{
  "id": 412802,
  "title": " ViT Segmentation Overview for HuBMAP - Hacking the Kidney",
  "url": "/competitions/hubmap-hacking-the-human-vasculature/discussion/412802",
  "author_name": "",
  "post_date": "2023-05-25T09:55:03.253651100Z",
  "votes": 6,
  "comment_count": 2,
  "views": 0,
  "content": "<h1>Vision Transformer Segmentation</h1>\n<p>Apply ViT Transformer PyTorch to Identify glomeruli in human kidney tissue images</p>\n<h2>Competetion</h2>\n<p><a href=\"https://www.kaggle.com/competitions/hubmap-kidney-segmentation\" target=\"_blank\">HuBMAP - Hacking the Kidney</a></p>\n<h2>Evaluation</h2>\n<p>This competition is evaluated on <strong>the mean Dice coefficient.</strong> The Dice coefficient can be used to compare the pixel-wise agreement between a predicted segmentation and its corresponding ground truth.</p>\n<h3>Score</h3>\n<table>\n<thead>\n<tr>\n<th>Private Score</th>\n<th>Public Score</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>0.9354</td>\n<td>0.9064</td>\n</tr>\n</tbody>\n</table>\n<hr>\n<p>Copy &amp; Edit directly <a href=\"https://www.kaggle.com/elcaiseri\" target=\"_blank\">Kaggle@elcaiseri</a></p>\n<ol>\n<li><strong>Training:</strong> <a href=\"https://www.kaggle.com/code/elcaiseri/hubmap-pytorch-vit-segmentation-starter-train\" target=\"_blank\">hubmap-pytorch-vit-segmentation-train</a></li>\n<li><strong>Inference:</strong> <a href=\"https://www.kaggle.com/code/elcaiseri/hubmap-pytorch-vit-segmentation-sub1\" target=\"_blank\">hubmap-pytorch-vit-segmentation-inference</a></li>\n</ol>\n<p>good luck,</p>",
  "messages": [
    {
      "id": "2273624",
      "postDate": "05/25/2023 09:55:03",
      "content": "<h1>Vision Transformer Segmentation</h1>\n<p>Apply ViT Transformer PyTorch to Identify glomeruli in human kidney tissue images</p>\n<h2>Competetion</h2>\n<p><a href=\"https://www.kaggle.com/competitions/hubmap-kidney-segmentation\" target=\"_blank\">HuBMAP - Hacking the Kidney</a></p>\n<h2>Evaluation</h2>\n<p>This competition is evaluated on <strong>the mean Dice coefficient.</strong> The Dice coefficient can be used to compare the pixel-wise agreement between a predicted segmentation and its corresponding ground truth.</p>\n<h3>Score</h3>\n<table>\n<thead>\n<tr>\n<th>Private Score</th>\n<th>Public Score</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>0.9354</td>\n<td>0.9064</td>\n</tr>\n</tbody>\n</table>\n<hr>\n<p>Copy &amp; Edit directly <a href=\"https://www.kaggle.com/elcaiseri\" target=\"_blank\">Kaggle@elcaiseri</a></p>\n<ol>\n<li><strong>Training:</strong> <a href=\"https://www.kaggle.com/code/elcaiseri/hubmap-pytorch-vit-segmentation-starter-train\" target=\"_blank\">hubmap-pytorch-vit-segmentation-train</a></li>\n<li><strong>Inference:</strong> <a href=\"https://www.kaggle.com/code/elcaiseri/hubmap-pytorch-vit-segmentation-sub1\" target=\"_blank\">hubmap-pytorch-vit-segmentation-inference</a></li>\n</ol>\n<p>good luck,</p>",
      "rawMarkdown": "# Vision Transformer Segmentation\n\nApply ViT Transformer PyTorch to Identify glomeruli in human kidney tissue images\n\n## Competetion\n[HuBMAP - Hacking the Kidney](https://www.kaggle.com/competitions/hubmap-kidney-segmentation)\n\n## Evaluation \nThis competition is evaluated on **the mean Dice coefficient.** The Dice coefficient can be used to compare the pixel-wise agreement between a predicted segmentation and its corresponding ground truth.\n\n### Score\n\n| Private Score | Public Score |\n| --- | --- |\n| 0.9354 | 0.9064 |\n\n\n<hr>\n\nCopy & Edit directly [Kaggle@elcaiseri](https://www.kaggle.com/elcaiseri)\n1. **Training:** [hubmap-pytorch-vit-segmentation-train](https://www.kaggle.com/code/elcaiseri/hubmap-pytorch-vit-segmentation-starter-train)\n2. **Inference:** [hubmap-pytorch-vit-segmentation-inference](https://www.kaggle.com/code/elcaiseri/hubmap-pytorch-vit-segmentation-sub1)\n\n\ngood luck,",
      "votes": null
    },
    {
      "id": "2273661",
      "postDate": "05/25/2023 10:20:23",
      "content": "<p>Maybe we can train the same model in this competition.</p>",
      "rawMarkdown": "Maybe we can train the same model in this competition.",
      "votes": null
    },
    {
      "id": "2273683",
      "postDate": "05/25/2023 10:36:14",
      "content": "<p>Yes, I think so.</p>",
      "rawMarkdown": "Yes, I think so.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2273661,
      "author_name": "dwchen",
      "author_url": "",
      "post_date": "05/25/2023 10:20:23",
      "content": "<p>Maybe we can train the same model in this competition.</p>",
      "votes": null,
      "replies": [
        {
          "id": 2273683,
          "author_name": "elcaiseri",
          "author_url": "",
          "post_date": "05/25/2023 10:36:14",
          "content": "<p>Yes, I think so.</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2273624": "# Vision Transformer Segmentation\n\nApply ViT Transformer PyTorch to Identify glomeruli in human kidney tissue images\n\n## Competetion\n[HuBMAP - Hacking the Kidney](https://www.kaggle.com/competitions/hubmap-kidney-segmentation)\n\n## Evaluation \nThis competition is evaluated on **the mean Dice coefficient.** The Dice coefficient can be used to compare the pixel-wise agreement between a predicted segmentation and its corresponding ground truth.\n\n### Score\n\n| Private Score | Public Score |\n| --- | --- |\n| 0.9354 | 0.9064 |\n\n\n<hr>\n\nCopy & Edit directly [Kaggle@elcaiseri](https://www.kaggle.com/elcaiseri)\n1. **Training:** [hubmap-pytorch-vit-segmentation-train](https://www.kaggle.com/code/elcaiseri/hubmap-pytorch-vit-segmentation-starter-train)\n2. **Inference:** [hubmap-pytorch-vit-segmentation-inference](https://www.kaggle.com/code/elcaiseri/hubmap-pytorch-vit-segmentation-sub1)\n\n\ngood luck,",
    "2273661": "Maybe we can train the same model in this competition.",
    "2273683": "Yes, I think so."
  },
  "source": "meta"
}