{
  "id": 146124,
  "title": "fastai2 starter kernel",
  "url": "/competitions/prostate-cancer-grade-assessment/discussion/146124",
  "author_name": "ilovescience",
  "post_date": "2020-04-26T00:24:37.162000",
  "votes": 3,
  "comment_count": 0,
  "views": 0,
  "content": "<p>I have written a starter kernel over here:\n<a href=\"https://www.kaggle.com/tanlikesmath/prostate-cancer-grading-intro-fastai2-starter\">https://www.kaggle.com/tanlikesmath/prostate-cancer-grading-intro-fastai2-starter</a></p>\n\n<p>It uses a single Se_ResNext50 model trained on a <a href=\"https://www.kaggle.com/tanlikesmath/panda-challenge-512x512-resized-dataset\">512x512 resized dataset</a> that I created. It also includes a \"quick-n-dirty\" EDA as well. I hope this is helpful for those starting out 😄 </p>",
  "messages": [
    {
      "id": 821154,
      "postDate": "2020-04-26T00:24:37.163Z",
      "content": "<p>I have written a starter kernel over here:\n<a href=\"https://www.kaggle.com/tanlikesmath/prostate-cancer-grading-intro-fastai2-starter\">https://www.kaggle.com/tanlikesmath/prostate-cancer-grading-intro-fastai2-starter</a></p>\n\n<p>It uses a single Se_ResNext50 model trained on a <a href=\"https://www.kaggle.com/tanlikesmath/panda-challenge-512x512-resized-dataset\">512x512 resized dataset</a> that I created. It also includes a \"quick-n-dirty\" EDA as well. I hope this is helpful for those starting out 😄 </p>",
      "rawMarkdown": "I have written a starter kernel over here:\nhttps://www.kaggle.com/tanlikesmath/prostate-cancer-grading-intro-fastai2-starter\n\nIt uses a single Se_ResNext50 model trained on a [512x512 resized dataset](https://www.kaggle.com/tanlikesmath/panda-challenge-512x512-resized-dataset) that I created. It also includes a \"quick-n-dirty\" EDA as well. I hope this is helpful for those starting out 😄 ",
      "votes": 3
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "821154": "I have written a starter kernel over here:\nhttps://www.kaggle.com/tanlikesmath/prostate-cancer-grading-intro-fastai2-starter\n\nIt uses a single Se_ResNext50 model trained on a [512x512 resized dataset](https://www.kaggle.com/tanlikesmath/panda-challenge-512x512-resized-dataset) that I created. It also includes a \"quick-n-dirty\" EDA as well. I hope this is helpful for those starting out 😄 "
  }
}