{
  "id": 302135,
  "title": "how can i infer the testimgs,i dont know where they are!!!",
  "url": "/competitions/tensorflow-great-barrier-reef/discussion/302135",
  "author_name": "",
  "post_date": "2022-01-21T02:13:53.611140400Z",
  "votes": null,
  "comment_count": 2,
  "views": 0,
  "content": "<p>so here  i have 2 problems:<br>\n1,I can train online by using kaggle GPU,but how can i upload with my offline model?<br>\n2,when i got my model after several hours training,how can i infer the testimgs,i only get a test.csv,how can i parse the path of the 3 test images?</p>",
  "messages": [
    {
      "id": "1658401",
      "postDate": "01/21/2022 02:13:53",
      "content": "<p>so here  i have 2 problems:<br>\n1,I can train online by using kaggle GPU,but how can i upload with my offline model?<br>\n2,when i got my model after several hours training,how can i infer the testimgs,i only get a test.csv,how can i parse the path of the 3 test images?</p>",
      "rawMarkdown": "so here  i have 2 problems:\n1,I can train online by using kaggle GPU,but how can i upload with my offline model?\n2,when i got my model after several hours training,how can i infer the testimgs,i only get a test.csv,how can i parse the path of the 3 test images?",
      "votes": null
    },
    {
      "id": "1658517",
      "postDate": "01/21/2022 05:08:04",
      "content": "<ol>\n<li>Upload your saved model checkpoint as a dataset and import the dataset into your notebook</li>\n<li>Images are provided by the competition API to stop competitors from using future images in their predicitions, see: <a href=\"https://www.kaggle.com/c/tensorflow-great-barrier-reef/overview/evaluation\" target=\"_blank\">https://www.kaggle.com/c/tensorflow-great-barrier-reef/overview/evaluation</a> for how the submission should be formatted.</li>\n</ol>",
      "rawMarkdown": "1. Upload your saved model checkpoint as a dataset and import the dataset into your notebook\n2. Images are provided by the competition API to stop competitors from using future images in their predicitions, see: https://www.kaggle.com/c/tensorflow-great-barrier-reef/overview/evaluation for how the submission should be formatted.",
      "votes": null
    },
    {
      "id": "1658519",
      "postDate": "01/21/2022 05:12:54",
      "content": "<p>Thx soooooo much!!!!😄</p>",
      "rawMarkdown": "Thx soooooo much!!!!😄",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1658517,
      "author_name": "maxvandijck",
      "author_url": "",
      "post_date": "01/21/2022 05:08:04",
      "content": "<ol>\n<li>Upload your saved model checkpoint as a dataset and import the dataset into your notebook</li>\n<li>Images are provided by the competition API to stop competitors from using future images in their predicitions, see: <a href=\"https://www.kaggle.com/c/tensorflow-great-barrier-reef/overview/evaluation\" target=\"_blank\">https://www.kaggle.com/c/tensorflow-great-barrier-reef/overview/evaluation</a> for how the submission should be formatted.</li>\n</ol>",
      "votes": null,
      "replies": [
        {
          "id": 1658519,
          "author_name": "jamesbondzhou2022",
          "author_url": "",
          "post_date": "01/21/2022 05:12:54",
          "content": "<p>Thx soooooo much!!!!😄</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1658401": "so here  i have 2 problems:\n1,I can train online by using kaggle GPU,but how can i upload with my offline model?\n2,when i got my model after several hours training,how can i infer the testimgs,i only get a test.csv,how can i parse the path of the 3 test images?",
    "1658517": "1. Upload your saved model checkpoint as a dataset and import the dataset into your notebook\n2. Images are provided by the competition API to stop competitors from using future images in their predicitions, see: https://www.kaggle.com/c/tensorflow-great-barrier-reef/overview/evaluation for how the submission should be formatted.",
    "1658519": "Thx soooooo much!!!!😄"
  },
  "source": "meta"
}