{
  "id": 332830,
  "title": "Mask Dataset in PNG format",
  "url": "/competitions/hubmap-organ-segmentation/discussion/332830",
  "author_name": "",
  "post_date": "2022-06-23T14:04:40.119731Z",
  "votes": 13,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Here is the mask dataset in PNG format. Hope this helps you by eliminating the need to decode RLE during training</p>\n<p><a href=\"https://www.kaggle.com/datasets/nishantbhansali/hubmap-hpa-2022-maskdataset\" target=\"_blank\">https://www.kaggle.com/datasets/nishantbhansali/hubmap-hpa-2022-maskdataset</a></p>\n<p>The masks have not been resized. They will be as per the size of the corresponding input image.<br>\nAlthough I am confused as to how will we resize the masks to feed it into the model?</p>\n<p>Do let me know in case of any discrepancies.</p>",
  "messages": [
    {
      "id": "1830562",
      "postDate": "06/23/2022 14:04:40",
      "content": "<p>Here is the mask dataset in PNG format. Hope this helps you by eliminating the need to decode RLE during training</p>\n<p><a href=\"https://www.kaggle.com/datasets/nishantbhansali/hubmap-hpa-2022-maskdataset\" target=\"_blank\">https://www.kaggle.com/datasets/nishantbhansali/hubmap-hpa-2022-maskdataset</a></p>\n<p>The masks have not been resized. They will be as per the size of the corresponding input image.<br>\nAlthough I am confused as to how will we resize the masks to feed it into the model?</p>\n<p>Do let me know in case of any discrepancies.</p>",
      "rawMarkdown": "Here is the mask dataset in PNG format. Hope this helps you by eliminating the need to decode RLE during training\n\nhttps://www.kaggle.com/datasets/nishantbhansali/hubmap-hpa-2022-maskdataset\n\nThe masks have not been resized. They will be as per the size of the corresponding input image.\nAlthough I am confused as to how will we resize the masks to feed it into the model?\n\nDo let me know in case of any discrepancies.",
      "votes": null
    },
    {
      "id": "1838199",
      "postDate": "06/30/2022 10:15:21",
      "content": "<p>have something similar: <a href=\"https://www.kaggle.com/datasets/jirkaborovec/hacking-the-human-body-annotation-masks\" target=\"_blank\">https://www.kaggle.com/datasets/jirkaborovec/hacking-the-human-body-annotation-masks</a><br>\nplus a notebook on how to tile the large images: <a href=\"https://www.kaggle.com/code/jirkaborovec/ftus-segm-decompose-large-images-to-tiles\" target=\"_blank\">https://www.kaggle.com/code/jirkaborovec/ftus-segm-decompose-large-images-to-tiles</a></p>",
      "rawMarkdown": "have something similar: https://www.kaggle.com/datasets/jirkaborovec/hacking-the-human-body-annotation-masks\nplus a notebook on how to tile the large images: https://www.kaggle.com/code/jirkaborovec/ftus-segm-decompose-large-images-to-tiles",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1838199,
      "author_name": "jirkaborovec",
      "author_url": "",
      "post_date": "06/30/2022 10:15:21",
      "content": "<p>have something similar: <a href=\"https://www.kaggle.com/datasets/jirkaborovec/hacking-the-human-body-annotation-masks\" target=\"_blank\">https://www.kaggle.com/datasets/jirkaborovec/hacking-the-human-body-annotation-masks</a><br>\nplus a notebook on how to tile the large images: <a href=\"https://www.kaggle.com/code/jirkaborovec/ftus-segm-decompose-large-images-to-tiles\" target=\"_blank\">https://www.kaggle.com/code/jirkaborovec/ftus-segm-decompose-large-images-to-tiles</a></p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1830562": "Here is the mask dataset in PNG format. Hope this helps you by eliminating the need to decode RLE during training\n\nhttps://www.kaggle.com/datasets/nishantbhansali/hubmap-hpa-2022-maskdataset\n\nThe masks have not been resized. They will be as per the size of the corresponding input image.\nAlthough I am confused as to how will we resize the masks to feed it into the model?\n\nDo let me know in case of any discrepancies.",
    "1838199": "have something similar: https://www.kaggle.com/datasets/jirkaborovec/hacking-the-human-body-annotation-masks\nplus a notebook on how to tile the large images: https://www.kaggle.com/code/jirkaborovec/ftus-segm-decompose-large-images-to-tiles"
  },
  "source": "meta"
}