{
  "id": 294989,
  "title": "Question on Competition API",
  "url": "/competitions/tensorflow-great-barrier-reef/discussion/294989",
  "author_name": "",
  "post_date": "2021-12-13T20:45:44.999792Z",
  "votes": 2,
  "comment_count": 1,
  "views": 0,
  "content": "<p>i saw that the public notebooks weren't using batch inferencing (so i did the same way).<br>\nWhen i was looking into the API. i found something doubtful here</p>\n<pre><code>import sys\nsys.path.append('../input/tensorflow-great-barrier-reef')\nimport greatbarrierreef\nenv = greatbarrierreef.make_env()\niter_test = env.iter_test()\n\nfor idx, (img, pred_df) in enumerate(iter_test):\n    break\nenv.features.shape\n</code></pre>\n<p>the shape of the env.features were <code>3,720,1280,3</code><br>\nit outputs all pixel arrays. Will it happen in same way on hidden test set.</p>",
  "messages": [
    {
      "id": "1617098",
      "postDate": "12/13/2021 20:45:45",
      "content": "<p>i saw that the public notebooks weren't using batch inferencing (so i did the same way).<br>\nWhen i was looking into the API. i found something doubtful here</p>\n<pre><code>import sys\nsys.path.append('../input/tensorflow-great-barrier-reef')\nimport greatbarrierreef\nenv = greatbarrierreef.make_env()\niter_test = env.iter_test()\n\nfor idx, (img, pred_df) in enumerate(iter_test):\n    break\nenv.features.shape\n</code></pre>\n<p>the shape of the env.features were <code>3,720,1280,3</code><br>\nit outputs all pixel arrays. Will it happen in same way on hidden test set.</p>",
      "rawMarkdown": "i saw that the public notebooks weren't using batch inferencing (so i did the same way).\nWhen i was looking into the API. i found something doubtful here\n```\nimport sys\nsys.path.append('../input/tensorflow-great-barrier-reef')\nimport greatbarrierreef\nenv = greatbarrierreef.make_env()\niter_test = env.iter_test()\n\nfor idx, (img, pred_df) in enumerate(iter_test):\n    break\nenv.features.shape\n```\nthe shape of the env.features were `3,720,1280,3`\nit outputs all pixel arrays. Will it happen in same way on hidden test set.",
      "votes": null
    },
    {
      "id": "1617412",
      "postDate": "12/14/2021 04:19:36",
      "content": "<p>I think according to this discussion, for hidden test data we can't access the future frames, <a href=\"https://www.kaggle.com/c/tensorflow-great-barrier-reef/discussion/291520\" target=\"_blank\">link</a></p>",
      "rawMarkdown": "I think according to this discussion, for hidden test data we can't access the future frames, [link](https://www.kaggle.com/c/tensorflow-great-barrier-reef/discussion/291520)",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1617412,
      "author_name": "awsaf49",
      "author_url": "",
      "post_date": "12/14/2021 04:19:36",
      "content": "<p>I think according to this discussion, for hidden test data we can't access the future frames, <a href=\"https://www.kaggle.com/c/tensorflow-great-barrier-reef/discussion/291520\" target=\"_blank\">link</a></p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1617098": "i saw that the public notebooks weren't using batch inferencing (so i did the same way).\nWhen i was looking into the API. i found something doubtful here\n```\nimport sys\nsys.path.append('../input/tensorflow-great-barrier-reef')\nimport greatbarrierreef\nenv = greatbarrierreef.make_env()\niter_test = env.iter_test()\n\nfor idx, (img, pred_df) in enumerate(iter_test):\n    break\nenv.features.shape\n```\nthe shape of the env.features were `3,720,1280,3`\nit outputs all pixel arrays. Will it happen in same way on hidden test set.",
    "1617412": "I think according to this discussion, for hidden test data we can't access the future frames, [link](https://www.kaggle.com/c/tensorflow-great-barrier-reef/discussion/291520)"
  },
  "source": "meta"
}