{
  "id": 33840,
  "title": "Fully convolutional prove of concept in Keras",
  "url": "/competitions/noaa-fisheries-steller-sea-lion-population-count/discussion/33840",
  "author_name": "",
  "post_date": "2017-05-30T21:42:24.884908900Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Here is sliding window vs fully convolutional approach implemented in Keras, if someone would like to use sea lions crops.\nIt's just an example, so no lions included, just black and white images, maybe I will make example on real data soon.\nAny ideas on this topic appreciated.</p>\n\n<p>Here is the code:\n<a href=\"https://github.com/mrgloom/Fully-Convolutional-Example/blob/master/fully_convolutional_example.ipynb\">https://github.com/mrgloom/Fully-Convolutional-Example/blob/master/fully_convolutional_example.ipynb</a></p>",
  "messages": [
    {
      "id": "187272",
      "postDate": "05/30/2017 21:42:24",
      "content": "<p>Here is sliding window vs fully convolutional approach implemented in Keras, if someone would like to use sea lions crops.\nIt's just an example, so no lions included, just black and white images, maybe I will make example on real data soon.\nAny ideas on this topic appreciated.</p>\n\n<p>Here is the code:\n<a href=\"https://github.com/mrgloom/Fully-Convolutional-Example/blob/master/fully_convolutional_example.ipynb\">https://github.com/mrgloom/Fully-Convolutional-Example/blob/master/fully_convolutional_example.ipynb</a></p>",
      "rawMarkdown": "Here is sliding window vs fully convolutional approach implemented in Keras, if someone would like to use sea lions crops.\nIt's just an example, so no lions included, just black and white images, maybe I will make example on real data soon.\nAny ideas on this topic appreciated.\n\nHere is the code:\nhttps://github.com/mrgloom/Fully-Convolutional-Example/blob/master/fully_convolutional_example.ipynb",
      "votes": null
    },
    {
      "id": "187322",
      "postDate": "05/31/2017 01:04:38",
      "content": "<p>very nice idea~I think this will achieve good result~~~WoW~</p>",
      "rawMarkdown": "very nice idea~I think this will achieve good result~~~WoW~",
      "votes": null
    },
    {
      "id": "190764",
      "postDate": "06/08/2017 12:29:10",
      "content": "<p>Thanks for sharing!</p>",
      "rawMarkdown": "Thanks for sharing!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 187322,
      "author_name": "pandav5",
      "author_url": "",
      "post_date": "05/31/2017 01:04:38",
      "content": "<p>very nice idea~I think this will achieve good result~~~WoW~</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 190764,
      "author_name": "sanderdalm",
      "author_url": "",
      "post_date": "06/08/2017 12:29:10",
      "content": "<p>Thanks for sharing!</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "187272": "Here is sliding window vs fully convolutional approach implemented in Keras, if someone would like to use sea lions crops.\nIt's just an example, so no lions included, just black and white images, maybe I will make example on real data soon.\nAny ideas on this topic appreciated.\n\nHere is the code:\nhttps://github.com/mrgloom/Fully-Convolutional-Example/blob/master/fully_convolutional_example.ipynb",
    "187322": "very nice idea~I think this will achieve good result~~~WoW~",
    "190764": "Thanks for sharing!"
  },
  "source": "meta"
}