{
  "id": 160793,
  "title": "Introduction Notebook",
  "url": "/competitions/tpu-getting-started/discussion/160793",
  "author_name": "Kurian Benoy",
  "post_date": "2020-06-22T17:41:51.015000",
  "votes": 1,
  "comment_count": 2,
  "views": null,
  "content": "<p>I have written an introduction notebook for getting started in the competition- Petals to the Metals.</p>\n\n<p><a href=\"https://www.kaggle.com/kurianbenoy/introduction-kernel-for-petal2metal-flowers\">Introduction notebook</a></p>\n\n<h2>Tips to improve the score</h2>\n\n<ul>\n<li>Use augmentations (checkout <a href=\"https://www.kaggle.com/c/flower-classification-with-tpus/discussion\">discussions to what all worked</a></li>\n<li><a href=\"https://www.kaggle.com/romanweilguny/tpu-flowers-first-love\">Techniques to improve scores</a></li>\n<li>Check the best score notebooks in Flower classification comp(there are SOTA models out there)</li>\n<li>Use Big Transfer architecture: <a href=\"https://github.com/google-research/big_transfer\">code</a></li>\n</ul>",
  "messages": [
    {
      "id": 897199,
      "postDate": "2020-06-22T17:41:51.017Z",
      "content": "<p>I have written an introduction notebook for getting started in the competition- Petals to the Metals.</p>\n\n<p><a href=\"https://www.kaggle.com/kurianbenoy/introduction-kernel-for-petal2metal-flowers\">Introduction notebook</a></p>\n\n<h2>Tips to improve the score</h2>\n\n<ul>\n<li>Use augmentations (checkout <a href=\"https://www.kaggle.com/c/flower-classification-with-tpus/discussion\">discussions to what all worked</a></li>\n<li><a href=\"https://www.kaggle.com/romanweilguny/tpu-flowers-first-love\">Techniques to improve scores</a></li>\n<li>Check the best score notebooks in Flower classification comp(there are SOTA models out there)</li>\n<li>Use Big Transfer architecture: <a href=\"https://github.com/google-research/big_transfer\">code</a></li>\n</ul>",
      "rawMarkdown": "I have written an introduction notebook for getting started in the competition- Petals to the Metals.\n\n[Introduction notebook](https://www.kaggle.com/kurianbenoy/introduction-kernel-for-petal2metal-flowers)\n\n## Tips to improve the score\n\n- Use augmentations (checkout [discussions to what all worked](https://www.kaggle.com/c/flower-classification-with-tpus/discussion)\n- [Techniques to improve scores](https://www.kaggle.com/romanweilguny/tpu-flowers-first-love)\n- Check the best score notebooks in Flower classification comp(there are SOTA models out there)\n- Use Big Transfer architecture: [code](https://github.com/google-research/big_transfer)",
      "votes": 1
    },
    {
      "id": 1624042,
      "postDate": "2021-12-20T14:01:59.040Z",
      "content": "<p>**Great!! **thanks for this awesome intro!!!!</p>",
      "rawMarkdown": "**Great!! **thanks for this awesome intro!!!!"
    },
    {
      "id": 897334,
      "postDate": "2020-06-22T19:29:59.350Z",
      "content": "<p>Great!</p>",
      "rawMarkdown": "Great!"
    }
  ],
  "comments": [
    {
      "id": 1624042,
      "author_name": "Shehan Weerakkody",
      "author_url": "",
      "post_date": "2021-12-20T14:01:59.040000",
      "content": "<p>**Great!! **thanks for this awesome intro!!!!</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 897334,
      "author_name": "Rashidul Hasan Hridoy",
      "author_url": "",
      "post_date": "2020-06-22T19:29:59.350000",
      "content": "<p>Great!</p>",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "897199": "I have written an introduction notebook for getting started in the competition- Petals to the Metals.\n\n[Introduction notebook](https://www.kaggle.com/kurianbenoy/introduction-kernel-for-petal2metal-flowers)\n\n## Tips to improve the score\n\n- Use augmentations (checkout [discussions to what all worked](https://www.kaggle.com/c/flower-classification-with-tpus/discussion)\n- [Techniques to improve scores](https://www.kaggle.com/romanweilguny/tpu-flowers-first-love)\n- Check the best score notebooks in Flower classification comp(there are SOTA models out there)\n- Use Big Transfer architecture: [code](https://github.com/google-research/big_transfer)",
    "1624042": "**Great!! **thanks for this awesome intro!!!!",
    "897334": "Great!"
  }
}