{
  "id": 205637,
  "title": "New Metric in TensorFlow",
  "url": "/competitions/ranzcr-clip-catheter-line-classification/discussion/205637",
  "author_name": "",
  "post_date": "2020-12-21T04:19:39.975772800Z",
  "votes": 2,
  "comment_count": 1,
  "views": 0,
  "content": "<p><code>tf.keras.metrics.AUC(multi_label=True)</code> . Is this the new metric implementation in TensorFlow. Thanks in advance.</p>",
  "messages": [
    {
      "id": "1120710",
      "postDate": "12/21/2020 04:19:39",
      "content": "<p><code>tf.keras.metrics.AUC(multi_label=True)</code> . Is this the new metric implementation in TensorFlow. Thanks in advance.</p>",
      "rawMarkdown": "`tf.keras.metrics.AUC(multi_label=True)` . Is this the new metric implementation in TensorFlow. Thanks in advance.",
      "votes": null
    },
    {
      "id": "1123695",
      "postDate": "12/23/2020 12:41:38",
      "content": "<p>Hi, No it is actually an approximation to the metric. Because the AUC is the area under the ROC curve in other words it is integral. Tensorflow function AUC takes an argument (num_thresholds) means the number of points to be taken into account from the curve (200 by default). </p>",
      "rawMarkdown": "Hi, No it is actually an approximation to the metric. Because the AUC is the area under the ROC curve in other words it is integral. Tensorflow function AUC takes an argument (num_thresholds) means the number of points to be taken into account from the curve (200 by default).",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1123695,
      "author_name": "ammarali32",
      "author_url": "",
      "post_date": "12/23/2020 12:41:38",
      "content": "<p>Hi, No it is actually an approximation to the metric. Because the AUC is the area under the ROC curve in other words it is integral. Tensorflow function AUC takes an argument (num_thresholds) means the number of points to be taken into account from the curve (200 by default). </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1120710": "`tf.keras.metrics.AUC(multi_label=True)` . Is this the new metric implementation in TensorFlow. Thanks in advance.",
    "1123695": "Hi, No it is actually an approximation to the metric. Because the AUC is the area under the ROC curve in other words it is integral. Tensorflow function AUC takes an argument (num_thresholds) means the number of points to be taken into account from the curve (200 by default)."
  },
  "source": "meta"
}