這幾天因為要對yolo進行重新訓練，需要用到imagenet pretrain，由於網路是自己設計的網路，所以需要先在darknet上訓練imagenet，由於網上都沒有相關的說明教程，特別是圖片路徑是怎麼和類別標籤對應起來的，讓我百思不得其解，所以最後就自己去查看了darknet的原始碼，發現原來作者是用了字串匹配，來查詢圖片路徑字串中是否有與類別標籤字串匹配的子字串，以此判斷該類別標籤的。

1、darknet對於圖片分類訓練、驗證命令為：

./darknet classifier train cfg/imagenet1k.data cfg/extraction.cfg extraction.weights

./darknet classifier valid cfg/imagenet1k.data cfg/extraction.cfg extraction.weights
 

2、資料格式：資料路徑配置主要讀取自：cfg/imagenet1k.data 

classes=1000
train  = imagenet/darknet_train.txt
valid  = imagenet/darknet_val.txt
backup = backup/
labels = data/imagenet.labels.list
names  = data/imagenet.shortnames.list
top=5

/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10026.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10027.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10029.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10040.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10042.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10043.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10048.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10066.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10074.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_1009.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10095.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10108.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10110.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10120.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10124.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10150.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10159.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10162.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10183.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10194.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10211.JPEG
/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/n01440764/n01440764_10218.JPEG
 

data/imagenet.labels.list

3、由於imagenet的val圖片是放在一起的，路徑不包含標籤，所以需要讀取val標籤.xml檔案，把val的圖片根據標籤，重新存過一遍，放在對應的類別標籤檔案：

#coding=utf-8
import os
import shutil
from BeautifulSoup import BeautifulSoup
#train.txt可通過執行指令碼caffe/data/get_ilsvrc_aux.sh下載獲得
'''with open("../imagenet/train.txt") as f:
    with open("../imagenet/darknet_train.txt",'w') as w:
        for l in f.readlines():
            w.writelines('/home/research/disk1/imagenet/ILSVRC2015/Data/CLS-LOC/train/'+l.split()[0]+'\n')'''


#val
dataroot='/home/research/disk1/imagenet/ILSVRC2015/'
vallabel=dataroot+'Annotations/CLS-LOC/val'
valimage=dataroot+'Data/CLS-LOC/val'
with open("../imagenet/darknet_val.txt",'w') as w:
    for l in os.listdir(vallabel):

        xml = ""
        with open(os.path.join(vallabel,l)) as f:
            xml = f.readlines()
        xml = ''.join([line.strip('\t') for line in xml])

        label=BeautifulSoup(xml).find('name').string
        filename=BeautifulSoup(xml).find('filename').string+'.JPEG'

        saveroot='../temp/'+label
        if os.path.exists(saveroot) is False:
            os.makedirs(saveroot)
        shutil.copy(os.path.join(valimage,filename),os.path.join(saveroot,filename))
        w.writelines('/home/research/disk1/compress_yolo/temp/' + filename+ '\n')