{
  "id": 342684,
  "title": "What about test set annotations ? ",
  "url": "/competitions/hubmap-organ-segmentation/discussion/342684",
  "author_name": "Raphaël",
  "post_date": "2022-08-08T10:58:16.736000",
  "votes": 3,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Dear hosts,</p>\n<p>In <a href=\"https://www.kaggle.com/competitions/hubmap-organ-segmentation/discussion/332958\" target=\"_blank\">his post</a>, Philipp Sodmann has highlighted that the training set annotations were inconsistent and kindly offered to repost a manually corrected version (thanks to him).<br>\nBut it remains a real problem for the competition and I wanted to know if all the FTUs were correctly annotated in the public and private test set or if there was a medical rational behind this incomplete labeling?</p>",
  "messages": [
    {
      "id": 1889721,
      "postDate": "2022-08-08T10:58:16.737Z",
      "content": "<p>Dear hosts,</p>\n<p>In <a href=\"https://www.kaggle.com/competitions/hubmap-organ-segmentation/discussion/332958\" target=\"_blank\">his post</a>, Philipp Sodmann has highlighted that the training set annotations were inconsistent and kindly offered to repost a manually corrected version (thanks to him).<br>\nBut it remains a real problem for the competition and I wanted to know if all the FTUs were correctly annotated in the public and private test set or if there was a medical rational behind this incomplete labeling?</p>",
      "rawMarkdown": "Dear hosts,\n\nIn [his post](https://www.kaggle.com/competitions/hubmap-organ-segmentation/discussion/332958), Philipp Sodmann has highlighted that the training set annotations were inconsistent and kindly offered to repost a manually corrected version (thanks to him).\nBut it remains a real problem for the competition and I wanted to know if all the FTUs were correctly annotated in the public and private test set or if there was a medical rational behind this incomplete labeling?",
      "votes": 3
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1889721": "Dear hosts,\n\nIn [his post](https://www.kaggle.com/competitions/hubmap-organ-segmentation/discussion/332958), Philipp Sodmann has highlighted that the training set annotations were inconsistent and kindly offered to repost a manually corrected version (thanks to him).\nBut it remains a real problem for the competition and I wanted to know if all the FTUs were correctly annotated in the public and private test set or if there was a medical rational behind this incomplete labeling?"
  }
}