{
  "id": 291474,
  "title": "Confusion about the number of test images",
  "url": "/competitions/tensorflow-great-barrier-reef/discussion/291474",
  "author_name": "",
  "post_date": "2021-11-29T12:53:39.348806100Z",
  "votes": 1,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Here, on the '<a href=\"https://www.kaggle.com/c/tensorflow-great-barrier-reef/data\" target=\"_blank\">Data' page</a>, it has been said that:</p>\n<blockquote>\n  <p>Expect to see roughly 13,000 images in the test set.</p>\n</blockquote>\n<p>Also, in <a href=\"https://www.kaggle.com/c/tensorflow-great-barrier-reef/leaderboard\" target=\"_blank\">'Leaderboard' page</a>, it has also been mentioned that:</p>\n<blockquote>\n  <p>This leaderboard is calculated with approximately 25% of the test data.<br>\n  The final results will be based on the other 75%, so the final standings may be different.</p>\n</blockquote>\n<p>Currently, in the public test set, it has only 3 images. So, there is a chance of 9 images in the private leaderboard as 75% remains. But, 13,000 images are expected by their saying. </p>\n<p>I am really confused here. 🤕</p>",
  "messages": [
    {
      "id": "1599453",
      "postDate": "11/29/2021 12:53:39",
      "content": "<p>Here, on the '<a href=\"https://www.kaggle.com/c/tensorflow-great-barrier-reef/data\" target=\"_blank\">Data' page</a>, it has been said that:</p>\n<blockquote>\n  <p>Expect to see roughly 13,000 images in the test set.</p>\n</blockquote>\n<p>Also, in <a href=\"https://www.kaggle.com/c/tensorflow-great-barrier-reef/leaderboard\" target=\"_blank\">'Leaderboard' page</a>, it has also been mentioned that:</p>\n<blockquote>\n  <p>This leaderboard is calculated with approximately 25% of the test data.<br>\n  The final results will be based on the other 75%, so the final standings may be different.</p>\n</blockquote>\n<p>Currently, in the public test set, it has only 3 images. So, there is a chance of 9 images in the private leaderboard as 75% remains. But, 13,000 images are expected by their saying. </p>\n<p>I am really confused here. 🤕</p>",
      "rawMarkdown": "Here, on the '[Data' page](https://www.kaggle.com/c/tensorflow-great-barrier-reef/data), it has been said that:\n> Expect to see roughly 13,000 images in the test set.\n\nAlso, in ['Leaderboard' page](https://www.kaggle.com/c/tensorflow-great-barrier-reef/leaderboard), it has also been mentioned that:\n> This leaderboard is calculated with approximately 25% of the test data.\nThe final results will be based on the other 75%, so the final standings may be different.\n\nCurrently, in the public test set, it has only 3 images. So, there is a chance of 9 images in the private leaderboard as 75% remains. But, 13,000 images are expected by their saying. \n\nI am really confused here. 🤕",
      "votes": null
    },
    {
      "id": "1599460",
      "postDate": "11/29/2021 13:01:33",
      "content": "<p>The public test set has 3 images, private has 13000. The leaderboard is calculated with the private set. (13000 * .25 is the public leaderboard, the rest is the private lb)</p>",
      "rawMarkdown": "The public test set has 3 images, private has 13000. The leaderboard is calculated with the private set. (13000 * .25 is the public leaderboard, the rest is the private lb)",
      "votes": null
    },
    {
      "id": "1599468",
      "postDate": "11/29/2021 13:10:12",
      "content": "<p>Thanks for your reply. I understand now.</p>",
      "rawMarkdown": "Thanks for your reply. I understand now.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1599460,
      "author_name": "pestipeti",
      "author_url": "",
      "post_date": "11/29/2021 13:01:33",
      "content": "<p>The public test set has 3 images, private has 13000. The leaderboard is calculated with the private set. (13000 * .25 is the public leaderboard, the rest is the private lb)</p>",
      "votes": null,
      "replies": [
        {
          "id": 1599468,
          "author_name": "faisaltfc",
          "author_url": "",
          "post_date": "11/29/2021 13:10:12",
          "content": "<p>Thanks for your reply. I understand now.</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1599453": "Here, on the '[Data' page](https://www.kaggle.com/c/tensorflow-great-barrier-reef/data), it has been said that:\n> Expect to see roughly 13,000 images in the test set.\n\nAlso, in ['Leaderboard' page](https://www.kaggle.com/c/tensorflow-great-barrier-reef/leaderboard), it has also been mentioned that:\n> This leaderboard is calculated with approximately 25% of the test data.\nThe final results will be based on the other 75%, so the final standings may be different.\n\nCurrently, in the public test set, it has only 3 images. So, there is a chance of 9 images in the private leaderboard as 75% remains. But, 13,000 images are expected by their saying. \n\nI am really confused here. 🤕",
    "1599460": "The public test set has 3 images, private has 13000. The leaderboard is calculated with the private set. (13000 * .25 is the public leaderboard, the rest is the private lb)",
    "1599468": "Thanks for your reply. I understand now."
  },
  "source": "meta"
}