In [1]:

    

import sklearn
import numpy as np


    

In [2]:

    

import os
import re


    

In [3]:

    

dataset = {
    (folder_name,int(re.findall(r"\d\d\d\d",file_name)[0])): "dataset/lfw/%s/%s" % (folder_name,file_name)
    for folder_name in os.listdir("dataset/lfw/")
    for file_name in os.listdir("dataset/lfw/"+folder_name)
}
#dataset[('Mehdi_Ghanimifard','1')] = 'dataset/lfw/Mehdi_Ghanimifard/Mehdi_Ghanimifard_0001.jpg'


    

In [ ]:

    




    

In [4]:

    

dataset_att = dict()
with open('dataset/pubfig_attributes.txt') as att_file:
    for index, line in enumerate(att_file):
        items = line.split('\t')
        if index == 1:
            attributes = items[2:]
        if index > 1:
            dataset_att[tuple(items[:2])] = np.array(items[2:]).astype(np.float)


    

In [ ]: