{
  "id": 54978,
  "title": "transforms the dataset into tfrecords that can be feed into deeplab model",
  "url": "/competitions/carvana-image-masking-challenge/discussion/54978",
  "author_name": "wine lover",
  "post_date": "2018-04-20T13:05:14.990000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hi, google just released the latest version of deeplab,   <a href=\"https://github.com/tensorflow/models/tree/master/research/deeplab\">https://github.com/tensorflow/models/tree/master/research/deeplab</a></p>\n\n<p>It seems that the code can only support data format of voc or Cityscape. How to convert the data set of Carvana challenge into the tfrecords format that can be feedinto the deeplab V3 model? Any suggestions are welcomed.</p>",
  "messages": [
    {
      "id": 317012,
      "postDate": "2018-04-20T13:05:14.990Z",
      "content": "<p>Hi, google just released the latest version of deeplab,   <a href=\"https://github.com/tensorflow/models/tree/master/research/deeplab\">https://github.com/tensorflow/models/tree/master/research/deeplab</a></p>\n\n<p>It seems that the code can only support data format of voc or Cityscape. How to convert the data set of Carvana challenge into the tfrecords format that can be feedinto the deeplab V3 model? Any suggestions are welcomed.</p>",
      "rawMarkdown": "Hi, google just released the latest version of deeplab,   https://github.com/tensorflow/models/tree/master/research/deeplab\n\nIt seems that the code can only support data format of voc or Cityscape. How to convert the data set of Carvana challenge into the tfrecords format that can be feedinto the deeplab V3 model? Any suggestions are welcomed."
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "317012": "Hi, google just released the latest version of deeplab,   https://github.com/tensorflow/models/tree/master/research/deeplab\n\nIt seems that the code can only support data format of voc or Cityscape. How to convert the data set of Carvana challenge into the tfrecords format that can be feedinto the deeplab V3 model? Any suggestions are welcomed."
  }
}