MS-Celeb-1M 数据

MS-Celeb-1M数据集

MS-Celeb-1M	Clean	100,000	5,084,127	-	-	Google Drive
MS-Celeb-1M	Align_112x112	85,742	5,822,653	-	-	Google Drive

解压数据集：还未测试

import base64
import csv
import os
 
filename = "K:\celib\dataset\MsCelebV1-Faces-Aligned.part.04.tsv"
outputDir = "K:\celib"
 
with open(filename, 'r') as tsvF:
    reader = csv.reader(tsvF, delimiter='\t')
    i = 0
    for row in reader:
        MID, imgSearchRank, faceID, data = row[0], row[1], row[4], base64.b64decode(row[-1])
 
        saveDir = os.path.join(outputDir, MID)
        savePath = os.path.join(saveDir, "{}-{}.jpg".format(imgSearchRank, faceID))
 
        if not os.path.exists(saveDir):
            os.mkdir(saveDir)
        with open(savePath, 'wb') as f:
            f.write(data)
 
        i += 1
 
        if i % 1000 == 0:
            print("Extracted {} images.".format(i))