{
  "id": 74132,
  "title": "12th place code release",
  "url": "/competitions/quickdraw-doodle-recognition/discussion/74132",
  "author_name": "Peiyuan Liao",
  "post_date": "2018-12-09T01:01:13.334000",
  "votes": 13,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hi everyone, we are releasing our solution to the Doodle challenge. It's located under the <a href=\"https://github.com/liaopeiyuan/ml-arsenal-public\">ml-arsenal-public</a> repository, where in the future you may find the code to all of my high scoring-solutions. The solution journal will be released in the future, but in short, we used various models, encoding methods, input sizes, and a careful ensemble (done by @ShenTao) to stabilize the score.</p>",
  "messages": [
    {
      "id": 435880,
      "postDate": "2018-12-09T01:01:13.333Z",
      "content": "<p>Hi everyone, we are releasing our solution to the Doodle challenge. It's located under the <a href=\"https://github.com/liaopeiyuan/ml-arsenal-public\">ml-arsenal-public</a> repository, where in the future you may find the code to all of my high scoring-solutions. The solution journal will be released in the future, but in short, we used various models, encoding methods, input sizes, and a careful ensemble (done by @ShenTao) to stabilize the score.</p>",
      "rawMarkdown": "Hi everyone, we are releasing our solution to the Doodle challenge. It's located under the [ml-arsenal-public][1] repository, where in the future you may find the code to all of my high scoring-solutions. The solution journal will be released in the future, but in short, we used various models, encoding methods, input sizes, and a careful ensemble (done by @ShenTao) to stabilize the score.\n\n  [1]: https://github.com/liaopeiyuan/ml-arsenal-public",
      "votes": 13
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "435880": "Hi everyone, we are releasing our solution to the Doodle challenge. It's located under the [ml-arsenal-public][1] repository, where in the future you may find the code to all of my high scoring-solutions. The solution journal will be released in the future, but in short, we used various models, encoding methods, input sizes, and a careful ensemble (done by @ShenTao) to stabilize the score.\n\n  [1]: https://github.com/liaopeiyuan/ml-arsenal-public"
  }
}