{
  "id": 471034,
  "title": "Train targets vs Submission output equivalence ",
  "url": "/competitions/hms-harmful-brain-activity-classification/discussion/471034",
  "author_name": "",
  "post_date": "2024-01-26T17:12:56.107028200Z",
  "votes": 1,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Maybe it's obvious for everyone but me since I didn't find the discussion about it, <br>\nBut how do the train targets are related to the expected output? <br>\nI presume test data was also labeled by experts, just as it is in train data, and then their votes were Softmaxed, and that is what is expected in the submission output?  Just need a confirmation, so there are no surprises.</p>",
  "messages": [
    {
      "id": "2621286",
      "postDate": "01/26/2024 17:12:56",
      "content": "<p>Maybe it's obvious for everyone but me since I didn't find the discussion about it, <br>\nBut how do the train targets are related to the expected output? <br>\nI presume test data was also labeled by experts, just as it is in train data, and then their votes were Softmaxed, and that is what is expected in the submission output?  Just need a confirmation, so there are no surprises.</p>",
      "rawMarkdown": "Maybe it's obvious for everyone but me since I didn't find the discussion about it, \nBut how do the train targets are related to the expected output? \nI presume test data was also labeled by experts, just as it is in train data, and then their votes were Softmaxed, and that is what is expected in the submission output?  Just need a confirmation, so there are no surprises.",
      "votes": null
    },
    {
      "id": "2621768",
      "postDate": "01/27/2024 01:20:07",
      "content": "<blockquote>\n  <p>and that is what is expected in the submission output?</p>\n</blockquote>\n<p>Correct.</p>\n<p>You can confirm it in competition description:</p>\n<blockquote>\n  <p>(…) For each eeg_id in the test set, you must predict a probability for each of the vote columns</p>\n</blockquote>",
      "rawMarkdown": "> and that is what is expected in the submission output?\n\nCorrect.\n\nYou can confirm it in competition description:\n> (...) For each eeg_id in the test set, you must predict a probability for each of the vote columns",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2621768,
      "author_name": "serjhenrique",
      "author_url": "",
      "post_date": "01/27/2024 01:20:07",
      "content": "<blockquote>\n  <p>and that is what is expected in the submission output?</p>\n</blockquote>\n<p>Correct.</p>\n<p>You can confirm it in competition description:</p>\n<blockquote>\n  <p>(…) For each eeg_id in the test set, you must predict a probability for each of the vote columns</p>\n</blockquote>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2621286": "Maybe it's obvious for everyone but me since I didn't find the discussion about it, \nBut how do the train targets are related to the expected output? \nI presume test data was also labeled by experts, just as it is in train data, and then their votes were Softmaxed, and that is what is expected in the submission output?  Just need a confirmation, so there are no surprises.",
    "2621768": "> and that is what is expected in the submission output?\n\nCorrect.\n\nYou can confirm it in competition description:\n> (...) For each eeg_id in the test set, you must predict a probability for each of the vote columns"
  },
  "source": "meta"
}