{
  "id": 114795,
  "title": "Evaluation Metric, Local CV ?",
  "url": "/competitions/pku-autonomous-driving/discussion/114795",
  "author_name": "",
  "post_date": "2019-10-29T11:05:18.207657Z",
  "votes": 2,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hi All , recently joined this competition and finding it quite difficult .  Did anyone implement the metric to check CV ? Will someone be kind enough to explain the mAP ?</p>",
  "messages": [
    {
      "id": "660583",
      "postDate": "10/29/2019 11:05:18",
      "content": "<p>Hi All , recently joined this competition and finding it quite difficult .  Did anyone implement the metric to check CV ? Will someone be kind enough to explain the mAP ?</p>",
      "rawMarkdown": "Hi All , recently joined this competition and finding it quite difficult .  Did anyone implement the metric to check CV ? Will someone be kind enough to explain the mAP ?",
      "votes": null
    },
    {
      "id": "674404",
      "postDate": "11/16/2019 12:54:29",
      "content": "<p>Hi Nirjhar Roy,</p>\n\n<p>Short answer is that mAP is average of average precision, and average precision is area under recall-precision curve.</p>\n\n<p>You can find more general mAP information <a href=\"https://medium.com/&lt;a href=\">@jonathan</a>_hui/map-mean-average-precision-for-object-detection-45c121a31173\"&gt;here.</p>\n\n<p>I think no one knows metrics of this competition exactly, but one of possible implementation can be found <a href=\"https://www.kaggle.com/its7171/metrics-evaluation-script\">here</a>. </p>",
      "rawMarkdown": "Hi Nirjhar Roy,\n\nShort answer is that mAP is average of average precision, and average precision is area under recall-precision curve.\n\nYou can find more general mAP information [here](https://medium.com/@jonathan_hui/map-mean-average-precision-for-object-detection-45c121a31173).\n\nI think no one knows metrics of this competition exactly, but one of possible implementation can be found [here](https://www.kaggle.com/its7171/metrics-evaluation-script).",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 674404,
      "author_name": "its7171",
      "author_url": "",
      "post_date": "11/16/2019 12:54:29",
      "content": "<p>Hi Nirjhar Roy,</p>\n\n<p>Short answer is that mAP is average of average precision, and average precision is area under recall-precision curve.</p>\n\n<p>You can find more general mAP information <a href=\"https://medium.com/&lt;a href=\">@jonathan</a>_hui/map-mean-average-precision-for-object-detection-45c121a31173\"&gt;here.</p>\n\n<p>I think no one knows metrics of this competition exactly, but one of possible implementation can be found <a href=\"https://www.kaggle.com/its7171/metrics-evaluation-script\">here</a>. </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "660583": "Hi All , recently joined this competition and finding it quite difficult .  Did anyone implement the metric to check CV ? Will someone be kind enough to explain the mAP ?",
    "674404": "Hi Nirjhar Roy,\n\nShort answer is that mAP is average of average precision, and average precision is area under recall-precision curve.\n\nYou can find more general mAP information [here](https://medium.com/@jonathan_hui/map-mean-average-precision-for-object-detection-45c121a31173).\n\nI think no one knows metrics of this competition exactly, but one of possible implementation can be found [here](https://www.kaggle.com/its7171/metrics-evaluation-script)."
  },
  "source": "meta"
}