{
  "id": 105002,
  "title": "Small concern regarding submission kernels run-time",
  "url": "/competitions/aptos2019-blindness-detection/discussion/105002",
  "author_name": "",
  "post_date": "2019-08-20T14:16:45.418081200Z",
  "votes": 1,
  "comment_count": 2,
  "views": 0,
  "content": "<p>The competition rules state the following ;\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2221110%2F863e28cc21a9b76cf55e0f09cdd8d294%2Finbox2F23321812F785a013f1fa95dcc23dc1b59925abfd42FScreen%20Shot%202019-08-12%20at%2018.28.31.png?generation=1566308561402717&amp;alt=media\" alt=\"\"></p>\n\n<p>I would like to know whether the 9 hours rule refers to the kernels running on public test data or full test data.</p>\n\n<p>In other words: Does a kernel running on public test data in less than 9 hours will be valid for final scoring or do we have to anticipate the total test set size (+- 6,6x bigger) and have a kernel that runs in less than 9 hours/6,6 = 81 min ?</p>\n\n<p>This has probably been answered in the past but I can't find any official statement. </p>\n\n<p>Thank you very much in advance and good luck. </p>",
  "messages": [
    {
      "id": "603646",
      "postDate": "08/20/2019 14:16:45",
      "content": "<p>The competition rules state the following ;\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2221110%2F863e28cc21a9b76cf55e0f09cdd8d294%2Finbox2F23321812F785a013f1fa95dcc23dc1b59925abfd42FScreen%20Shot%202019-08-12%20at%2018.28.31.png?generation=1566308561402717&amp;alt=media\" alt=\"\"></p>\n\n<p>I would like to know whether the 9 hours rule refers to the kernels running on public test data or full test data.</p>\n\n<p>In other words: Does a kernel running on public test data in less than 9 hours will be valid for final scoring or do we have to anticipate the total test set size (+- 6,6x bigger) and have a kernel that runs in less than 9 hours/6,6 = 81 min ?</p>\n\n<p>This has probably been answered in the past but I can't find any official statement. </p>\n\n<p>Thank you very much in advance and good luck. </p>",
      "rawMarkdown": "The competition rules state the following ;\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2221110%2F863e28cc21a9b76cf55e0f09cdd8d294%2Finbox2F23321812F785a013f1fa95dcc23dc1b59925abfd42FScreen%20Shot%202019-08-12%20at%2018.28.31.png?generation=1566308561402717&amp;alt=media)\n\nI would like to know whether the 9 hours rule refers to the kernels running on public test data or full test data.\n\nIn other words: Does a kernel running on public test data in less than 9 hours will be valid for final scoring or do we have to anticipate the total test set size (+- 6,6x bigger) and have a kernel that runs in less than 9 hours/6,6 = 81 min ?\n\nThis has probably been answered in the past but I can't find any official statement. \n\nThank you very much in advance and good luck.",
      "votes": null
    },
    {
      "id": "603674",
      "postDate": "08/20/2019 14:39:40",
      "content": "<p>It is quite easy: If you can properly submit you are fine --- \"instant gratification\"</p>",
      "rawMarkdown": "It is quite easy: If you can properly submit you are fine --- \"instant gratification\"",
      "votes": null
    },
    {
      "id": "603678",
      "postDate": "08/20/2019 14:49:28",
      "content": "<p>Great, thank you !</p>",
      "rawMarkdown": "Great, thank you !",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 603674,
      "author_name": "philippsinger",
      "author_url": "",
      "post_date": "08/20/2019 14:39:40",
      "content": "<p>It is quite easy: If you can properly submit you are fine --- \"instant gratification\"</p>",
      "votes": null,
      "replies": [
        {
          "id": 603678,
          "author_name": "adrienbrogniet",
          "author_url": "",
          "post_date": "08/20/2019 14:49:28",
          "content": "<p>Great, thank you !</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "603646": "The competition rules state the following ;\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2221110%2F863e28cc21a9b76cf55e0f09cdd8d294%2Finbox2F23321812F785a013f1fa95dcc23dc1b59925abfd42FScreen%20Shot%202019-08-12%20at%2018.28.31.png?generation=1566308561402717&amp;alt=media)\n\nI would like to know whether the 9 hours rule refers to the kernels running on public test data or full test data.\n\nIn other words: Does a kernel running on public test data in less than 9 hours will be valid for final scoring or do we have to anticipate the total test set size (+- 6,6x bigger) and have a kernel that runs in less than 9 hours/6,6 = 81 min ?\n\nThis has probably been answered in the past but I can't find any official statement. \n\nThank you very much in advance and good luck.",
    "603674": "It is quite easy: If you can properly submit you are fine --- \"instant gratification\"",
    "603678": "Great, thank you !"
  },
  "source": "meta"
}