{
  "id": 200562,
  "title": "train_fp purpose",
  "url": "/competitions/rfcx-species-audio-detection/discussion/200562",
  "author_name": "",
  "post_date": "2020-12-01T01:40:42.755102400Z",
  "votes": 5,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I still quite not understand the purpose of <strong>train_fp</strong>. If according to the competition description:</p>\n<p><code>Each row in train_fp.csv corresponds to a flagged segment that was verified to not contain the species and songtype</code></p>\n<p>Then:</p>\n<p>1)  What is the purpose of knowing that on certain seconds of a particular audio a species was not present?<br>\n2) Should we treat them as if they did?</p>\n<p>Thanks</p>",
  "messages": [
    {
      "id": "1097234",
      "postDate": "12/01/2020 01:40:42",
      "content": "<p>I still quite not understand the purpose of <strong>train_fp</strong>. If according to the competition description:</p>\n<p><code>Each row in train_fp.csv corresponds to a flagged segment that was verified to not contain the species and songtype</code></p>\n<p>Then:</p>\n<p>1)  What is the purpose of knowing that on certain seconds of a particular audio a species was not present?<br>\n2) Should we treat them as if they did?</p>\n<p>Thanks</p>",
      "rawMarkdown": "I still quite not understand the purpose of **train_fp**. If according to the competition description:\n\n`Each row in train_fp.csv corresponds to a flagged segment that was verified to not contain the species and songtype`\n\nThen:\n\n1)  What is the purpose of knowing that on certain seconds of a particular audio a species was not present?\n2) Should we treat them as if they did?\n\nThanks",
      "votes": null
    },
    {
      "id": "1097274",
      "postDate": "12/01/2020 02:06:12",
      "content": "<p>According to the host, train_fp is a set of events that were automatically classified as one of the target classes and confirmed to be false positives by human annotators later on. This means those events were something similar to the true positives so we can use them as hard negative examples.</p>\n<p><a href=\"https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/197866#1083495\" target=\"_blank\">https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/197866#1083495</a></p>",
      "rawMarkdown": "According to the host, train_fp is a set of events that were automatically classified as one of the target classes and confirmed to be false positives by human annotators later on. This means those events were something similar to the true positives so we can use them as hard negative examples.\n\nhttps://www.kaggle.com/c/rfcx-species-audio-detection/discussion/197866#1083495",
      "votes": null
    },
    {
      "id": "1097293",
      "postDate": "12/01/2020 02:16:17",
      "content": "<p>Thank you very much!</p>",
      "rawMarkdown": "Thank you very much!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1097274,
      "author_name": "hidehisaarai1213",
      "author_url": "",
      "post_date": "12/01/2020 02:06:12",
      "content": "<p>According to the host, train_fp is a set of events that were automatically classified as one of the target classes and confirmed to be false positives by human annotators later on. This means those events were something similar to the true positives so we can use them as hard negative examples.</p>\n<p><a href=\"https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/197866#1083495\" target=\"_blank\">https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/197866#1083495</a></p>",
      "votes": null,
      "replies": [
        {
          "id": 1097293,
          "author_name": "alejopaullier",
          "author_url": "",
          "post_date": "12/01/2020 02:16:17",
          "content": "<p>Thank you very much!</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1097234": "I still quite not understand the purpose of **train_fp**. If according to the competition description:\n\n`Each row in train_fp.csv corresponds to a flagged segment that was verified to not contain the species and songtype`\n\nThen:\n\n1)  What is the purpose of knowing that on certain seconds of a particular audio a species was not present?\n2) Should we treat them as if they did?\n\nThanks",
    "1097274": "According to the host, train_fp is a set of events that were automatically classified as one of the target classes and confirmed to be false positives by human annotators later on. This means those events were something similar to the true positives so we can use them as hard negative examples.\n\nhttps://www.kaggle.com/c/rfcx-species-audio-detection/discussion/197866#1083495",
    "1097293": "Thank you very much!"
  },
  "source": "meta"
}