{
  "id": 53864,
  "title": "How could we segment some big nuclei in testing set? ",
  "url": "/competitions/data-science-bowl-2018/discussion/53864",
  "author_name": "john1231983",
  "post_date": "2018-04-06T04:28:49.583000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hello all, I am using Heng code and it achieved a good result. However, I got some unexpected result in some images as the attached file. I guess that these images have some big nucleus that unnormal (likes noise...) or unseen in the training set. Any suggestion to deal with these case? For now, I am using <code>self.rpn_base_sizes  = [ 8, 16, 32, 64, ] #diameter</code> . Thanks so much</p>\n\n<p>Image id1 <code>1879f4f4f05e2bada0ffeb46c128b8df7a79b14c84f38c3e216a69653495153b</code>\n<img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/309863/8947/1.png\" alt=\"enter image description here\">\nImage id2 <code>505bc0a3928d8aef5ce441c5a611fdd32e1e8eccdc15cc3a52b88030acb50f81</code>\n<img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/309863/8948/2.png\" alt=\"enter image description here\"></p>",
  "messages": [
    {
      "id": 309863,
      "postDate": "2018-04-06T04:28:49.583Z",
      "content": "<p>Hello all, I am using Heng code and it achieved a good result. However, I got some unexpected result in some images as the attached file. I guess that these images have some big nucleus that unnormal (likes noise...) or unseen in the training set. Any suggestion to deal with these case? For now, I am using <code>self.rpn_base_sizes  = [ 8, 16, 32, 64, ] #diameter</code> . Thanks so much</p>\n\n<p>Image id1 <code>1879f4f4f05e2bada0ffeb46c128b8df7a79b14c84f38c3e216a69653495153b</code>\n<img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/309863/8947/1.png\" alt=\"enter image description here\">\nImage id2 <code>505bc0a3928d8aef5ce441c5a611fdd32e1e8eccdc15cc3a52b88030acb50f81</code>\n<img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/309863/8948/2.png\" alt=\"enter image description here\"></p>",
      "rawMarkdown": "Hello all, I am using Heng code and it achieved a good result. However, I got some unexpected result in some images as the attached file. I guess that these images have some big nucleus that unnormal (likes noise...) or unseen in the training set. Any suggestion to deal with these case? For now, I am using `self.rpn_base_sizes  = [ 8, 16, 32, 64, ] #diameter` . Thanks so much\n\n\nImage id1 `1879f4f4f05e2bada0ffeb46c128b8df7a79b14c84f38c3e216a69653495153b`\n![enter image description here][1]\nImage id2 `505bc0a3928d8aef5ce441c5a611fdd32e1e8eccdc15cc3a52b88030acb50f81`\n![enter image description here][2]\n\n\n  [1]: https://kaggle2.blob.core.windows.net/forum-message-attachments/309863/8947/1.png\n  [2]: https://kaggle2.blob.core.windows.net/forum-message-attachments/309863/8948/2.png"
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "309863": "Hello all, I am using Heng code and it achieved a good result. However, I got some unexpected result in some images as the attached file. I guess that these images have some big nucleus that unnormal (likes noise...) or unseen in the training set. Any suggestion to deal with these case? For now, I am using `self.rpn_base_sizes  = [ 8, 16, 32, 64, ] #diameter` . Thanks so much\n\n\nImage id1 `1879f4f4f05e2bada0ffeb46c128b8df7a79b14c84f38c3e216a69653495153b`\n![enter image description here][1]\nImage id2 `505bc0a3928d8aef5ce441c5a611fdd32e1e8eccdc15cc3a52b88030acb50f81`\n![enter image description here][2]\n\n\n  [1]: https://kaggle2.blob.core.windows.net/forum-message-attachments/309863/8947/1.png\n  [2]: https://kaggle2.blob.core.windows.net/forum-message-attachments/309863/8948/2.png"
  }
}