{
  "id": 30897,
  "title": "Update to kernels data subset",
  "url": "/competitions/noaa-fisheries-steller-sea-lion-population-count/discussion/30897",
  "author_name": "DataCanary",
  "post_date": "2017-03-30T21:13:01.899000",
  "votes": 1,
  "comment_count": 0,
  "views": 0,
  "content": "<p>I've added the contents of TrainSmall2.7z to the Train and TrainDotted folders in kernels (see <a href=\"https://www.kaggle.com/c/noaa-fisheries-steller-sea-lion-population-count/discussion/30895\">explanation</a>). The first batch of images are still in there, for compatibility with older kernels, but two of them happen to be affected by the mismatch between Train and TrainDotted.</p>\n\n<p>I also added the first ten images from the Test folder, in case you want to demo some techniques for a full model pipeline.</p>",
  "messages": [
    {
      "id": 171635,
      "postDate": "2017-03-30T21:13:01.900Z",
      "content": "<p>I've added the contents of TrainSmall2.7z to the Train and TrainDotted folders in kernels (see <a href=\"https://www.kaggle.com/c/noaa-fisheries-steller-sea-lion-population-count/discussion/30895\">explanation</a>). The first batch of images are still in there, for compatibility with older kernels, but two of them happen to be affected by the mismatch between Train and TrainDotted.</p>\n\n<p>I also added the first ten images from the Test folder, in case you want to demo some techniques for a full model pipeline.</p>",
      "rawMarkdown": "I've added the contents of TrainSmall2.7z to the Train and TrainDotted folders in kernels (see [explanation](https://www.kaggle.com/c/noaa-fisheries-steller-sea-lion-population-count/discussion/30895)). The first batch of images are still in there, for compatibility with older kernels, but two of them happen to be affected by the mismatch between Train and TrainDotted.\n\nI also added the first ten images from the Test folder, in case you want to demo some techniques for a full model pipeline.",
      "votes": 1
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "171635": "I've added the contents of TrainSmall2.7z to the Train and TrainDotted folders in kernels (see [explanation](https://www.kaggle.com/c/noaa-fisheries-steller-sea-lion-population-count/discussion/30895)). The first batch of images are still in there, for compatibility with older kernels, but two of them happen to be affected by the mismatch between Train and TrainDotted.\n\nI also added the first ten images from the Test folder, in case you want to demo some techniques for a full model pipeline."
  }
}