{
  "fetched_at": "2026-10-24T16:30:23Z",
  "source_url": "https://www.kaggle.com/competitions/deep-learning-hw2p2-part-2-verification/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>Please refer to the writeup</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>This is part 2 Face verification for HW2P2. In addition to this, you should also finish part 1 Face classification.</p>\n\n<p>In part 2 Face verification, you will use Convolutional Neural Networks (CNNs) to design an end-to-end system for face verification. Your system will be given two images as input and will output a score that quantifies the similarity between the faces in these images. This helps us decide whether the faces from the two images are of the same person or not.</p>\n\n<p>You can build on your face classification model, or use other methods like Siamese Networks. Read the writeup for more hints.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The Receiver Operating Characteristic (ROC) curve is created by plotting the True Positive Rate (TPR) against the False Positive Rate (FPR) at various threshold settings. The Area Under the Curve (AUC) for the ROC curve is equal to the probability that a classifier will rank a randomly chosen similar pair (images of same people) higher than a randomly chosen dissimilar one (images from two different people) (assuming 'similar' ranks higher than 'dissimilar' in terms of similarity scores).</p>\n\n<p>As mentioned in the part 2 handout, the utils.py utility is:</p>\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)</pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "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
    }
  ]
}