{
  "id": 114838,
  "title": "Difference between micro-F1 and F1",
  "url": "/competitions/tensorflow2-question-answering/discussion/114838",
  "author_name": "",
  "post_date": "2019-10-29T16:24:36.539307700Z",
  "votes": 15,
  "comment_count": 1,
  "views": 0,
  "content": "<blockquote>\n  <p>Submissions are evaluated using micro F1</p>\n</blockquote>\n\n<p>If you click on the link it takes you to wikipedia page for F1 score, I was wondering how is <code>micro F1</code> used in this competition different from <code>F1</code> found the following article helpful <a href=\"https://towardsdatascience.com/multi-class-metrics-made-simple-part-ii-the-f1-score-ebe8b2c2ca1\">https://towardsdatascience.com/multi-class-metrics-made-simple-part-ii-the-f1-score-ebe8b2c2ca1</a>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F551520%2Fd90cda4312c37cabd12ca15e8e8c60b5%2FScreen%20Shot%202019-10-29%20at%204.22.36%20PM.png?generation=1572366201109359&amp;alt=media\" alt=\"\"></p>",
  "messages": [
    {
      "id": "660803",
      "postDate": "10/29/2019 16:24:36",
      "content": "<blockquote>\n  <p>Submissions are evaluated using micro F1</p>\n</blockquote>\n\n<p>If you click on the link it takes you to wikipedia page for F1 score, I was wondering how is <code>micro F1</code> used in this competition different from <code>F1</code> found the following article helpful <a href=\"https://towardsdatascience.com/multi-class-metrics-made-simple-part-ii-the-f1-score-ebe8b2c2ca1\">https://towardsdatascience.com/multi-class-metrics-made-simple-part-ii-the-f1-score-ebe8b2c2ca1</a>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F551520%2Fd90cda4312c37cabd12ca15e8e8c60b5%2FScreen%20Shot%202019-10-29%20at%204.22.36%20PM.png?generation=1572366201109359&amp;alt=media\" alt=\"\"></p>",
      "rawMarkdown": "&gt;Submissions are evaluated using micro F1\n\nIf you click on the link it takes you to wikipedia page for F1 score, I was wondering how is `micro F1` used in this competition different from `F1` found the following article helpful https://towardsdatascience.com/multi-class-metrics-made-simple-part-ii-the-f1-score-ebe8b2c2ca1\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F551520%2Fd90cda4312c37cabd12ca15e8e8c60b5%2FScreen%20Shot%202019-10-29%20at%204.22.36%20PM.png?generation=1572366201109359&amp;alt=media)",
      "votes": null
    },
    {
      "id": "669735",
      "postDate": "11/10/2019 12:00:03",
      "content": "<p>Thanks! It's good to understand that micro-F1 is just accuracy. </p>",
      "rawMarkdown": "Thanks! It's good to understand that micro-F1 is just accuracy.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 669735,
      "author_name": "kashnitsky",
      "author_url": "",
      "post_date": "11/10/2019 12:00:03",
      "content": "<p>Thanks! It's good to understand that micro-F1 is just accuracy. </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "660803": "&gt;Submissions are evaluated using micro F1\n\nIf you click on the link it takes you to wikipedia page for F1 score, I was wondering how is `micro F1` used in this competition different from `F1` found the following article helpful https://towardsdatascience.com/multi-class-metrics-made-simple-part-ii-the-f1-score-ebe8b2c2ca1\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F551520%2Fd90cda4312c37cabd12ca15e8e8c60b5%2FScreen%20Shot%202019-10-29%20at%204.22.36%20PM.png?generation=1572366201109359&amp;alt=media)",
    "669735": "Thanks! It's good to understand that micro-F1 is just accuracy."
  },
  "source": "meta"
}