{
  "id": 98468,
  "title": "Starter kernel for transfer learning from previous competition",
  "url": "/competitions/aptos2019-blindness-detection/discussion/98468",
  "author_name": "",
  "post_date": "2019-07-04T02:31:02.835456200Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>As promised, here is a <a href=\"https://www.kaggle.com/tanlikesmath/training-on-previous-dataset-for-aptos\">starter kernel</a> for training on the previous dataset and transfer learning for this task. It is probably not helpful in its current form due to the time limitations, but if you separate the two training steps into two kernels you might be able to achieve better results.</p>",
  "messages": [
    {
      "id": "567787",
      "postDate": "07/04/2019 02:31:02",
      "content": "<p>As promised, here is a <a href=\"https://www.kaggle.com/tanlikesmath/training-on-previous-dataset-for-aptos\">starter kernel</a> for training on the previous dataset and transfer learning for this task. It is probably not helpful in its current form due to the time limitations, but if you separate the two training steps into two kernels you might be able to achieve better results.</p>",
      "rawMarkdown": "As promised, here is a [starter kernel](https://www.kaggle.com/tanlikesmath/training-on-previous-dataset-for-aptos) for training on the previous dataset and transfer learning for this task. It is probably not helpful in its current form due to the time limitations, but if you separate the two training steps into two kernels you might be able to achieve better results.",
      "votes": null
    },
    {
      "id": "567845",
      "postDate": "07/04/2019 04:43:03",
      "content": "<p>I see you have <code>internet access</code> enabled, that will prevent from making subs..</p>",
      "rawMarkdown": "I see you have `internet access` enabled, that will prevent from making subs..",
      "votes": null
    },
    {
      "id": "567848",
      "postDate": "07/04/2019 04:46:54",
      "content": "<p>Oops! I will fix it ASAP! Sorry about that!</p>",
      "rawMarkdown": "Oops! I will fix it ASAP! Sorry about that!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 567845,
      "author_name": "adityaecdrid",
      "author_url": "",
      "post_date": "07/04/2019 04:43:03",
      "content": "<p>I see you have <code>internet access</code> enabled, that will prevent from making subs..</p>",
      "votes": null,
      "replies": [
        {
          "id": 567848,
          "author_name": "tanlikesmath",
          "author_url": "",
          "post_date": "07/04/2019 04:46:54",
          "content": "<p>Oops! I will fix it ASAP! Sorry about that!</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "567787": "As promised, here is a [starter kernel](https://www.kaggle.com/tanlikesmath/training-on-previous-dataset-for-aptos) for training on the previous dataset and transfer learning for this task. It is probably not helpful in its current form due to the time limitations, but if you separate the two training steps into two kernels you might be able to achieve better results.",
    "567845": "I see you have `internet access` enabled, that will prevent from making subs..",
    "567848": "Oops! I will fix it ASAP! Sorry about that!"
  },
  "source": "meta"
}