{
  "id": 234089,
  "title": "How to make a successful submission?",
  "url": "/competitions/plant-pathology-2021-fgvc8/discussion/234089",
  "author_name": "",
  "post_date": "2021-04-22T15:15:39.804127800Z",
  "votes": 1,
  "comment_count": 4,
  "views": 0,
  "content": "<p>the submission note say that: the systerm will run our model to get the final score.<br>\nso dose it mean that we can only submit pretrained model (trained model locally)？<br>\n(appreciating for your kind answer)</p>",
  "messages": [
    {
      "id": "1281019",
      "postDate": "04/22/2021 15:15:39",
      "content": "<p>the submission note say that: the systerm will run our model to get the final score.<br>\nso dose it mean that we can only submit pretrained model (trained model locally)？<br>\n(appreciating for your kind answer)</p>",
      "rawMarkdown": "the submission note say that: the systerm will run our model to get the final score.\n\nso dose it mean that we can only submit pretrained model (trained model locally)？\n\n(appreciating for your kind answer)",
      "votes": null
    },
    {
      "id": "1281065",
      "postDate": "04/22/2021 15:54:16",
      "content": "<p>You need to split your notebook to two notebooks: training and inference. You can use internet in the first one - use it to train model and save your weights. Create a dataset with that weights, and then use it in the second notebook with disabled Internet which you can submit. If you're using Tensorflow, use <code>weights=None</code> paramater to disable weights download, and use <code>model.load_weights(...)</code> to load weights to the model. </p>",
      "rawMarkdown": "You need to split your notebook to two notebooks: training and inference. You can use internet in the first one - use it to train model and save your weights. Create a dataset with that weights, and then use it in the second notebook with disabled Internet which you can submit. If you're using Tensorflow, use `weights=None` paramater to disable weights download, and use `model.load_weights(...)` to load weights to the model.",
      "votes": null
    },
    {
      "id": "1281315",
      "postDate": "04/22/2021 19:25:29",
      "content": "<p>You can create a seperate notebook and disable the internet in that notebook. Now you can load your model from another notebook or from your local machine in this notebook. After making predictions you can create submission csv file.</p>",
      "rawMarkdown": "You can create a seperate notebook and disable the internet in that notebook. Now you can load your model from another notebook or from your local machine in this notebook. After making predictions you can create submission csv file.",
      "votes": null
    },
    {
      "id": "1281747",
      "postDate": "04/23/2021 09:10:58",
      "content": "<p>yes, got it, thank you for your reply</p>",
      "rawMarkdown": "yes, got it, thank you for your reply",
      "votes": null
    },
    {
      "id": "1281748",
      "postDate": "04/23/2021 09:11:01",
      "content": "<p>got it , thanks for your reply !</p>",
      "rawMarkdown": "got it , thanks for your reply !",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1281065,
      "author_name": "atamazian",
      "author_url": "",
      "post_date": "04/22/2021 15:54:16",
      "content": "<p>You need to split your notebook to two notebooks: training and inference. You can use internet in the first one - use it to train model and save your weights. Create a dataset with that weights, and then use it in the second notebook with disabled Internet which you can submit. If you're using Tensorflow, use <code>weights=None</code> paramater to disable weights download, and use <code>model.load_weights(...)</code> to load weights to the model. </p>",
      "votes": null,
      "replies": [
        {
          "id": 1281747,
          "author_name": "gjzhongdf163com",
          "author_url": "",
          "post_date": "04/23/2021 09:10:58",
          "content": "<p>yes, got it, thank you for your reply</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1281315,
      "author_name": "rajatsanjaypatel",
      "author_url": "",
      "post_date": "04/22/2021 19:25:29",
      "content": "<p>You can create a seperate notebook and disable the internet in that notebook. Now you can load your model from another notebook or from your local machine in this notebook. After making predictions you can create submission csv file.</p>",
      "votes": null,
      "replies": [
        {
          "id": 1281748,
          "author_name": "gjzhongdf163com",
          "author_url": "",
          "post_date": "04/23/2021 09:11:01",
          "content": "<p>got it , thanks for your reply !</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1281019": "the submission note say that: the systerm will run our model to get the final score.\n\nso dose it mean that we can only submit pretrained model (trained model locally)？\n\n(appreciating for your kind answer)",
    "1281065": "You need to split your notebook to two notebooks: training and inference. You can use internet in the first one - use it to train model and save your weights. Create a dataset with that weights, and then use it in the second notebook with disabled Internet which you can submit. If you're using Tensorflow, use `weights=None` paramater to disable weights download, and use `model.load_weights(...)` to load weights to the model.",
    "1281315": "You can create a seperate notebook and disable the internet in that notebook. Now you can load your model from another notebook or from your local machine in this notebook. After making predictions you can create submission csv file.",
    "1281747": "yes, got it, thank you for your reply",
    "1281748": "got it , thanks for your reply !"
  },
  "source": "meta"
}