{
  "id": 93539,
  "title": "confuse about the evaluation",
  "url": "/competitions/imaterialist-fashion-2019-FGVC6/discussion/93539",
  "author_name": "",
  "post_date": "2019-05-28T02:45:11.465796500Z",
  "votes": null,
  "comment_count": 2,
  "views": 0,
  "content": "<p>If the label is  3-1-10-20-41-60-61-91, but I only predict the class  3, don't have the attributes,  then how to compute the score ? The  attributes is accotiated to the correct class ID and attribution ID ?\nThanks ！！！</p>",
  "messages": [
    {
      "id": "538028",
      "postDate": "05/28/2019 02:45:11",
      "content": "<p>If the label is  3-1-10-20-41-60-61-91, but I only predict the class  3, don't have the attributes,  then how to compute the score ? The  attributes is accotiated to the correct class ID and attribution ID ?\nThanks ！！！</p>",
      "rawMarkdown": "If the label is  3-1-10-20-41-60-61-91, but I only predict the class  3, don't have the attributes,  then how to compute the score ? The  attributes is accotiated to the correct class ID and attribution ID ?\nThanks ！！！",
      "votes": null
    },
    {
      "id": "538047",
      "postDate": "05/28/2019 03:36:39",
      "content": "<p>According to</p>\n\n<blockquote>\n  <p>It is important to distinguish both fine-grained classes of the object as well as object instances. If the mask is correct but the class associated with the mask is wrong then it is considered a false positive.</p>\n</blockquote>",
      "rawMarkdown": "According to\n&gt; It is important to distinguish both fine-grained classes of the object as well as object instances. If the mask is correct but the class associated with the mask is wrong then it is considered a false positive.",
      "votes": null
    },
    {
      "id": "538100",
      "postDate": "05/28/2019 06:12:09",
      "content": "",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 538047,
      "author_name": "raykoo",
      "author_url": "",
      "post_date": "05/28/2019 03:36:39",
      "content": "<p>According to</p>\n\n<blockquote>\n  <p>It is important to distinguish both fine-grained classes of the object as well as object instances. If the mask is correct but the class associated with the mask is wrong then it is considered a false positive.</p>\n</blockquote>",
      "votes": null,
      "replies": [
        {
          "id": 538100,
          "author_name": "sunxiaotao",
          "author_url": "",
          "post_date": "05/28/2019 06:12:09",
          "content": "",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "538028": "If the label is  3-1-10-20-41-60-61-91, but I only predict the class  3, don't have the attributes,  then how to compute the score ? The  attributes is accotiated to the correct class ID and attribution ID ?\nThanks ！！！",
    "538047": "According to\n&gt; It is important to distinguish both fine-grained classes of the object as well as object instances. If the mask is correct but the class associated with the mask is wrong then it is considered a false positive.",
    "538100": ""
  },
  "source": "meta"
}