{
  "id": 223259,
  "title": "Why Resnet200D",
  "url": "/competitions/ranzcr-clip-catheter-line-classification/discussion/223259",
  "author_name": "",
  "post_date": "2021-03-03T05:17:08.346465200Z",
  "votes": 4,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Scrolling through the discussion topics and notebooks it is clear that the resnet200d seems to be the most used model for now (at least publicly). I had a question as to intuitively why that was the case. Personally, I have been trying out several networks blindly hoping that one of them would work. But is there a specific reason why a Resnet200d and not an efficientnet or even an inception resnet v2 is working for this problem?</p>",
  "messages": [
    {
      "id": "1224834",
      "postDate": "03/03/2021 05:17:08",
      "content": "<p>Scrolling through the discussion topics and notebooks it is clear that the resnet200d seems to be the most used model for now (at least publicly). I had a question as to intuitively why that was the case. Personally, I have been trying out several networks blindly hoping that one of them would work. But is there a specific reason why a Resnet200d and not an efficientnet or even an inception resnet v2 is working for this problem?</p>",
      "rawMarkdown": "Scrolling through the discussion topics and notebooks it is clear that the resnet200d seems to be the most used model for now (at least publicly). I had a question as to intuitively why that was the case. Personally, I have been trying out several networks blindly hoping that one of them would work. But is there a specific reason why a Resnet200d and not an efficientnet or even an inception resnet v2 is working for this problem?",
      "votes": null
    },
    {
      "id": "1224891",
      "postDate": "03/03/2021 06:39:49",
      "content": "<p>because it gives high scores and well, that's all.</p>",
      "rawMarkdown": "because it gives high scores and well, that's all.",
      "votes": null
    },
    {
      "id": "1225182",
      "postDate": "03/03/2021 11:53:07",
      "content": "<p>Basically it's working on this case…</p>",
      "rawMarkdown": "Basically it's working on this case...",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1224891,
      "author_name": "moewie94",
      "author_url": "",
      "post_date": "03/03/2021 06:39:49",
      "content": "<p>because it gives high scores and well, that's all.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1225182,
      "author_name": "datafan07",
      "author_url": "",
      "post_date": "03/03/2021 11:53:07",
      "content": "<p>Basically it's working on this case…</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1224834": "Scrolling through the discussion topics and notebooks it is clear that the resnet200d seems to be the most used model for now (at least publicly). I had a question as to intuitively why that was the case. Personally, I have been trying out several networks blindly hoping that one of them would work. But is there a specific reason why a Resnet200d and not an efficientnet or even an inception resnet v2 is working for this problem?",
    "1224891": "because it gives high scores and well, that's all.",
    "1225182": "Basically it's working on this case..."
  },
  "source": "meta"
}