{
  "id": 107290,
  "title": "Importing older versions of dataset to kernels",
  "url": "/competitions/aptos2019-blindness-detection/discussion/107290",
  "author_name": "",
  "post_date": "2019-09-03T14:53:22.852128600Z",
  "votes": 5,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Currently we can only import latest versions of datasets created using kernel outputs. So in order to ensemble previous models it becomes a cumbersome task to download the weights and upload again. If there exists an option to import previous versions of datasets, it will be awesome.    Is there any way to do this that I am unaware of?</p>",
  "messages": [
    {
      "id": "616879",
      "postDate": "09/03/2019 14:53:22",
      "content": "<p>Currently we can only import latest versions of datasets created using kernel outputs. So in order to ensemble previous models it becomes a cumbersome task to download the weights and upload again. If there exists an option to import previous versions of datasets, it will be awesome.    Is there any way to do this that I am unaware of?</p>",
      "rawMarkdown": "Currently we can only import latest versions of datasets created using kernel outputs. So in order to ensemble previous models it becomes a cumbersome task to download the weights and upload again. If there exists an option to import previous versions of datasets, it will be awesome.    Is there any way to do this that I am unaware of?",
      "votes": null
    },
    {
      "id": "617521",
      "postDate": "09/04/2019 08:00:25",
      "content": "<p>I was wondering the same. At the moment, we are saving the best models in a specific dataset and it's quite a boring task 😁.\nMaybe this could be also posted as a product feedback <a href=\"https://www.kaggle.com/product-feedback\">here</a>.</p>",
      "rawMarkdown": "I was wondering the same. At the moment, we are saving the best models in a specific dataset and it's quite a boring task 😁.\nMaybe this could be also posted as a product feedback [here](https://www.kaggle.com/product-feedback).",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 617521,
      "author_name": "raimonds1993",
      "author_url": "",
      "post_date": "09/04/2019 08:00:25",
      "content": "<p>I was wondering the same. At the moment, we are saving the best models in a specific dataset and it's quite a boring task 😁.\nMaybe this could be also posted as a product feedback <a href=\"https://www.kaggle.com/product-feedback\">here</a>.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "616879": "Currently we can only import latest versions of datasets created using kernel outputs. So in order to ensemble previous models it becomes a cumbersome task to download the weights and upload again. If there exists an option to import previous versions of datasets, it will be awesome.    Is there any way to do this that I am unaware of?",
    "617521": "I was wondering the same. At the moment, we are saving the best models in a specific dataset and it's quite a boring task 😁.\nMaybe this could be also posted as a product feedback [here](https://www.kaggle.com/product-feedback)."
  },
  "source": "meta"
}