{
  "id": 243689,
  "title": "Installing detectron2 offline",
  "url": "/competitions/siim-covid19-detection/discussion/243689",
  "author_name": "",
  "post_date": "2021-06-03T15:27:05.593276900Z",
  "votes": 9,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I have not seen any notebooks using detectron2 offline. This is required when doing predictions in this competition. I collected some python code in a dataset: </p>\n<p>\"<a href=\"https://www.kaggle.com/helgith/detectron2\" target=\"_blank\">Detectron2</a>\" </p>\n<p>to install offline. The installation can be performed through:</p>\n<p>`!pip install /kaggle/input/detectron2/omegaconf-2.0.6-py3-none-any.whl  </p>\n<p>!pip install /kaggle/input/detectron2/iopath-0.1.8-py3-none-any.whl  </p>\n<p>!pip install /kaggle/input/detectron2/fvcore-0.1.3.post20210317/fvcore-0.1.3.post20210317/  </p>\n<p>!pip install /kaggle/input/detectron2/pycocotools-2.0.2/dist/pycocotools-2.0.2.tar  </p>\n<p>!pip install /kaggle/input/detectron2/detectron2-0.4cu110-cp37-cp37m-linux_x86_64.whl`  </p>\n<p>after attaching the dataset. I have created a prediction notebook based on this. (This also requires offline installation of gdcm as a prerequisite).</p>",
  "messages": [
    {
      "id": "1334544",
      "postDate": "06/03/2021 15:27:05",
      "content": "<p>I have not seen any notebooks using detectron2 offline. This is required when doing predictions in this competition. I collected some python code in a dataset: </p>\n<p>\"<a href=\"https://www.kaggle.com/helgith/detectron2\" target=\"_blank\">Detectron2</a>\" </p>\n<p>to install offline. The installation can be performed through:</p>\n<p>`!pip install /kaggle/input/detectron2/omegaconf-2.0.6-py3-none-any.whl  </p>\n<p>!pip install /kaggle/input/detectron2/iopath-0.1.8-py3-none-any.whl  </p>\n<p>!pip install /kaggle/input/detectron2/fvcore-0.1.3.post20210317/fvcore-0.1.3.post20210317/  </p>\n<p>!pip install /kaggle/input/detectron2/pycocotools-2.0.2/dist/pycocotools-2.0.2.tar  </p>\n<p>!pip install /kaggle/input/detectron2/detectron2-0.4cu110-cp37-cp37m-linux_x86_64.whl`  </p>\n<p>after attaching the dataset. I have created a prediction notebook based on this. (This also requires offline installation of gdcm as a prerequisite).</p>",
      "rawMarkdown": "I have not seen any notebooks using detectron2 offline. This is required when doing predictions in this competition. I collected some python code in a dataset: \n\n\"[Detectron2](https://www.kaggle.com/helgith/detectron2)\" \n\nto install offline. The installation can be performed through:\n\n`!pip install /kaggle/input/detectron2/omegaconf-2.0.6-py3-none-any.whl  \n\n!pip install /kaggle/input/detectron2/iopath-0.1.8-py3-none-any.whl  \n\n!pip install /kaggle/input/detectron2/fvcore-0.1.3.post20210317/fvcore-0.1.3.post20210317/  \n\n!pip install /kaggle/input/detectron2/pycocotools-2.0.2/dist/pycocotools-2.0.2.tar  \n\n!pip install /kaggle/input/detectron2/detectron2-0.4cu110-cp37-cp37m-linux_x86_64.whl`  \n\nafter attaching the dataset. I have created a prediction notebook based on this. (This also requires offline installation of gdcm as a prerequisite).",
      "votes": null
    },
    {
      "id": "1335278",
      "postDate": "06/04/2021 06:04:55",
      "content": "<p>Thanks, I also couldn't find a way to use detectron offline. Can you give a link to your notebook on how you using the detectron for the predictions?<br>\nThanks <br>\nBtw which detectron version are you using</p>",
      "rawMarkdown": "Thanks, I also couldn't find a way to use detectron offline. Can you give a link to your notebook on how you using the detectron for the predictions?\nThanks \nBtw which detectron version are you using",
      "votes": null
    },
    {
      "id": "1337259",
      "postDate": "06/05/2021 14:08:30",
      "content": "<p>oh.thank you. i tyied to find it. i 'll use it.</p>",
      "rawMarkdown": "oh.thank you. i tyied to find it. i 'll use it.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1335278,
      "author_name": "mrinath",
      "author_url": "",
      "post_date": "06/04/2021 06:04:55",
      "content": "<p>Thanks, I also couldn't find a way to use detectron offline. Can you give a link to your notebook on how you using the detectron for the predictions?<br>\nThanks <br>\nBtw which detectron version are you using</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1337259,
      "author_name": "tensorchoko",
      "author_url": "",
      "post_date": "06/05/2021 14:08:30",
      "content": "<p>oh.thank you. i tyied to find it. i 'll use it.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1334544": "I have not seen any notebooks using detectron2 offline. This is required when doing predictions in this competition. I collected some python code in a dataset: \n\n\"[Detectron2](https://www.kaggle.com/helgith/detectron2)\" \n\nto install offline. The installation can be performed through:\n\n`!pip install /kaggle/input/detectron2/omegaconf-2.0.6-py3-none-any.whl  \n\n!pip install /kaggle/input/detectron2/iopath-0.1.8-py3-none-any.whl  \n\n!pip install /kaggle/input/detectron2/fvcore-0.1.3.post20210317/fvcore-0.1.3.post20210317/  \n\n!pip install /kaggle/input/detectron2/pycocotools-2.0.2/dist/pycocotools-2.0.2.tar  \n\n!pip install /kaggle/input/detectron2/detectron2-0.4cu110-cp37-cp37m-linux_x86_64.whl`  \n\nafter attaching the dataset. I have created a prediction notebook based on this. (This also requires offline installation of gdcm as a prerequisite).",
    "1335278": "Thanks, I also couldn't find a way to use detectron offline. Can you give a link to your notebook on how you using the detectron for the predictions?\nThanks \nBtw which detectron version are you using",
    "1337259": "oh.thank you. i tyied to find it. i 'll use it."
  },
  "source": "meta"
}