identify.py

def identify_traffic(x, database, model):
    """
    Implements traffic recognition.

    Arguments:
    x -- the traffic to identify
    database -- database containing recognized traffic encodings
    model -- the encoding model

    Returns:
    min_dist -- the minimum distance between traffic encoding and the encodings from the database
    identity -- string, the traffic prediction name
    """

    # Compute the target "encoding" for the traffic.
    encoding = traffic_to_encoding(x, model)

    # Find the closest encoding
    min_dist = 100

    identity = 'unknown'
    for (name, db_enc) in database.items():
     # Compute L2 distance between the target "encoding" and the current "emb" from the database.
        dist = np.linalg.norm(db_enc-encoding)

        # If this distance is less than the min_dist, then set min_dist to dist, and identity to name.
        if dist < min_dist:
            min_dist = dist
            identity = name

    return min_dist, identity