{
  "id": 375564,
  "title": "Some questions about the index F1 score",
  "url": "/competitions/rsna-breast-cancer-detection/discussion/375564",
  "author_name": "StarxSky",
  "post_date": "2023-01-02T09:51:11.573000",
  "votes": 2,
  "comment_count": 0,
  "views": 0,
  "content": "<p>After my experiments I found that using the torchMetrics library will speed up the program, and at the same time it is more convenient compared to using your own implementation Here is my simple demonstration hope it can help people who are just entering the competition</p>\n<pre><code> torchmetrics.classification  BinaryF1Score\nf1_metrics = BinaryF1Score()\n\nf1_metrics(y_pred, y)\n</code></pre>\n<p>Happy Kaggling !<br>\nHappy 2023🎉 </p>",
  "messages": [
    {
      "id": 2083145,
      "postDate": "2023-01-02T09:51:11.573Z",
      "content": "<p>After my experiments I found that using the torchMetrics library will speed up the program, and at the same time it is more convenient compared to using your own implementation Here is my simple demonstration hope it can help people who are just entering the competition</p>\n<pre><code> torchmetrics.classification  BinaryF1Score\nf1_metrics = BinaryF1Score()\n\nf1_metrics(y_pred, y)\n</code></pre>\n<p>Happy Kaggling !<br>\nHappy 2023🎉 </p>",
      "rawMarkdown": "After my experiments I found that using the torchMetrics library will speed up the program, and at the same time it is more convenient compared to using your own implementation Here is my simple demonstration hope it can help people who are just entering the competition\n\n```python\nfrom torchmetrics.classification import BinaryF1Score\nf1_metrics = BinaryF1Score()\n#It is important to note that the variables y_pred and y must be of the torch.tensor data type\nf1_metrics(y_pred, y)\n```\nHappy Kaggling !\nHappy 2023🎉 ",
      "votes": 2
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2083145": "After my experiments I found that using the torchMetrics library will speed up the program, and at the same time it is more convenient compared to using your own implementation Here is my simple demonstration hope it can help people who are just entering the competition\n\n```python\nfrom torchmetrics.classification import BinaryF1Score\nf1_metrics = BinaryF1Score()\n#It is important to note that the variables y_pred and y must be of the torch.tensor data type\nf1_metrics(y_pred, y)\n```\nHappy Kaggling !\nHappy 2023🎉 "
  }
}