{
  "fetched_at": "2026-10-19T17:40:54Z",
  "source_url": "https://www.kaggle.com/competitions/11-785-summer-20-homework-2-part-2-verification/data",
  "pages": [
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "The data for the verification task can be downloaded from [here](https://www.kaggle.com/c/11-785-summer-20-homework-2-part-2-classification/data).\n\nA sample submission is provided below.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "The problem of determining whether two face images are of the same person is known as\nface verification. The input to your system will be a trial, i.e., a pair of face images that may or may not belong to the same person. Given a trial, your goal is to output a numeric score that quantifies how similar the faces in the two images are. A higher score will indicate higher confidence that the faces in the two images are of the same person. Please check the writeup for more details.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "As mentioned in the part 2 handout, the utils.py utility is:\n\n<pre>from sklearn.metrics import roc_auc_score\nimport sys\nimport pandas as pd\n\ndef get_auc(y_true, y_score):\n    auc = roc_auc_score(y_true, y_score)\n    return auc\n\nif __name__ == '__main__':\n    args = sys.argv[1:]\n    if len(args)  \"\n        exit()\n    score_csv = args[0]\n    label_csv = args[1]\n    y_score = pd.read_csv(score_csv).score.values\n    y_true = pd.read_csv(label_csv).score.values\n    auc = get_auc(y_true, y_score)\n    print \"AUC: \", auc\n</pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}