\u001b[K\\\\rremote: Counting objects:  66% (277/419)\\\\u001b[K\\\\rremote: Counting objects:  67% (281/419)\\\\u001b[K\\\\rremote: Counting objects:  68% (285/419)\\\\u001b[K\\\\rremote: Counting objects:  69% (290/419)\\\\u001b[K\\\\rremote: Counting objects:  70% (294/419)\\\\u001b[K\\\\rremote: Counting objects:  71% (298/419)\\\\u001b[K\\\\rremote: Counting objects:  72% (302/419)\\\\u001b[K\\\\rremote: Counting objects:  73% (306/419)\\\\u001b[K\\\\rremote: Counting objects:  74% (311/419)\\\\u001b[K\\\\rremote: Counting objects:  75% (315/419)\\\\u001b[K\\\\rremote: Counting objects:  76% (319/419)\\\\u001b[K\\\\rremote: Counting objects:  77% (323/419)\\\\u001b[K\\\\rremote: Counting objects:  78% (327/419)\\\\u001b[K\\\\rremote: Counting objects:  79% (332/419)\\\\u001b[K\\\\rremote: Counting objects:  80% (336/419)\\\\u001b[K\\\\rremote: Counting objects:  81% (340/419)\\\\u001b[K\\\\rremote: Counting objects:  82% (344/419)\\\\u001b[K\\\\rremote: Counting objects:  83% (348/419)\\\\u001b[K\\\\rremote: Counting objects:  84% (352/419)\\\\u001b[K\\\\rremote: Counting objects:  85% (357/419)\\\\u001b[K\\\\rremote: Counting objects:  86% (361/419)\\\\u001b[K\\\\rremote: Counting objects:  87% (365/419)\\\\u001b[K\\\\rremote: Counting objects:  88% (369/419)\\\\u001b[K\\\\rremote: Counting objects:  89% (373/419)\\\\u001b[K\\\\rremote: Counting objects:  90% (378/419)\\\\u001b[K\\\\rremote: Counting objects:  91% (382/419)\\\\u001b[K\\\\rremote: Counting objects:  92% (386/419)\\\\u001b[K\\\\rremote: Counting objects:  93% (390/419)\\\\u001b[K\\\\rremote: Counting objects:  94% (394/419)\\\\u001b[K\\\\rremote: Counting objects:  95% (399/419)\\\\u001b[K\\\\rremote: Counting objects:  96% (403/419)\\\\u001b[K\\\\rremote: Counting objects:  97% (407/419)\\\\u001b[K\\\\rremote: Counting objects:  98% (411/419)\\\\u001b[K\\\\rremote: Counting objects:  99% (415/419)\\\\u001b[K\\\\rremote: Counting objects: 100% (419/419)\\\\u001b[K\\\\rremote: Counting objects: 100% (419/419), done.\\\\u001b[K\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:15.535356874,\\u0022data\\u0022:\\u0022remote: Compressing objects:   0% (1/269)\\\\u001b[K\\\\rremote: Compressing objects:   1% (3/269)\\\\u001b[K\\\\rremote: Compressing objects:   2% (6/269)\\\\u001b[K\\\\rremote: Compressing objects:   3% (9/269)\\\\u001b[K\\\\rremote: Compressing objects:   4% (11/269)\\\\u001b[K\\\\rremote: Compressing objects:   5% (14/269)\\\\u001b[K\\\\rremote: Compressing objects:   6% (17/269)\\\\u001b[K\\\\rremote: Compressing objects:   7% (19/269)\\\\u001b[K\\\\rremote: Compressing objects:   8% (22/269)\\\\u001b[K\\\\rremote: Compressing objects:   9% (25/269)\\\\u001b[K\\\\rremote: Compressing objects:  10% (27/269)\\\\u001b[K\\\\rremote: Compressing objects:  11% (30/269)\\\\u001b[K\\\\rremote: Compressing objects:  12% (33/269)\\\\u001b[K\\\\rremote: Compressing objects:  13% (35/269)\\\\u001b[K\\\\rremote: Compressing objects:  14% (38/269)\\\\u001b[K\\\\rremote: Compressing objects:  15% (41/269)\\\\u001b[K\\\\rremote: Compressing objects:  16% (44/269)\\\\u001b[K\\\\rremote: Compressing objects:  17% (46/269)\\\\u001b[K\\\\rremote: Compressing objects:  18% (49/269)\\\\u001b[K\\\\rremote: Compressing objects:  19% (52/269)\\\\u001b[K\\\\rremote: Compressing objects:  20% (54/269)\\\\u001b[K\\\\rremote: Compressing objects:  21% (57/269)\\\\u001b[K\\\\rremote: Compressing objects:  22% (60/269)\\\\u001b[K\\\\rremote: Compressing objects:  23% (62/269)\\\\u001b[K\\\\rremote: Compressing objects:  24% (65/269)\\\\u001b[K\\\\rremote: Compressing objects:  25% (68/269)\\\\u001b[K\\\\rremote: Compressing objects:  26% (70/269)\\\\u001b[K\\\\rremote: Compressing objects:  27% (73/269)\\\\u001b[K\\\\rremote: Compressing objects:  28% (76/269)\\\\u001b[K\\\\rremote: Compressing objects:  29% (79/269)\\\\u001b[K\\\\rremote: Compressing objects:  30% (81/269)\\\\u001b[K\\\\rremote: Compressing objects:  31% (84/269)\\\\u001b[K\\\\rremote: Compressing objects:  32% (87/269)\\\\u001b[K\\\\rremote: Compressing objects:  33% (89/269)\\\\u001b[K\\\\rremote: Compressing objects:  34% (92/269)\\\\u001b[K\\\\rremote: Compressing objects:  35% (95/269)\\\\u001b[K\\\\rremote: Compressing objects:  36% (97/269)\\\\u001b[K\\\\rremote: Compressing objects:  37% (100/269)\\\\u001b[K\\\\rremote: Compressing objects:  38% (103/269)\\\\u001b[K\\\\rremote: Compressing objects:  39% (105/269)\\\\u001b[K\\\\rremote: Compressing objects:  40% (108/269)\\\\u001b[K\\\\rremote: Compressing objects:  41% (111/269)\\\\u001b[K\\\\rremote: Compressing objects:  42% (113/269)\\\\u001b[K\\\\rremote: Compressing objects:  43% (116/269)\\\\u001b[K\\\\rremote: Compressing objects:  44% (119/269)\\\\u001b[K\\\\rremote: Compressing objects:  45% (122/269)\\\\u001b[K\\\\rremote: Compressing objects:  46% (124/269)\\\\u001b[K\\\\rremote: Compressing objects:  47% (127/269)\\\\u001b[K\\\\rremote: Compressing objects:  48% (130/269)\\\\u001b[K\\\\rremote: Compressing objects:  49% (132/269)\\\\u001b[K\\\\rremote: Compressing objects:  50% (135/269)\\\\u001b[K\\\\rremote: Compressing objects:  51% (138/269)\\\\u001b[K\\\\rremote: Compressing objects:  52% (140/269)\\\\u001b[K\\\\rremote: Compressing objects:  53% (143/269)\\\\u001b[K\\\\rremote: Compressing objects:  54% (146/269)\\\\u001b[K\\\\rremote: Compressing objects:  55% (148/269)\\\\u001b[K\\\\rremote: Compressing objects:  56% (151/269)\\\\u001b[K\\\\rremote: Compressing objects:  57% (154/269)\\\\u001b[K\\\\rremote: Compressing objects:  58% (157/269)\\\\u001b[K\\\\rremote: Compressing objects:  59% (159/269)\\\\u001b[K\\\\rremote: Compressing objects:  60% (162/269)\\\\u001b[K\\\\rremote: Compressing objects:  61% (165/269)\\\\u001b[K\\\\rremote: Compressing objects:  62% (167/269)\\\\u001b[K\\\\rremote: Compressing objects:  63% (170/269)\\\\u001b[K\\\\rremote: Compressing objects:  64% (173/269)\\\\u001b[K\\\\rremote: Compressing objects:  65% (175/269)\\\\u001b[K\\\\rremote: Compressing objects:  66% (178/269)\\\\u001b[K\\\\rremote: Compressing objects:  67% (181/269)\\\\u001b[K\\\\rremote: Compressing objects:  68% (183/269)\\\\u001b[K\\\\rremote: Compressing objects:  69% (186/269)\\\\u001b[K\\\\rremote: Compressing objects:  70% (189/269)\\\\u001b[K\\\\rremote: Compressing objects:  71% (191/269)\\\\u001b[K\\\\rremote: Compressing objects:  72% (194/269)\\\\u001b[K\\\\rremote: Compressing objects:  73% (197/269)\\\\u001b[K\\\\rremote: Compressing objects:  74% (200/269)\\\\u001b[K\\\\rremote: Compressing objects:  75% (202/269)\\\\u001b[K\\\\rremote: Compressing objects:  76% (205/269)\\\\u001b[K\\\\rremote: Compressing objects:  77% (208/269)\\\\u001b[K\\\\rremote: Compressing objects:  78% (210/269)\\\\u001b[K\\\\rremote: Compressing objects:  79% (213/269)\\\\u001b[K\\\\rremote: Compressing objects:  80% (216/269)\\\\u001b[K\\\\rremote: Compressing objects:  81% (218/269)\\\\u001b[K\\\\rremote: Compressing objects:  82% (221/269)\\\\u001b[K\\\\rremote: Compressing objects:  83% (224/269)\\\\u001b[K\\\\rremote: Compressing objects:  84% (226/269)\\\\u001b[K\\\\rremote: Compressing objects:  85% (229/269)\\\\u001b[K\\\\rremote: Compressing objects:  86% (232/269)\\\\u001b[K\\\\rremote: Compressing objects:  87% (235/269)\\\\u001b[K\\\\rremote: Compressing objects:  88% (237/269)\\\\u001b[K\\\\rremote: Compressing objects:  89% (240/269)\\\\u001b[K\\\\rremote: Compressing objects:  90% (243/269)\\\\u001b[K\\\\rremote: Compressing objects:  91% (245/269)\\\\u001b[K\\\\rremote: Compressing objects:  92% (248/269)\\\\u001b[K\\\\rremote: Compressing objects:  93% (251/269)\\\\u001b[K\\\\rremote: Compressing objects:  94% (253/269)\\\\u001b[K\\\\rremote: Compressing objects:  95% (256/269)\\\\u001b[K\\\\rremote: Compressing objects:  96% (259/269)\\\\u001b[K\\\\rremote: Compressing objects:  97% (261/269)\\\\u001b[K\\\\rremote: Compressing objects:  98% (264/269)\\\\u001b[K\\\\rremote: Compressing objects:  99% (267/269)\\\\u001b[K\\\\rremote: Compressing objects: 100% (269/269)\\\\u001b[K\\\\rremote: Compressing objects: 100% (269/269), done.\\\\u001b[K\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:16.148033315,\\u0022data\\u0022:\\u0022Receiving objects:   0% (1/7297)   \\\\rReceiving objects:   1% (73/7297)   \\\\rReceiving objects:   2% (146/7297)   \\\\rReceiving objects:   3% (219/7297)   \\\\rReceiving objects:   4% (292/7297)   \\\\rReceiving objects:   5% (365/7297)   \\\\rReceiving objects:   6% (438/7297)   \\\\rReceiving objects:   7% (511/7297)   \\\\rReceiving objects:   8% (584/7297)   \\\\rReceiving objects:   9% (657/7297)   \\\\rReceiving objects:  10% (730/7297)   \\\\rReceiving objects:  11% (803/7297)   \\\\rReceiving objects:  12% (876/7297)   \\\\rReceiving objects:  13% (949/7297)   \\\\rReceiving objects:  14% (1022/7297)   \\\\rReceiving objects:  15% (1095/7297)   \\\\rReceiving objects:  16% (1168/7297)   \\\\rReceiving objects:  17% (1241/7297)   \\\\rReceiving objects:  18% (1314/7297)   \\\\rReceiving objects:  19% (1387/7297)   \\\\rReceiving objects:  20% (1460/7297)   \\\\rReceiving objects:  21% (1533/7297)   \\\\rReceiving objects:  22% (1606/7297)   \\\\rReceiving objects:  23% (1679/7297)   \\\\rReceiving objects:  24% (1752/7297)   \\\\rReceiving objects:  25% (1825/7297)   \\\\rReceiving objects:  26% (1898/7297)   \\\\rReceiving objects:  27% (1971/7297)   \\\\rReceiving objects:  28% (2044/7297)   \\\\rReceiving objects:  29% (2117/7297)   \\\\rReceiving objects:  30% (2190/7297)   \\\\rReceiving objects:  31% (2263/7297)   \\\\rReceiving objects:  32% (2336/7297)   \\\\rReceiving objects:  33% (2409/7297)   \\\\rReceiving objects:  34% (2481/7297)   \\\\rReceiving objects:  35% (2554/7297)   \\\\rReceiving objects:  36% (2627/7297)   \\\\rReceiving objects:  37% (2700/7297)   \\\\rReceiving objects:  38% (2773/7297)   \\\\rReceiving objects:  39% (2846/7297)   \\\\rReceiving objects:  40% (2919/7297)   \\\\rReceiving objects:  41% (2992/7297)   \\\\rReceiving objects:  42% (3065/7297)   \\\\rReceiving objects:  43% (3138/7297)   \\\\rReceiving objects:  44% (3211/7297)   \\\\rReceiving objects:  45% (3284/7297)   \\\\rReceiving objects:  46% (3357/7297)   \\\\rReceiving objects:  47% (3430/7297)   \\\\rReceiving objects:  48% (3503/7297)   \\\\rReceiving objects:  49% (3576/7297)   \\\\rReceiving objects:  50% (3649/7297)   \\\\rReceiving objects:  51% (3722/7297)   \\\\rReceiving objects:  52% (3795/7297)   \\\\rReceiving objects:  53% (3868/7297)   \\\\rReceiving objects:  54% (3941/7297)   \\\\rReceiving objects:  55% (4014/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  56% (4087/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  57% (4160/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  58% (4233/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  59% (4306/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  60% (4379/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  61% (4452/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  62% (4525/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  63% (4598/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  64% (4671/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  65% (4744/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  66% (4817/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  67% (4889/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  68% (4962/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  69% (5035/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  70% (5108/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  71% (5181/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  72% (5254/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  73% (5327/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  74% (5400/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  75% (5473/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  76% (5546/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  77% (5619/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  78% (5692/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  79% (5765/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  80% (5838/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  81% (5911/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  82% (5984/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  83% (6057/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  84% (6130/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  85% (6203/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  86% (6276/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  87% (6349/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  88% (6422/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  89% (6495/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  90% (6568/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  91% (6641/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  92% (6714/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  93% (6787/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  94% (6860/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  95% (6933/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  96% (7006/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  97% (7079/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects:  98% (7152/7297), 6.98 MiB | 13.94 MiB/s   \\\\rremote: Total 7297 (delta 261), reused 272 (delta 150), pack-reused 6878\\\\u001b[K\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:16.148127025,\\u0022data\\u0022:\\u0022Receiving objects:  99% (7225/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects: 100% (7297/7297), 6.98 MiB | 13.94 MiB/s   \\\\rReceiving objects: 100% (7297/7297), 9.23 MiB | 16.10 MiB/s, done.\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:16.453698587,\\u0022data\\u0022:\\u0022Resolving deltas:   0% (0/4989)   \\\\rResolving deltas:   1% (67/4989)   \\\\rResolving deltas:   2% (101/4989)   \\\\rResolving deltas:   3% (196/4989)   \\\\rResolving deltas:   4% (204/4989)   \\\\rResolving deltas:   5% (257/4989)   \\\\rResolving deltas:   6% (325/4989)   \\\\rResolving deltas:   7% (377/4989)   \\\\rResolving deltas:   8% (420/4989)   \\\\rResolving deltas:   9% (452/4989)   \\\\rResolving deltas:  12% (622/4989)   \\\\rResolving deltas:  13% (657/4989)   \\\\rResolving deltas:  14% (714/4989)   \\\\rResolving deltas:  15% (756/4989)   \\\\rResolving deltas:  17% (859/4989)   \\\\rResolving deltas:  18% (909/4989)   \\\\rResolving deltas:  19% (971/4989)   \\\\rResolving deltas:  20% (1000/4989)   \\\\rResolving deltas:  21% (1069/4989)   \\\\rResolving deltas:  22% (1129/4989)   \\\\rResolving deltas:  23% (1159/4989)   \\\\rResolving deltas:  25% (1258/4989)   \\\\rResolving deltas:  27% (1386/4989)   \\\\rResolving deltas:  28% (1412/4989)   \\\\rResolving deltas:  29% (1495/4989)   \\\\rResolving deltas:  30% (1541/4989)   \\\\rResolving deltas:  31% (1551/4989)   \\\\rResolving deltas:  32% (1601/4989)   \\\\rResolving deltas:  33% (1649/4989)   \\\\rResolving deltas:  34% (1703/4989)   \\\\rResolving deltas:  35% (1757/4989)   \\\\rResolving deltas:  36% (1838/4989)   \\\\rResolving deltas:  37% (1849/4989)   \\\\rResolving deltas:  38% (1909/4989)   \\\\rResolving deltas:  39% (1947/4989)   \\\\rResolving deltas:  40% (1996/4989)   \\\\rResolving deltas:  41% (2064/4989)   \\\\rResolving deltas:  42% (2121/4989)   \\\\rResolving deltas:  43% (2147/4989)   \\\\rResolving deltas:  44% (2217/4989)   \\\\rResolving deltas:  45% (2251/4989)   \\\\rResolving deltas:  46% (2303/4989)   \\\\rResolving deltas:  48% (2415/4989)   \\\\rResolving deltas:  49% (2471/4989)   \\\\rResolving deltas:  50% (2501/4989)   \\\\rResolving deltas:  51% (2559/4989)   \\\\rResolving deltas:  52% (2596/4989)   \\\\rResolving deltas:  53% (2645/4989)   \\\\rResolving deltas:  54% (2696/4989)   \\\\rResolving deltas:  55% (2757/4989)   \\\\rResolving deltas:  56% (2816/4989)   \\\\rResolving deltas:  57% (2866/4989)   \\\\rResolving deltas:  58% (2899/4989)   \\\\rResolving deltas:  59% (2945/4989)   \\\\rResolving deltas:  62% (3128/4989)   \\\\rResolving deltas:  63% (3185/4989)   \\\\rResolving deltas:  64% (3211/4989)   \\\\rResolving deltas:  65% (3252/4989)   \\\\rResolving deltas:  66% (3300/4989)   \\\\rResolving deltas:  67% (3374/4989)   \\\\rResolving deltas:  68% (3399/4989)   \\\\rResolving deltas:  69% (3479/4989)   \\\\rResolving deltas:  70% (3505/4989)   \\\\rResolving deltas:  71% (3546/4989)   \\\\rResolving deltas:  72% (3616/4989)   \\\\rResolving deltas:  73% (3667/4989)   \\\\rResolving deltas:  74% (3692/4989)   \\\\rResolving deltas:  75% (3752/4989)   \\\\rResolving deltas:  76% (3816/4989)   \\\\rResolving deltas:  77% (3850/4989)   \\\\rResolving deltas:  78% (3900/4989)   \\\\rResolving deltas:  79% (3970/4989)   \\\\rResolving deltas:  80% (4000/4989)   \\\\rResolving deltas:  82% (4109/4989)   \\\\rResolving deltas:  83% (4146/4989)   \\\\rResolving deltas:  84% (4192/4989)   \\\\rResolving deltas:  85% (4253/4989)   \\\\rResolving deltas:  86% (4304/4989)   \\\\rResolving deltas:  87% (4345/4989)   \\\\rResolving deltas:  88% (4404/4989)   \\\\rResolving deltas:  90% (4508/4989)   \\\\rResolving deltas:  91% (4557/4989)   \\\\rResolving deltas:  92% (4600/4989)   \\\\rResolving deltas:  93% (4644/4989)   \\\\rResolving deltas:  94% (4725/4989)   \\\\rResolving deltas:  95% (4762/4989)   \\\\rResolving deltas:  96% (4792/4989)   \\\\rResolving deltas:  97% (4853/4989)   \\\\rResolving deltas:  98% (4899/4989)   \\\\rResolving deltas:  99% (4947/4989)   \\\\rResolving deltas: 100% (4989/4989)   \\\\rResolving deltas: 100% (4989/4989), done.\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:16.656760097,\\u0022data\\u0022:\\u0022/kaggle/tmp/tmp/yolov5\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:24.206933431,\\u0022data\\u0022:\\u0022Note: you may need to restart the kernel to use updated packages.\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:24.20700023,\\u0022data\\u0022:\\u0022/kaggle/tmp/tmp\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:25.49418645,\\u0022data\\u0022:\\u0022Setup complete. Using torch 1.7.0 (Tesla P100-PCIE-16GB)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:36.850158511,\\u0022data\\u0022:\\u0022\\\\u001b[34m\\\\u001b[1mwandb\\\\u001b[0m: You can find your API key in your browser here: https://wandb.ai/authorize\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:38.586740947,\\u0022data\\u0022:\\u0022/kaggle/tmp\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:38.586774934,\\u0022data\\u0022:\\u0022/kaggle\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:39.070144479,\\u0022data\\u0022:\\u0022/opt/conda/lib/python3.7/site-packages/pandas/core/indexing.py:1596: SettingWithCopyWarning: \\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:39.070175864,\\u0022data\\u0022:\\u0022A value is trying to be set on a copy of a slice from a DataFrame.\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:39.070184257,\\u0022data\\u0022:\\u0022Try using .loc[row_indexer,col_indexer] = value instead\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:39.070190527,\\u0022data\\u0022:\\u0022\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:39.070196352,\\u0022data\\u0022:\\u0022See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:39.070202987,\\u0022data\\u0022:\\u0022  self.obj[key] = _infer_fill_value(value)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:39.07020889,\\u0022data\\u0022:\\u0022/opt/conda/lib/python3.7/site-packages/pandas/core/indexing.py:1763: SettingWithCopyWarning: \\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:39.07021523,\\u0022data\\u0022:\\u0022A value is trying to be set on a copy of a slice from a DataFrame.\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:39.070221058,\\u0022data\\u0022:\\u0022Try using .loc[row_indexer,col_indexer] = value instead\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:39.070226974,\\u0022data\\u0022:\\u0022\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:39.070232595,\\u0022data\\u0022:\\u0022See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:39.070238647,\\u0022data\\u0022:\\u0022  isetter(loc, value)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:39.179929589,\\u0022data\\u0022:\\u0022Size of dataset: 6334, training images: 5383. validation images: 951\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:39.826160512,\\u0022data\\u0022:\\u0022ls: cannot access \\u0027tmp/covid/images\\u0027: No such file or directory\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:40.037761436,\\u0022data\\u0022:\\u0022/\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:40.308427533,\\u0022data\\u0022:\\u0022\\\\r  0%|          | 0/6334 [00:00\\\\u003c?, ?it/s]\\\\r  0%|          | 0/6334 [00:00\\\\u003c?, ?it/s]\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:40.437345761,\\u0022data\\u0022:\\u0022\\\\r  0%|          | 0/6334 [00:00\\\\u003c?, ?it/s]\\\\r  0%|          | 0/6334 [00:00\\\\u003c?, ?it/s]\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:40.945875382,\\u0022data\\u0022:\\u0022\\\\r  0%|          | 0/6334 [00:00\\\\u003c?, ?it/s]\\\\r  0%|          | 0/6334 [00:00\\\\u003c?, ?it/s]\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:41.191734328,\\u0022data\\u0022:\\u0022[Errno 2] No such file or directory: \\u0027working/tmp/yolov5/\\u0027\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:41.191769281,\\u0022data\\u0022:\\u0022/\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:41.877608447,\\u0022data\\u0022:\\u0022\\\\u001b[0m\\\\u001b[01;34mbin\\\\u001b[0m/   \\\\u001b[01;32mentrypoint.sh\\\\u001b[0m*  \\\\u001b[01;34mkaggle\\\\u001b[0m/  \\\\u001b[01;34mmedia\\\\u001b[0m/  \\\\u001b[01;34mproc\\\\u001b[0m/  \\\\u001b[01;32mrun_jupyter.sh\\\\u001b[0m*  \\\\u001b[01;34msrv\\\\u001b[0m/  \\\\u001b[01;34musr\\\\u001b[0m/\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:41.877645046,\\u0022data\\u0022:\\u0022\\\\u001b[01;34mboot\\\\u001b[0m/  \\\\u001b[01;34metc\\\\u001b[0m/            \\\\u001b[01;34mlib\\\\u001b[0m/     \\\\u001b[01;34mmnt\\\\u001b[0m/    \\\\u001b[01;34mroot\\\\u001b[0m/  \\\\u001b[01;34msbin\\\\u001b[0m/            \\\\u001b[01;34msys\\\\u001b[0m/  \\\\u001b[01;34mvar\\\\u001b[0m/\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:41.877653161,\\u0022data\\u0022:\\u0022\\\\u001b[01;34mdev\\\\u001b[0m/   \\\\u001b[01;34mhome\\\\u001b[0m/           \\\\u001b[01;34mlib64\\\\u001b[0m/   \\\\u001b[01;34mopt\\\\u001b[0m/    \\\\u001b[01;34mrun\\\\u001b[0m/   \\\\u001b[01;34msrc\\\\u001b[0m/             \\\\u001b[30;42mtmp\\\\u001b[0m/\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:42.819911294,\\u0022data\\u0022:\\u0022python: can\\u0027t open file \\u0027train.py\\u0027: [Errno 2] No such file or directory\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:43.33393672,\\u0022data\\u0022:\\u0022/\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:43.532910495,\\u0022data\\u0022:\\u0022[Errno 2] No such file or directory: \\u0027yolov5\\u0027\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:43.532955146,\\u0022data\\u0022:\\u0022/\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:44.026472904,\\u0022data\\u0022:\\u0022\\\\u001b[0m\\\\u001b[01;34mbin\\\\u001b[0m/   \\\\u001b[01;32mentrypoint.sh\\\\u001b[0m*  \\\\u001b[01;34mkaggle\\\\u001b[0m/  \\\\u001b[01;34mmedia\\\\u001b[0m/  \\\\u001b[01;34mproc\\\\u001b[0m/  \\\\u001b[01;32mrun_jupyter.sh\\\\u001b[0m*  \\\\u001b[01;34msrv\\\\u001b[0m/  \\\\u001b[01;34musr\\\\u001b[0m/\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:44.026520448,\\u0022data\\u0022:\\u0022\\\\u001b[01;34mboot\\\\u001b[0m/  \\\\u001b[01;34metc\\\\u001b[0m/            \\\\u001b[01;34mlib\\\\u001b[0m/     \\\\u001b[01;34mmnt\\\\u001b[0m/    \\\\u001b[01;34mroot\\\\u001b[0m/  \\\\u001b[01;34msbin\\\\u001b[0m/            \\\\u001b[01;34msys\\\\u001b[0m/  \\\\u001b[01;34mvar\\\\u001b[0m/\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:44.026527861,\\u0022data\\u0022:\\u0022\\\\u001b[01;34mdev\\\\u001b[0m/   \\\\u001b[01;34mhome\\\\u001b[0m/           \\\\u001b[01;34mlib64\\\\u001b[0m/   \\\\u001b[01;34mopt\\\\u001b[0m/    \\\\u001b[01;34mrun\\\\u001b[0m/   \\\\u001b[01;34msrc\\\\u001b[0m/             \\\\u001b[30;42mtmp\\\\u001b[0m/\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:45.08604338,\\u0022data\\u0022:\\u0022python: can\\u0027t open file \\u0027detect.py\\u0027: [Errno 2] No such file or directory\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:45.925599564,\\u0022data\\u0022:\\u0022python: can\\u0027t open file \\u0027train.py\\u0027: [Errno 2] No such file or directory\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:46.908375991,\\u0022data\\u0022:\\u0022ls: cannot access \\u0027runs/detect/exp3/labels\\u0027: No such file or directory\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stdout\\u0022,\\u0022time\\u0022:47.674741386,\\u0022data\\u0022:\\u0022cat: runs/detect/exp3/labels/ba91d37ee459.txt: No such file or directory\\\\r\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:48.430508933,\\u0022data\\u0022:\\u0022\\\\r  0%|          | 0/2477 [00:00\\\\u003c?, ?it/s]\\\\r 45%|████▌     | 1122/2477 [00:00\\\\u003c00:00, 11213.91it/s]\\\\r 49%|████▉     | 1214/2477 [00:00\\\\u003c00:00, 10983.33it/s]\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248155934,\\u0022data\\u0022:\\u0022Traceback (most recent call last):\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.24824287,\\u0022data\\u0022:\\u0022  File \\\\\\u0022\\\\u003cstring\\\\u003e\\\\\\u0022, line 1, in \\\\u003cmodule\\\\u003e\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248252387,\\u0022data\\u0022:\\u0022  File \\\\\\u0022/opt/conda/lib/python3.7/site-packages/papermill/execute.py\\\\\\u0022, line 122, in execute_notebook\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248257864,\\u0022data\\u0022:\\u0022    raise_for_execution_errors(nb, output_path)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248262862,\\u0022data\\u0022:\\u0022  File \\\\\\u0022/opt/conda/lib/python3.7/site-packages/papermill/execute.py\\\\\\u0022, line 234, in raise_for_execution_errors\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248268552,\\u0022data\\u0022:\\u0022    raise error\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248273421,\\u0022data\\u0022:\\u0022papermill.exceptions.PapermillExecutionError: \\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.24827809,\\u0022data\\u0022:\\u0022---------------------------------------------------------------------------\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248283117,\\u0022data\\u0022:\\u0022Exception encountered at \\\\\\u0022In [43]\\\\\\u0022:\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248287726,\\u0022data\\u0022:\\u0022---------------------------------------------------------------------------\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248292636,\\u0022data\\u0022:\\u0022ValueError                                Traceback (most recent call last)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248297281,\\u0022data\\u0022:\\u0022\\\\u003cipython-input-43-0afac2a3c7cd\\\\u003e in \\\\u003cmodule\\\\u003e\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248302303,\\u0022data\\u0022:\\u0022----\\\\u003e 1 sub_df[\\u0027PredictionString\\u0027] = predictions\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248307103,\\u0022data\\u0022:\\u0022      2 sub_df.to_csv(\\u0027/kaggle/working/submission.csv\\u0027, index=False)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248318119,\\u0022data\\u0022:\\u0022      3 sub_df.tail()\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248322872,\\u0022data\\u0022:\\u0022\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248337318,\\u0022data\\u0022:\\u0022/opt/conda/lib/python3.7/site-packages/pandas/core/frame.py in __setitem__(self, key, value)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248341991,\\u0022data\\u0022:\\u0022   3042         else:\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248347122,\\u0022data\\u0022:\\u0022   3043             # set column\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248351865,\\u0022data\\u0022:\\u0022-\\\\u003e 3044             self._set_item(key, value)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248356767,\\u0022data\\u0022:\\u0022   3045 \\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248361854,\\u0022data\\u0022:\\u0022   3046     def _setitem_slice(self, key: slice, value):\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248366972,\\u0022data\\u0022:\\u0022\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248371475,\\u0022data\\u0022:\\u0022/opt/conda/lib/python3.7/site-packages/pandas/core/frame.py in _set_item(self, key, value)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248376594,\\u0022data\\u0022:\\u0022   3118         \\\\\\u0022\\\\\\u0022\\\\\\u0022\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248381346,\\u0022data\\u0022:\\u0022   3119         self._ensure_valid_index(value)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248386152,\\u0022data\\u0022:\\u0022-\\\\u003e 3120         value = self._sanitize_column(key, value)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248390921,\\u0022data\\u0022:\\u0022   3121         NDFrame._set_item(self, key, value)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248396416,\\u0022data\\u0022:\\u0022   3122 \\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248401177,\\u0022data\\u0022:\\u0022\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248405697,\\u0022data\\u0022:\\u0022/opt/conda/lib/python3.7/site-packages/pandas/core/frame.py in _sanitize_column(self, key, value, broadcast)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248410599,\\u0022data\\u0022:\\u0022   3766 \\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248416029,\\u0022data\\u0022:\\u0022   3767             # turn me into an ndarray\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248420933,\\u0022data\\u0022:\\u0022-\\\\u003e 3768             value = sanitize_index(value, self.index)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248426181,\\u0022data\\u0022:\\u0022   3769             if not isinstance(value, (np.ndarray, Index)):\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248430907,\\u0022data\\u0022:\\u0022   3770                 if isinstance(value, list) and len(value) \\\\u003e 0:\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248435964,\\u0022data\\u0022:\\u0022\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248440802,\\u0022data\\u0022:\\u0022/opt/conda/lib/python3.7/site-packages/pandas/core/internals/construction.py in sanitize_index(data, index)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248446207,\\u0022data\\u0022:\\u0022    746     if len(data) != len(index):\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248450694,\\u0022data\\u0022:\\u0022    747         raise ValueError(\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248455541,\\u0022data\\u0022:\\u0022--\\\\u003e 748             \\\\\\u0022Length of values \\\\\\u0022\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248460478,\\u0022data\\u0022:\\u0022    749             f\\\\\\u0022({len(data)}) \\\\\\u0022\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248466977,\\u0022data\\u0022:\\u0022    750             \\\\\\u0022does not match length of index \\\\\\u0022\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248471984,\\u0022data\\u0022:\\u0022\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.24847669,\\u0022data\\u0022:\\u0022ValueError: Length of values (1214) does not match length of index (2477)\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:52.248481454,\\u0022data\\u0022:\\u0022\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:53.496834162,\\u0022data\\u0022:\\u0022/opt/conda/lib/python3.7/site-packages/traitlets/traitlets.py:2561: FutureWarning: --Exporter.preprocessors=[\\\\\\u0022remove_papermill_header.RemovePapermillHeader\\\\\\u0022] for containers is deprecated in traitlets 5.0. You can pass `--Exporter.preprocessors item` ... multiple times to add items to a list.\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:53.497042746,\\u0022data\\u0022:\\u0022  FutureWarning,\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:53.497147264,\\u0022data\\u0022:\\u0022[NbConvertApp] Converting notebook __notebook__.ipynb to notebook\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:54.062842486,\\u0022data\\u0022:\\u0022[NbConvertApp] Writing 111301 bytes to __notebook__.ipynb\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:55.150269932,\\u0022data\\u0022:\\u0022/opt/conda/lib/python3.7/site-packages/traitlets/traitlets.py:2561: FutureWarning: --Exporter.preprocessors=[\\\\\\u0022nbconvert.preprocessors.ExtractOutputPreprocessor\\\\\\u0022] for containers is deprecated in traitlets 5.0. You can pass `--Exporter.preprocessors item` ... multiple times to add items to a list.\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:55.15031732,\\u0022data\\u0022:\\u0022  FutureWarning,\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:55.150324015,\\u0022data\\u0022:\\u0022[NbConvertApp] Converting notebook __notebook__.ipynb to html\\\\n\\u0022}\\n,{\\u0022stream_name\\u0022:\\u0022stderr\\u0022,\\u0022time\\u0022:56.177456656,\\u0022data\\u0022:\\u0022[NbConvertApp] Writing 397383 bytes to __results__.html\\\\n\\u0022}\\n]\",\"outputFiles\":[],\"ouputFilesOwnerInfo\":{\"databundleVersionId\":0,\"dataset\":null,\"competition\":null,\"kernel\":{\"kernelId\":17874202,\"kernelVersionId\":66453229,\"scope\":\"ajinkyadeshpande39/yolo-notebook\"},\"previewsDisabled\":false},\"pageMessages\":[],\"dataSources\":[{\"sourceType\":\"Competition\",\"sourceId\":26680,\"datasetId\":null,\"databundleVersionId\":2283525,\"mountSlug\":\"siim-covid19-detection\"},{\"sourceType\":\"DatasetVersion\",\"sourceId\":1666454,\"datasetId\":986800,\"databundleVersionId\":null,\"mountSlug\":\"kerasapplications\"},{\"sourceType\":\"DatasetVersion\",\"sourceId\":2246642,\"datasetId\":1351041,\"databundleVersionId\":null,\"mountSlug\":\"siim-covid19-resized-to-512px-png\"}],\"renderableDataSources\":null,\"versions\":[{\"id\":66453442,\"isForkParent\":false,\"isNotebook\":true,\"languageName\":\"Python\",\"lastRunTime\":\"2021-06-23T16:47:04.2Z\",\"linesChangedFromPrevious\":0,\"linesDeletedFromPrevious\":0,\"linesInsertedFromPrevious\":0,\"outputFilesTotalSizeBytes\":0,\"runInfo\":{\"dockerfileUrl\":null,\"dockerHubUrl\":null,\"dockerImageId\":null,\"dockerImageName\":null,\"exitCode\":0,\"failureMessage\":null,\"isValidStatus\":false,\"runTimeSeconds\":null,\"succeeded\":false,\"timeoutExceeded\":false,\"usedAllSpace\":null},\"status\":\"queued\",\"title\":\"YOLO notebook\",\"url\":\"/ajinkyadeshpande39/yolo-notebook?scriptVersionId=66453442\",\"versionNumber\":13,\"hasVersionNumber\":true,\"isRedacted\":false,\"versionAuthor\":null,\"versionType\":\"quick\",\"userPlan\":\"free\"},{\"id\":66453229,\"isForkParent\":false,\"isNotebook\":true,\"languageName\":\"Python\",\"lastRunTime\":\"2021-06-23T16:43:11.29Z\",\"linesChangedFromPrevious\":0,\"linesDeletedFromPrevious\":0,\"linesInsertedFromPrevious\":0,\"outputFilesTotalSizeBytes\":0,\"runInfo\":{\"dockerfileUrl\":\"https://github.com/Kaggle/docker-python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794/blob/master/Dockerfile\",\"dockerHubUrl\":\"https://registry.hub.docker.com/u/kaggle/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794/\",\"dockerImageId\":\"sha256:f8509c5954373e53c6dcd069dca18ab94cfea4c5755c493c0b504a7e50a409ac\",\"dockerImageName\":\"gcr.io/kaggle-private-byod/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794\",\"exitCode\":0,\"failureMessage\":null,\"isValidStatus\":true,\"runTimeSeconds\":56.2550055,\"succeeded\":true,\"timeoutExceeded\":false,\"usedAllSpace\":false},\"status\":\"complete\",\"title\":\"YOLO notebook\",\"url\":\"/ajinkyadeshpande39/yolo-notebook?scriptVersionId=66453229\",\"versionNumber\":12,\"hasVersionNumber\":true,\"isRedacted\":false,\"versionAuthor\":null,\"versionType\":\"batch\",\"userPlan\":\"free\"},{\"id\":66453105,\"isForkParent\":false,\"isNotebook\":true,\"languageName\":\"Python\",\"lastRunTime\":\"2021-06-23T16:41:07.81Z\",\"linesChangedFromPrevious\":0,\"linesDeletedFromPrevious\":0,\"linesInsertedFromPrevious\":0,\"outputFilesTotalSizeBytes\":0,\"runInfo\":{\"dockerfileUrl\":\"https://github.com/Kaggle/docker-python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794/blob/master/Dockerfile\",\"dockerHubUrl\":\"https://registry.hub.docker.com/u/kaggle/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794/\",\"dockerImageId\":\"sha256:f8509c5954373e53c6dcd069dca18ab94cfea4c5755c493c0b504a7e50a409ac\",\"dockerImageName\":\"gcr.io/kaggle-private-byod/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794\",\"exitCode\":0,\"failureMessage\":null,\"isValidStatus\":true,\"runTimeSeconds\":59.3880631,\"succeeded\":true,\"timeoutExceeded\":false,\"usedAllSpace\":false},\"status\":\"complete\",\"title\":\"YOLO notebook\",\"url\":\"/ajinkyadeshpande39/yolo-notebook?scriptVersionId=66453105\",\"versionNumber\":11,\"hasVersionNumber\":true,\"isRedacted\":false,\"versionAuthor\":null,\"versionType\":\"batch\",\"userPlan\":\"free\"},{\"id\":66452646,\"isForkParent\":false,\"isNotebook\":true,\"languageName\":\"Python\",\"lastRunTime\":\"2021-06-23T16:32:38.893Z\",\"linesChangedFromPrevious\":0,\"linesDeletedFromPrevious\":0,\"linesInsertedFromPrevious\":0,\"outputFilesTotalSizeBytes\":0,\"runInfo\":{\"dockerfileUrl\":null,\"dockerHubUrl\":null,\"dockerImageId\":null,\"dockerImageName\":null,\"exitCode\":137,\"failureMessage\":\"\",\"isValidStatus\":true,\"runTimeSeconds\":0.0,\"succeeded\":false,\"timeoutExceeded\":false,\"usedAllSpace\":false},\"status\":\"cancelAcknowledged\",\"title\":\"YOLO notebook\",\"url\":\"/ajinkyadeshpande39/yolo-notebook?scriptVersionId=66452646\",\"versionNumber\":10,\"hasVersionNumber\":true,\"isRedacted\":false,\"versionAuthor\":null,\"versionType\":\"quick\",\"userPlan\":\"free\"},{\"id\":66451678,\"isForkParent\":false,\"isNotebook\":true,\"languageName\":\"Python\",\"lastRunTime\":\"2021-06-23T16:15:46.647Z\",\"linesChangedFromPrevious\":0,\"linesDeletedFromPrevious\":0,\"linesInsertedFromPrevious\":0,\"outputFilesTotalSizeBytes\":0,\"runInfo\":{\"dockerfileUrl\":null,\"dockerHubUrl\":null,\"dockerImageId\":null,\"dockerImageName\":null,\"exitCode\":137,\"failureMessage\":\"\",\"isValidStatus\":true,\"runTimeSeconds\":0.0,\"succeeded\":false,\"timeoutExceeded\":false,\"usedAllSpace\":false},\"status\":\"cancelAcknowledged\",\"title\":\"YOLO notebook\",\"url\":\"/ajinkyadeshpande39/yolo-notebook?scriptVersionId=66451678\",\"versionNumber\":9,\"hasVersionNumber\":true,\"isRedacted\":false,\"versionAuthor\":null,\"versionType\":\"quick\",\"userPlan\":\"free\"},{\"id\":66450779,\"isForkParent\":false,\"isNotebook\":true,\"languageName\":\"Python\",\"lastRunTime\":\"2021-06-23T16:00:25.117Z\",\"linesChangedFromPrevious\":0,\"linesDeletedFromPrevious\":0,\"linesInsertedFromPrevious\":0,\"outputFilesTotalSizeBytes\":0,\"runInfo\":{\"dockerfileUrl\":null,\"dockerHubUrl\":null,\"dockerImageId\":null,\"dockerImageName\":null,\"exitCode\":137,\"failureMessage\":\"\",\"isValidStatus\":true,\"runTimeSeconds\":0.0,\"succeeded\":false,\"timeoutExceeded\":false,\"usedAllSpace\":false},\"status\":\"cancelAcknowledged\",\"title\":\"YOLO notebook\",\"url\":\"/ajinkyadeshpande39/yolo-notebook?scriptVersionId=66450779\",\"versionNumber\":8,\"hasVersionNumber\":true,\"isRedacted\":false,\"versionAuthor\":null,\"versionType\":\"quick\",\"userPlan\":\"free\"},{\"id\":66449778,\"isForkParent\":false,\"isNotebook\":true,\"languageName\":\"Python\",\"lastRunTime\":\"2021-06-23T15:44:01.28Z\",\"linesChangedFromPrevious\":0,\"linesDeletedFromPrevious\":23,\"linesInsertedFromPrevious\":32,\"outputFilesTotalSizeBytes\":0,\"runInfo\":{\"dockerfileUrl\":null,\"dockerHubUrl\":null,\"dockerImageId\":null,\"dockerImageName\":null,\"exitCode\":137,\"failureMessage\":\"\",\"isValidStatus\":true,\"runTimeSeconds\":0.0,\"succeeded\":false,\"timeoutExceeded\":false,\"usedAllSpace\":false},\"status\":\"cancelAcknowledged\",\"title\":\"YOLO notebook\",\"url\":\"/ajinkyadeshpande39/yolo-notebook?scriptVersionId=66449778\",\"versionNumber\":7,\"hasVersionNumber\":true,\"isRedacted\":false,\"versionAuthor\":null,\"versionType\":\"quick\",\"userPlan\":\"free\"},{\"id\":66438989,\"isForkParent\":false,\"isNotebook\":true,\"languageName\":\"Python\",\"lastRunTime\":\"2021-06-23T12:56:56.13Z\",\"linesChangedFromPrevious\":0,\"linesDeletedFromPrevious\":0,\"linesInsertedFromPrevious\":0,\"outputFilesTotalSizeBytes\":0,\"runInfo\":{\"dockerfileUrl\":\"https://github.com/Kaggle/docker-python@sha256:648f97c8be132f304cff3d397339f2d815de79721f3695f43c08a6aec3bc0a5d/blob/master/Dockerfile\",\"dockerHubUrl\":\"https://registry.hub.docker.com/u/kaggle/python@sha256:648f97c8be132f304cff3d397339f2d815de79721f3695f43c08a6aec3bc0a5d/\",\"dockerImageId\":\"sha256:8f433497a6531c058852acca2245b7428c12f179d879d8cc92582540784fe442\",\"dockerImageName\":\"gcr.io/kaggle-images/python@sha256:648f97c8be132f304cff3d397339f2d815de79721f3695f43c08a6aec3bc0a5d\",\"exitCode\":0,\"failureMessage\":null,\"isValidStatus\":true,\"runTimeSeconds\":5.0663361,\"succeeded\":true,\"timeoutExceeded\":false,\"usedAllSpace\":false},\"status\":\"complete\",\"title\":\"YOLO notebook\",\"url\":\"/ajinkyadeshpande39/yolo-notebook?scriptVersionId=66438989\",\"versionNumber\":6,\"hasVersionNumber\":true,\"isRedacted\":false,\"versionAuthor\":null,\"versionType\":\"quick\",\"userPlan\":\"free\"},{\"id\":66438730,\"isForkParent\":false,\"isNotebook\":true,\"languageName\":\"Python\",\"lastRunTime\":\"2021-06-23T12:52:50.523Z\",\"linesChangedFromPrevious\":0,\"linesDeletedFromPrevious\":0,\"linesInsertedFromPrevious\":0,\"outputFilesTotalSizeBytes\":0,\"runInfo\":{\"dockerfileUrl\":null,\"dockerHubUrl\":null,\"dockerImageId\":null,\"dockerImageName\":null,\"exitCode\":137,\"failureMessage\":\"\",\"isValidStatus\":true,\"runTimeSeconds\":0.0,\"succeeded\":false,\"timeoutExceeded\":false,\"usedAllSpace\":false},\"status\":\"cancelAcknowledged\",\"title\":\"YOLO notebook\",\"url\":\"/ajinkyadeshpande39/yolo-notebook?scriptVersionId=66438730\",\"versionNumber\":5,\"hasVersionNumber\":true,\"isRedacted\":false,\"versionAuthor\":null,\"versionType\":\"quick\",\"userPlan\":\"free\"},{\"id\":66437524,\"isForkParent\":false,\"isNotebook\":true,\"languageName\":\"Python\",\"lastRunTime\":\"2021-06-23T12:33:32.53Z\",\"linesChangedFromPrevious\":0,\"linesDeletedFromPrevious\":0,\"linesInsertedFromPrevious\":0,\"outputFilesTotalSizeBytes\":0,\"runInfo\":{\"dockerfileUrl\":\"https://github.com/Kaggle/docker-python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794/blob/master/Dockerfile\",\"dockerHubUrl\":\"https://registry.hub.docker.com/u/kaggle/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794/\",\"dockerImageId\":\"sha256:f8509c5954373e53c6dcd069dca18ab94cfea4c5755c493c0b504a7e50a409ac\",\"dockerImageName\":\"gcr.io/kaggle-private-byod/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794\",\"exitCode\":0,\"failureMessage\":null,\"isValidStatus\":true,\"runTimeSeconds\":251.0138677,\"succeeded\":true,\"timeoutExceeded\":false,\"usedAllSpace\":false},\"status\":\"complete\",\"title\":\"YOLO notebook\",\"url\":\"/ajinkyadeshpande39/yolo-notebook?scriptVersionId=66437524\",\"versionNumber\":4,\"hasVersionNumber\":true,\"isRedacted\":false,\"versionAuthor\":null,\"versionType\":\"batch\",\"userPlan\":\"free\"},{\"id\":66437242,\"isForkParent\":false,\"isNotebook\":true,\"languageName\":\"Python\",\"lastRunTime\":\"2021-06-23T12:28:43.457Z\",\"linesChangedFromPrevious\":0,\"linesDeletedFromPrevious\":0,\"linesInsertedFromPrevious\":0,\"outputFilesTotalSizeBytes\":0,\"runInfo\":{\"dockerfileUrl\":\"https://github.com/Kaggle/docker-python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794/blob/master/Dockerfile\",\"dockerHubUrl\":\"https://registry.hub.docker.com/u/kaggle/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794/\",\"dockerImageId\":\"sha256:f8509c5954373e53c6dcd069dca18ab94cfea4c5755c493c0b504a7e50a409ac\",\"dockerImageName\":\"gcr.io/kaggle-private-byod/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794\",\"exitCode\":137,\"failureMessage\":\"\",\"isValidStatus\":true,\"runTimeSeconds\":205.9803148,\"succeeded\":false,\"timeoutExceeded\":false,\"usedAllSpace\":false},\"status\":\"cancelAcknowledged\",\"title\":\"YOLO notebook\",\"url\":\"/ajinkyadeshpande39/yolo-notebook?scriptVersionId=66437242\",\"versionNumber\":3,\"hasVersionNumber\":true,\"isRedacted\":false,\"versionAuthor\":null,\"versionType\":\"batch\",\"userPlan\":\"free\"},{\"id\":66436730,\"isForkParent\":false,\"isNotebook\":true,\"languageName\":\"Python\",\"lastRunTime\":\"2021-06-23T12:20:59.1Z\",\"linesChangedFromPrevious\":0,\"linesDeletedFromPrevious\":101,\"linesInsertedFromPrevious\":101,\"outputFilesTotalSizeBytes\":0,\"runInfo\":{\"dockerfileUrl\":\"https://github.com/Kaggle/docker-python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794/blob/master/Dockerfile\",\"dockerHubUrl\":\"https://registry.hub.docker.com/u/kaggle/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794/\",\"dockerImageId\":\"sha256:f8509c5954373e53c6dcd069dca18ab94cfea4c5755c493c0b504a7e50a409ac\",\"dockerImageName\":\"gcr.io/kaggle-private-byod/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794\",\"exitCode\":0,\"failureMessage\":null,\"isValidStatus\":true,\"runTimeSeconds\":69.9540655,\"succeeded\":true,\"timeoutExceeded\":false,\"usedAllSpace\":false},\"status\":\"complete\",\"title\":\"YOLO notebook\",\"url\":\"/ajinkyadeshpande39/yolo-notebook?scriptVersionId=66436730\",\"versionNumber\":2,\"hasVersionNumber\":true,\"isRedacted\":false,\"versionAuthor\":null,\"versionType\":\"batch\",\"userPlan\":\"free\"},{\"id\":66435893,\"isForkParent\":false,\"isNotebook\":true,\"languageName\":\"Python\",\"lastRunTime\":\"2021-06-23T12:07:43.447Z\",\"linesChangedFromPrevious\":0,\"linesDeletedFromPrevious\":0,\"linesInsertedFromPrevious\":446,\"outputFilesTotalSizeBytes\":0,\"runInfo\":{\"dockerfileUrl\":\"https://github.com/Kaggle/docker-python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794/blob/master/Dockerfile\",\"dockerHubUrl\":\"https://registry.hub.docker.com/u/kaggle/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794/\",\"dockerImageId\":\"sha256:f8509c5954373e53c6dcd069dca18ab94cfea4c5755c493c0b504a7e50a409ac\",\"dockerImageName\":\"gcr.io/kaggle-private-byod/python@sha256:046f8514e4f3f41fef443911ead054414479ea948e2c0fb074114d43daedd794\",\"exitCode\":137,\"failureMessage\":\"\",\"isValidStatus\":true,\"runTimeSeconds\":32.0935188,\"succeeded\":false,\"timeoutExceeded\":false,\"usedAllSpace\":false},\"status\":\"cancelAcknowledged\",\"title\":\"YOLO notebook\",\"url\":\"/ajinkyadeshpande39/yolo-notebook?scriptVersionId=66435893\",\"versionNumber\":1,\"hasVersionNumber\":true,\"isRedacted\":false,\"versionAuthor\":null,\"versionType\":\"batch\",\"userPlan\":\"free\"}],\"categories\":{\"type\":\"notebook\",\"tags\":[]},\"downloadAllFilesUrl\":\"/code/svzip/66453229\",\"submission\":null,\"menuLinks\":[{\"count\":null,\"href\":\"/ajinkyadeshpande39/yolo-notebook/notebook\",\"reportEventCategory\":null,\"reportEventType\":null,\"showZeroCountExplicitly\":false,\"showOnMobile\":true,\"tab\":\"notebook\",\"text\":\"Notebook\",\"title\":\"Notebook\"},{\"count\":null,\"href\":\"/ajinkyadeshpande39/yolo-notebook/code\",\"reportEventCategory\":null,\"reportEventType\":null,\"showZeroCountExplicitly\":false,\"showOnMobile\":true,\"tab\":\"code\",\"text\":\"Code\",\"title\":\"Code\"},{\"count\":3,\"href\":\"/ajinkyadeshpande39/yolo-notebook/data\",\"reportEventCategory\":null,\"reportEventType\":null,\"showZeroCountExplicitly\":false,\"showOnMobile\":true,\"tab\":\"data\",\"text\":\"Input\",\"title\":\"Input\"},{\"count\":null,\"href\":\"/ajinkyadeshpande39/yolo-notebook/execution\",\"reportEventCategory\":null,\"reportEventType\":null,\"showZeroCountExplicitly\":false,\"showOnMobile\":false,\"tab\":\"execution\",\"text\":\"Execution Info\",\"title\":\"Execution Info\"},{\"count\":null,\"href\":\"/ajinkyadeshpande39/yolo-notebook/log\",\"reportEventCategory\":null,\"reportEventType\":null,\"showZeroCountExplicitly\":false,\"showOnMobile\":false,\"tab\":\"log\",\"text\":\"Log\",\"title\":\"Log\"},{\"count\":0,\"href\":\"/ajinkyadeshpande39/yolo-notebook/comments\",\"reportEventCategory\":null,\"reportEventType\":null,\"showZeroCountExplicitly\":true,\"showOnMobile\":true,\"tab\":\"comments\",\"text\":\"Comments\",\"title\":\"Comments\"}],\"rightMenuLinks\":[],\"callToAction\":{\"count\":null,\"href\":\"/code/fork-version/66453229\",\"reportEventCategory\":\"kernels\",\"reportEventType\":\"anonymousKernelForkCreation\",\"showZeroCountExplicitly\":false,\"showOnMobile\":true,\"tab\":null,\"text\":\"Fork Notebook\",\"title\":\"Fork Notebook\"},\"voteButton\":{\"totalVotes\":1,\"medalVotes\":1,\"hasAlreadyVotedUp\":false,\"hasAlreadyVotedDown\":false,\"canUpvote\":true,\"canDownvote\":false,\"voteUpUrl\":null,\"voteDownUrl\":null,\"voters\":[{\"id\":7528647,\"displayName\":\"AJINKYA DESHPANDE\",\"email\":\"\",\"editedEmail\":null,\"editedEmailCode\":null,\"userName\":\"ajinkyadeshpande39\",\"thumbnailUrl\":\"https://storage.googleapis.com/kaggle-avatars/thumbnails/default-thumb.png\",\"profileUrl\":\"/ajinkyadeshpande39\",\"registerDate\":null,\"lastVisitDate\":null,\"statusId\":0,\"performanceTier\":1,\"userLogins\":[],\"groupIds\":[],\"duplicateUsers\":[],\"hasPhoneVerifications\":false,\"failedNerdchas\":0,\"hasPendingNerdcha\":false,\"deleteRequests\":[],\"isAdmin\":false,\"isKaggleBot\":false,\"isAnonymous\":false,\"canAct\":false,\"canBeSeen\":false,\"thumbnailName\":\"\",\"isPhoneVerified\":false}],\"currentUserInfo\":null,\"showVoters\":true,\"alwaysShowVoters\":true,\"kernelId\":17874202},\"parentName\":\"multiple data sources\",\"parentUrl\":\"#data\",\"thumbnailImageUrl\":\"/static/images/multiple-datasource.png\",\"canWrite\":false,\"canAdminister\":false,\"currentUserForkParentSessionId\":null,\"currentUserHasForked\":false,\"forkParentIsRedacted\":false,\"forkDiffLinesChanged\":0,\"forkDiffLinesDeleted\":0,\"forkDiffLinesInserted\":0,\"forkDiffUrl\":null,\"forkParentAuthorDisplayName\":null,\"forkParentAuthorUrl\":null,\"forkParentTitle\":null,\"forkParentUrl\":null,\"simplifiedViewer\":false,\"kernelOutputDataset\":null,\"disableComments\":false,\"taskSubmissionInfo\":null,\"learnSeriesNavigationData\":null,\"showSharingControls\":true,\"showUnchangedCopyWarning\":false});performance && performance.mark && performance.mark(\"KernelViewer.componentCouldBootstrap\");</script>\r\n\r\n<form action=\"/ajinkyadeshpande39/yolo-notebook\" id=\"__AjaxAntiForgeryForm\" method=\"post\"><input name=\"X-XSRF-TOKEN\" type=\"hidden\" value=\"CfDJ8LdUzqlsSWBPr4Ce3rb9VL_5oX2HL6-cE8-foejffFnYF_rzU-Ex9aIbwgoThojknU1_Ti-Rwq6SzmAuIAHAj3SXIbAyKshJidevH0RtSdYdU0kVblvqszilPO9DJF8IIvMSg6zxx9ZFnJ7swBrilV0\" /></form>\r\n<script nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\" type=\"text/x-mathjax-config\">\r\n    MathJax.Hub.Config({\r\n    \"HTML-CSS\": {\r\n    preferredFont: \"TeX\",\r\n    availableFonts: [\"STIX\", \"TeX\"],\r\n    linebreaks: {\r\n    automatic: true\r\n    },\r\n    EqnChunk: (MathJax.Hub.Browser.isMobile ? 10 : 50)\r\n    },\r\n    tex2jax: {\r\n    inlineMath: [[\"\\\\(\", \"\\\\)\"], [\"\\\\\\\\(\", \"\\\\\\\\)\"]],\r\n    displayMath: [[\"$$\", \"$$\"], [\"\\\\[\", \"\\\\]\"]],\r\n    processEscapes: true,\r\n    ignoreClass: \"tex2jax_ignore|dno\"\r\n    },\r\n    TeX: {\r\n    noUndefined: {\r\n    attributes: {\r\n    mathcolor: \"red\",\r\n    mathbackground: \"#FFEEEE\",\r\n    mathsize: \"90%\"\r\n    }\r\n    }\r\n    },\r\n    Macros: {\r\n    href: \"{}\"\r\n    },\r\n    skipStartupTypeset: true,\r\n    messageStyle: \"none\",\r\n    extensions: [],\r\n    });\r\n</script>\r\n<script type=\"text/javascript\" nonce=\"Ag0sLAPBC4HHXHsfBW7yUQ==\">\r\n  window.addEventListener(\"DOMContentLoaded\", () => {\r\n    const head = document.getElementsByTagName(\"head\")[0];\r\n    const useProdHosts = [\"www.kaggle.com\", \"admin.kaggle.com\"];\r\n    const subdomain = useProdHosts.includes(window.location.hostname) ? \"www\" : \"staging\";\r\n\r\n    const lib = document.createElement(\"script\");\r\n    lib.type = \"text/javascript\";\r\n    lib.src = `https://${subdomain}.kaggleusercontent.com/static/mathjax/2.7.9/MathJax.js?config=TeX-AMS-MML_HTMLorMML`;\r\n    head.appendChild(lib);\r\n  });\r\n</script>\r\n\r\n\r\n</div>\r\n\r\n\r\n\r\n\r\n  </main>\r\n</body>\r\n\r\n</html>","metadata":{"_uuid":"e47c84e0-80bb-40f6-b68e-8bd6ab7b67ef","_cell_guid":"a7d73ebe-dd8f-4d74-b715-b3d6c1722cd9","collapsed":false,"jupyter":{"outputs_hidden":false},"execution":{"iopub.status.busy":"2021-06-23T16:53:42.826664Z","iopub.execute_input":"2021-06-23T16:53:42.827372Z","iopub.status.idle":"2021-06-23T16:53:42.87129Z","shell.execute_reply.started":"2021-06-23T16:53:42.827276Z","shell.execute_reply":"2021-06-23T16:53:42.869861Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}