{
  "id": 295885,
  "title": "why  I got   -1.00 for recall and precision?",
  "url": "/competitions/tensorflow-great-barrier-reef/discussion/295885",
  "author_name": "",
  "post_date": "2021-12-18T14:01:50.473704200Z",
  "votes": 2,
  "comment_count": 3,
  "views": 0,
  "content": "<p>I switched fold and retrained:</p>\n<p>Average forward time: 48.11 ms, Average NMS time: 2.17 ms, Average inference time: 50.28 ms<br>\n Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.471<br>\n Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.896<br>\n Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.445<br>\n Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.329<br>\n Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.507<br>\n Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000 ***<br>\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.204<br>\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.539<br>\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.558<br>\n Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.463<br>\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.585<br>\n Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000 ***</p>",
  "messages": [
    {
      "id": "1622233",
      "postDate": "12/18/2021 14:01:50",
      "content": "<p>I switched fold and retrained:</p>\n<p>Average forward time: 48.11 ms, Average NMS time: 2.17 ms, Average inference time: 50.28 ms<br>\n Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.471<br>\n Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.896<br>\n Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.445<br>\n Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.329<br>\n Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.507<br>\n Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000 ***<br>\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.204<br>\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.539<br>\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.558<br>\n Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.463<br>\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.585<br>\n Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000 ***</p>",
      "rawMarkdown": "I switched fold and retrained:\n\nAverage forward time: 48.11 ms, Average NMS time: 2.17 ms, Average inference time: 50.28 ms\n Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.471\n Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.896\n Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.445\n Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.329\n Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.507\n Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000 ***\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.204\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.539\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.558\n Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.463\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.585\n Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000 ***",
      "votes": null
    },
    {
      "id": "1622312",
      "postDate": "12/18/2021 15:16:24",
      "content": "<p>Because in your fold, there are no area= large bboxes.</p>",
      "rawMarkdown": "Because in your fold, there are no area= large bboxes.",
      "votes": null
    },
    {
      "id": "1622465",
      "postDate": "12/18/2021 19:05:09",
      "content": "<p>I can confirm …. there is no large boxes in your training dataset.</p>",
      "rawMarkdown": "I can confirm .... there is no large boxes in your training dataset.",
      "votes": null
    },
    {
      "id": "1623157",
      "postDate": "12/19/2021 14:55:40",
      "content": "<p>thanks for   both replies.  I didn't dip into metric in detail. just thought of  0 to 1. </p>",
      "rawMarkdown": "thanks for   both replies.  I didn't dip into metric in detail. just thought of  0 to 1.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1622312,
      "author_name": "zzy990106",
      "author_url": "",
      "post_date": "12/18/2021 15:16:24",
      "content": "<p>Because in your fold, there are no area= large bboxes.</p>",
      "votes": null,
      "replies": [
        {
          "id": 1622465,
          "author_name": "remekkinas",
          "author_url": "",
          "post_date": "12/18/2021 19:05:09",
          "content": "<p>I can confirm …. there is no large boxes in your training dataset.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1623157,
          "author_name": "dragonzhang",
          "author_url": "",
          "post_date": "12/19/2021 14:55:40",
          "content": "<p>thanks for   both replies.  I didn't dip into metric in detail. just thought of  0 to 1. </p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1622233": "I switched fold and retrained:\n\nAverage forward time: 48.11 ms, Average NMS time: 2.17 ms, Average inference time: 50.28 ms\n Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.471\n Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.896\n Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.445\n Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.329\n Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.507\n Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000 ***\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.204\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.539\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.558\n Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.463\n Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.585\n Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000 ***",
    "1622312": "Because in your fold, there are no area= large bboxes.",
    "1622465": "I can confirm .... there is no large boxes in your training dataset.",
    "1623157": "thanks for   both replies.  I didn't dip into metric in detail. just thought of  0 to 1."
  },
  "source": "meta"
}