{
  "id": 146836,
  "title": "Dataset is too big? Let's make it small!",
  "url": "/competitions/prostate-cancer-grade-assessment/discussion/146836",
  "author_name": "seefun",
  "post_date": "2020-04-28T16:18:57.929000",
  "votes": 22,
  "comment_count": 4,
  "views": 0,
  "content": "<p>In this <a href=\"https://www.kaggle.com/seefun/panda-resize-crop-and-save-dataset\">kernel</a>, we down sample the image to 1/16  (1/16*h, 1/16*w, 3). Then we trim the white background to reduce the size of dataset. If the disk or computing resources are insufficient, you can consider using it.</p>\n\n<p>Kernel: <a href=\"https://www.kaggle.com/seefun/panda-resize-crop-and-save-dataset\">https://www.kaggle.com/seefun/panda-resize-crop-and-save-dataset</a>\nDataset: <a href=\"https://www.kaggle.com/seefun/panda-down16\">https://www.kaggle.com/seefun/panda-down16</a></p>\n\n<hr>\n\n<p>Reference: </p>\n\n<p>Time performance of read WSI tiff file and write in this <a href=\"https://www.kaggle.com/xhlulu/panda-resize-and-save-train-data\">kernel</a> .</p>\n\n<p>White Background Trim in this <a href=\"https://www.kaggle.com/c/prostate-cancer-grade-assessment/discussion/145618\">discussion</a>.</p>",
  "messages": [
    {
      "id": 824855,
      "postDate": "2020-04-28T16:18:57.930Z",
      "content": "<p>In this <a href=\"https://www.kaggle.com/seefun/panda-resize-crop-and-save-dataset\">kernel</a>, we down sample the image to 1/16  (1/16*h, 1/16*w, 3). Then we trim the white background to reduce the size of dataset. If the disk or computing resources are insufficient, you can consider using it.</p>\n\n<p>Kernel: <a href=\"https://www.kaggle.com/seefun/panda-resize-crop-and-save-dataset\">https://www.kaggle.com/seefun/panda-resize-crop-and-save-dataset</a>\nDataset: <a href=\"https://www.kaggle.com/seefun/panda-down16\">https://www.kaggle.com/seefun/panda-down16</a></p>\n\n<hr>\n\n<p>Reference: </p>\n\n<p>Time performance of read WSI tiff file and write in this <a href=\"https://www.kaggle.com/xhlulu/panda-resize-and-save-train-data\">kernel</a> .</p>\n\n<p>White Background Trim in this <a href=\"https://www.kaggle.com/c/prostate-cancer-grade-assessment/discussion/145618\">discussion</a>.</p>",
      "rawMarkdown": "In this [kernel](https://www.kaggle.com/seefun/panda-resize-crop-and-save-dataset), we down sample the image to 1/16  (1/16*h, 1/16*w, 3). Then we trim the white background to reduce the size of dataset. If the disk or computing resources are insufficient, you can consider using it.\n\nKernel: https://www.kaggle.com/seefun/panda-resize-crop-and-save-dataset\nDataset: https://www.kaggle.com/seefun/panda-down16\n\n------------\n\nReference: \n\nTime performance of read WSI tiff file and write in this [kernel](https://www.kaggle.com/xhlulu/panda-resize-and-save-train-data) .\n\nWhite Background Trim in this [discussion](https://www.kaggle.com/c/prostate-cancer-grade-assessment/discussion/145618).\n",
      "votes": 21
    },
    {
      "id": 826859,
      "postDate": "2020-04-29T22:52:07.180Z",
      "content": "<p>Great addition thanks! I made a <a href=\"https://www.kaggle.com/dannellyz/tissue-detection-and-size-optimization-70-shrink/\">notebook</a> inspired by your work and continuing with bounding boxes. Would be intersted in any more ideas you had that I may incorporate.</p>\n\n<p>Best,\nZ</p>",
      "rawMarkdown": "Great addition thanks! I made a [notebook](https://www.kaggle.com/dannellyz/tissue-detection-and-size-optimization-70-shrink/) inspired by your work and continuing with bounding boxes. Would be intersted in any more ideas you had that I may incorporate.\n\nBest,\nZ",
      "votes": 1
    },
    {
      "id": 826924,
      "postDate": "2020-04-30T00:24:54.817Z",
      "rawMarkdown": "",
      "votes": 1,
      "isDeleted": true
    },
    {
      "id": 914383,
      "postDate": "2020-07-03T20:13:18.937Z",
      "content": "<p>Thanks for sharing.</p>",
      "rawMarkdown": "Thanks for sharing."
    },
    {
      "id": 825048,
      "postDate": "2020-04-28T18:41:18.300Z",
      "content": "<p>Thanks for sharing :)</p>",
      "rawMarkdown": "Thanks for sharing :)"
    }
  ],
  "comments": [
    {
      "id": 826859,
      "author_name": "Zac Dannelly",
      "author_url": "",
      "post_date": "2020-04-29T22:52:07.180000",
      "content": "<p>Great addition thanks! I made a <a href=\"https://www.kaggle.com/dannellyz/tissue-detection-and-size-optimization-70-shrink/\">notebook</a> inspired by your work and continuing with bounding boxes. Would be intersted in any more ideas you had that I may incorporate.</p>\n\n<p>Best,\nZ</p>",
      "votes": 1,
      "replies": []
    },
    {
      "id": 826924,
      "author_name": "",
      "author_url": "",
      "post_date": "2020-04-30T00:24:54.817000",
      "content": "",
      "votes": 1,
      "replies": []
    },
    {
      "id": 914383,
      "author_name": "Prachi",
      "author_url": "",
      "post_date": "2020-07-03T20:13:18.937000",
      "content": "<p>Thanks for sharing.</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 825048,
      "author_name": "Alberto Maria Falletta",
      "author_url": "",
      "post_date": "2020-04-28T18:41:18.300000",
      "content": "<p>Thanks for sharing :)</p>",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "824855": "In this [kernel](https://www.kaggle.com/seefun/panda-resize-crop-and-save-dataset), we down sample the image to 1/16  (1/16*h, 1/16*w, 3). Then we trim the white background to reduce the size of dataset. If the disk or computing resources are insufficient, you can consider using it.\n\nKernel: https://www.kaggle.com/seefun/panda-resize-crop-and-save-dataset\nDataset: https://www.kaggle.com/seefun/panda-down16\n\n------------\n\nReference: \n\nTime performance of read WSI tiff file and write in this [kernel](https://www.kaggle.com/xhlulu/panda-resize-and-save-train-data) .\n\nWhite Background Trim in this [discussion](https://www.kaggle.com/c/prostate-cancer-grade-assessment/discussion/145618).\n",
    "826859": "Great addition thanks! I made a [notebook](https://www.kaggle.com/dannellyz/tissue-detection-and-size-optimization-70-shrink/) inspired by your work and continuing with bounding boxes. Would be intersted in any more ideas you had that I may incorporate.\n\nBest,\nZ",
    "826924": "",
    "914383": "Thanks for sharing.",
    "825048": "Thanks for sharing :)"
  }
}