YOLO V3 训练前戏1:数据集下载和格式转换
获取Pascal VOC数据集
- VOC 2007和 2012. here.
wget https://pjreddie.com/media/files/VOCtrainval_11-May-2012.tar wget https://pjreddie.com/media/files/VOCtrainval_06-Nov-2007.tar wget https://pjreddie.com/media/files/VOCtest_06-Nov-2007.tar tar xf VOCtrainval_11-May-2012.tar tar xf VOCtrainval_06-Nov-2007.tar tar xf VOCtest_06-Nov-2007.tar
生成 VOC标签
Darknet 需要 .txt
文件:
<object-class> <x> <y> <width> <height>
坐标:x
, y
长宽: width
, height
.
运行scripts/下面的 voc_label.py
或者直接下载运行:
wget https://pjreddie.com/media/files/voc_label.py python voc_label.py
生成 VOCdevkit/VOC2007/labels/
和 VOCdevkit/VOC2012/labels/
.
import xml.etree.ElementTree as ET import pickle import os from os import listdir, getcwd from os.path import join sets=[('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test')] classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"] def convert(size, box): dw = 1./(size[0]) dh = 1./(size[1]) x = (box[0] + box[1])/2.0 - 1 y = (box[2] + box[3])/2.0 - 1 w = box[1] - box[0] h = box[3] - box[2] x = x*dw w = w*dw y = y*dh h = h*dh return (x,y,w,h) def convert_annotation(year, image_id): in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id)) out_file = open('VOCdevkit/VOC%s/labels/%s.txt'%(year, image_id), 'w') tree=ET.parse(in_file) root = tree.getroot() size = root.find('size') w = int(size.find('width').text) h = int(size.find('height').text) for obj in root.iter('object'): difficult = obj.find('difficult').text cls = obj.find('name').text if cls not in classes or int(difficult)==1: continue cls_id = classes.index(cls) xmlbox = obj.find('bndbox') b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text)) bb = convert((w,h), b) out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n') wd = getcwd() for year, image_set in sets: if not os.path.exists('VOCdevkit/VOC%s/labels/'%(year)): os.makedirs('VOCdevkit/VOC%s/labels/'%(year)) image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split() list_file = open('%s_%s.txt'%(year, image_set), 'w') for image_id in image_ids: list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n'%(wd, year, image_id)) convert_annotation(year, image_id) list_file.close() os.system("cat 2007_train.txt 2007_val.txt 2012_train.txt 2012_val.txt > train.txt") os.system("cat 2007_train.txt 2007_val.txt 2007_test.txt 2012_train.txt 2012_val.txt > train.all.txt")
可以查看:
ls 2007_test.txt VOCdevkit 2007_train.txt voc_label.py 2007_val.txt VOCtest_06-Nov-2007.tar 2012_train.txt VOCtrainval_06-Nov-2007.tar 2012_val.txt VOCtrainval_11-May-2012.tar
其中我们只训练除test之外的.txt文件,运行:
cat 2007_train.txt 2007_val.txt 2012_*.txt > train.txt
到此为止,训练阶段数据部分就处理完毕!