{
  "id": 238176,
  "title": "What do you decide the input spectrum-image size?",
  "url": "/competitions/birdclef-2021/discussion/238176",
  "author_name": "furu-nag",
  "post_date": "2021-05-11T11:49:23.035000",
  "votes": 3,
  "comment_count": 0,
  "views": 0,
  "content": "<p>CNN model in the audio detection  needs to the spectrum image. The images is then consist of the two dimension, time bin and frequency bin. Moreover, some optionally carry out melfilterbank.<br>\nHow do you decide the size of time bin and frequency bin?<br>\nAlso, After you divide the time bin and frequency bin, Do you resize the spectrum-image?</p>\n<p>I would appreciate it if you could introduce the method you are using.</p>\n<p>Supplementary:<br>\nI will paste the information that seems to be helpful here<br>\n<a href=\"https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/220760\" target=\"_blank\">https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/220760</a></p>",
  "messages": [
    {
      "id": 1302106,
      "postDate": "2021-05-11T11:49:23.037Z",
      "content": "<p>CNN model in the audio detection  needs to the spectrum image. The images is then consist of the two dimension, time bin and frequency bin. Moreover, some optionally carry out melfilterbank.<br>\nHow do you decide the size of time bin and frequency bin?<br>\nAlso, After you divide the time bin and frequency bin, Do you resize the spectrum-image?</p>\n<p>I would appreciate it if you could introduce the method you are using.</p>\n<p>Supplementary:<br>\nI will paste the information that seems to be helpful here<br>\n<a href=\"https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/220760\" target=\"_blank\">https://www.kaggle.com/c/rfcx-species-audio-detection/discussion/220760</a></p>",
      "rawMarkdown": "CNN model in the audio detection  needs to the spectrum image. The images is then consist of the two dimension, time bin and frequency bin. Moreover, some optionally carry out melfilterbank.\nHow do you decide the size of time bin and frequency bin?\nAlso, After you divide the time bin and frequency bin, Do you resize the spectrum-image?\n\nI would appreciate it if you could introduce the method you are using.\n\nSupplementary:\nI will paste the information that seems to be helpful here\nhttps://www.kaggle.com/c/rfcx-species-audio-detection/discussion/220760",
      "votes": 3
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1302106": "CNN model in the audio detection  needs to the spectrum image. The images is then consist of the two dimension, time bin and frequency bin. Moreover, some optionally carry out melfilterbank.\nHow do you decide the size of time bin and frequency bin?\nAlso, After you divide the time bin and frequency bin, Do you resize the spectrum-image?\n\nI would appreciate it if you could introduce the method you are using.\n\nSupplementary:\nI will paste the information that seems to be helpful here\nhttps://www.kaggle.com/c/rfcx-species-audio-detection/discussion/220760"
  }
}