{
  "id": 149169,
  "title": "Metric & Model Validation",
  "url": "/competitions/global-wheat-detection/discussion/149169",
  "author_name": "",
  "post_date": "2020-05-07T06:24:42.220165600Z",
  "votes": 1,
  "comment_count": 1,
  "views": 0,
  "content": "<p><strong>## IoU (Intersection over Union)</strong>\nTo decide whether a prediction is correct w.r.t to an object or not, IoU or Jaccard Index is used. It is defines as the intersection b/w the predicted bbox and actual bbox divided by their union. A prediction is considered to be True Positive if IoU &gt; threshold, and False Positive if IoU &lt; threshold.</p>\n\n<p><strong>Precision and Recall</strong>\nTo understand mAP, let’s go through precision and recall first. Recall is the True Positive Rate i.e. Of all the actual positives, how many are True positives predictions. Precision is the Positive prediction value i.e. Of all the positive predictions, how many are True positives predictions. Read more in evaluation metrics for classification.</p>\n\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F378285%2F9858fe7ee794e13208aa26ab07652d02%2Fiou.png?generation=1588832573584305&amp;alt=media\" alt=\"\"></p>",
  "messages": [
    {
      "id": "836671",
      "postDate": "05/07/2020 06:24:42",
      "content": "<p><strong>## IoU (Intersection over Union)</strong>\nTo decide whether a prediction is correct w.r.t to an object or not, IoU or Jaccard Index is used. It is defines as the intersection b/w the predicted bbox and actual bbox divided by their union. A prediction is considered to be True Positive if IoU &gt; threshold, and False Positive if IoU &lt; threshold.</p>\n\n<p><strong>Precision and Recall</strong>\nTo understand mAP, let’s go through precision and recall first. Recall is the True Positive Rate i.e. Of all the actual positives, how many are True positives predictions. Precision is the Positive prediction value i.e. Of all the positive predictions, how many are True positives predictions. Read more in evaluation metrics for classification.</p>\n\n<p><img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F378285%2F9858fe7ee794e13208aa26ab07652d02%2Fiou.png?generation=1588832573584305&amp;alt=media\" alt=\"\"></p>",
      "rawMarkdown": "**## IoU (Intersection over Union)**\nTo decide whether a prediction is correct w.r.t to an object or not, IoU or Jaccard Index is used. It is defines as the intersection b/w the predicted bbox and actual bbox divided by their union. A prediction is considered to be True Positive if IoU &gt; threshold, and False Positive if IoU &lt; threshold.\n\n\n**Precision and Recall**\nTo understand mAP, let’s go through precision and recall first. Recall is the True Positive Rate i.e. Of all the actual positives, how many are True positives predictions. Precision is the Positive prediction value i.e. Of all the positive predictions, how many are True positives predictions. Read more in evaluation metrics for classification.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F378285%2F9858fe7ee794e13208aa26ab07652d02%2Fiou.png?generation=1588832573584305&amp;alt=media)",
      "votes": null
    },
    {
      "id": "836840",
      "postDate": "05/07/2020 09:44:38",
      "content": "<p>Nice pictorial description, thanks for sharing.</p>",
      "rawMarkdown": "Nice pictorial description, thanks for sharing.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 836840,
      "author_name": "darshangandhi",
      "author_url": "",
      "post_date": "05/07/2020 09:44:38",
      "content": "<p>Nice pictorial description, thanks for sharing.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "836671": "**## IoU (Intersection over Union)**\nTo decide whether a prediction is correct w.r.t to an object or not, IoU or Jaccard Index is used. It is defines as the intersection b/w the predicted bbox and actual bbox divided by their union. A prediction is considered to be True Positive if IoU &gt; threshold, and False Positive if IoU &lt; threshold.\n\n\n**Precision and Recall**\nTo understand mAP, let’s go through precision and recall first. Recall is the True Positive Rate i.e. Of all the actual positives, how many are True positives predictions. Precision is the Positive prediction value i.e. Of all the positive predictions, how many are True positives predictions. Read more in evaluation metrics for classification.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F378285%2F9858fe7ee794e13208aa26ab07652d02%2Fiou.png?generation=1588832573584305&amp;alt=media)",
    "836840": "Nice pictorial description, thanks for sharing."
  },
  "source": "meta"
}