{
  "id": 229310,
  "title": "[Hosts, please read this] Is there a possibility that the labeling issue will be resolved?",
  "url": "/competitions/hubmap-kidney-segmentation/discussion/229310",
  "author_name": "",
  "post_date": "2021-03-29T15:47:17.334224Z",
  "votes": 13,
  "comment_count": 3,
  "views": 0,
  "content": "<p><a href=\"https://www.kaggle.com/c/hubmap-kidney-segmentation/discussion/228993\" target=\"_blank\">https://www.kaggle.com/c/hubmap-kidney-segmentation/discussion/228993</a><br>\nThere was a discussion about this a few days ago, but I am wondering if this issue will be resolved.</p>\n<p>The <strong>test set(public test)</strong> seems to adopt <strong>sclerotic glomeruli</strong> as the ground truth. <br>\nHowever, as mentioned in previous discussions, <strong>aaa6a05cc.tiff</strong>(train dataset) did not set sclerotic glomeruli to ground truth.</p>\n<p>We don't know whether or not to choose <strong>sclerotic glomeruli</strong> as the ground truth in private data. <br>\nSo we have to devise a strategy for private data because of this <strong>inconsistent labeling.</strong></p>\n<p>I think there is a <strong>need for consistent labeling</strong> for <strong>sclerotic glomeruli</strong>.<br>\nI hope this issue will be resolved in the future. <br>\nThank you.</p>",
  "messages": [
    {
      "id": "1256171",
      "postDate": "03/29/2021 15:47:17",
      "content": "<p><a href=\"https://www.kaggle.com/c/hubmap-kidney-segmentation/discussion/228993\" target=\"_blank\">https://www.kaggle.com/c/hubmap-kidney-segmentation/discussion/228993</a><br>\nThere was a discussion about this a few days ago, but I am wondering if this issue will be resolved.</p>\n<p>The <strong>test set(public test)</strong> seems to adopt <strong>sclerotic glomeruli</strong> as the ground truth. <br>\nHowever, as mentioned in previous discussions, <strong>aaa6a05cc.tiff</strong>(train dataset) did not set sclerotic glomeruli to ground truth.</p>\n<p>We don't know whether or not to choose <strong>sclerotic glomeruli</strong> as the ground truth in private data. <br>\nSo we have to devise a strategy for private data because of this <strong>inconsistent labeling.</strong></p>\n<p>I think there is a <strong>need for consistent labeling</strong> for <strong>sclerotic glomeruli</strong>.<br>\nI hope this issue will be resolved in the future. <br>\nThank you.</p>",
      "rawMarkdown": "https://www.kaggle.com/c/hubmap-kidney-segmentation/discussion/228993\nThere was a discussion about this a few days ago, but I am wondering if this issue will be resolved.\n\nThe **test set(public test)** seems to adopt **sclerotic glomeruli** as the ground truth. \nHowever, as mentioned in previous discussions, **aaa6a05cc.tiff**(train dataset) did not set sclerotic glomeruli to ground truth.\n\nWe don't know whether or not to choose **sclerotic glomeruli** as the ground truth in private data. \nSo we have to devise a strategy for private data because of this **inconsistent labeling.**\n\nI think there is a **need for consistent labeling** for **sclerotic glomeruli**.\nI hope this issue will be resolved in the future. \nThank you.",
      "votes": null
    },
    {
      "id": "1256463",
      "postDate": "03/29/2021 22:27:02",
      "content": "<p>There was a reply in another thread that only non-sclerotic glomeruli should be predicted: <a href=\"https://www.kaggle.com/c/hubmap-kidney-segmentation/discussion/228993#1256424\" target=\"_blank\">https://www.kaggle.com/c/hubmap-kidney-segmentation/discussion/228993#1256424</a>. </p>",
      "rawMarkdown": "There was a reply in another thread that only non-sclerotic glomeruli should be predicted: https://www.kaggle.com/c/hubmap-kidney-segmentation/discussion/228993#1256424.",
      "votes": null
    },
    {
      "id": "1256534",
      "postDate": "03/30/2021 01:46:38",
      "content": "<p>Oh! Thank you</p>",
      "rawMarkdown": "Oh! Thank you",
      "votes": null
    },
    {
      "id": "1780329",
      "postDate": "05/07/2022 09:59:24",
      "content": "<p>Thank you.</p>",
      "rawMarkdown": "Thank you.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1256463,
      "author_name": "gdonchyts",
      "author_url": "",
      "post_date": "03/29/2021 22:27:02",
      "content": "<p>There was a reply in another thread that only non-sclerotic glomeruli should be predicted: <a href=\"https://www.kaggle.com/c/hubmap-kidney-segmentation/discussion/228993#1256424\" target=\"_blank\">https://www.kaggle.com/c/hubmap-kidney-segmentation/discussion/228993#1256424</a>. </p>",
      "votes": null,
      "replies": [
        {
          "id": 1256534,
          "author_name": "gwanghan",
          "author_url": "",
          "post_date": "03/30/2021 01:46:38",
          "content": "<p>Oh! Thank you</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1780329,
      "author_name": "kimjegonhyeon",
      "author_url": "",
      "post_date": "05/07/2022 09:59:24",
      "content": "<p>Thank you.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1256171": "https://www.kaggle.com/c/hubmap-kidney-segmentation/discussion/228993\nThere was a discussion about this a few days ago, but I am wondering if this issue will be resolved.\n\nThe **test set(public test)** seems to adopt **sclerotic glomeruli** as the ground truth. \nHowever, as mentioned in previous discussions, **aaa6a05cc.tiff**(train dataset) did not set sclerotic glomeruli to ground truth.\n\nWe don't know whether or not to choose **sclerotic glomeruli** as the ground truth in private data. \nSo we have to devise a strategy for private data because of this **inconsistent labeling.**\n\nI think there is a **need for consistent labeling** for **sclerotic glomeruli**.\nI hope this issue will be resolved in the future. \nThank you.",
    "1256463": "There was a reply in another thread that only non-sclerotic glomeruli should be predicted: https://www.kaggle.com/c/hubmap-kidney-segmentation/discussion/228993#1256424.",
    "1256534": "Oh! Thank you",
    "1780329": "Thank you."
  },
  "source": "meta"
}