基于 Paddle 和 YOLOv5 实现 猫狗检测_yolov5 paddle

1. YOLOv5训练数据集准备

解压数据集并移动到工作目录

In [1]

#解压数据集
!ls /home/aistudio/data
!unzip -q /home/aistudio/data/data249593/datasets.zip
!mv datasets VOCdata
# 将数据集移动到工作区
!mv /home/aistudio/VOCdata /home/aistudio/work/
%cd /home/aistudio/work/VOCdata/
# 重命名图片文件夹
!mv JPEGImages images

data249593
/home/aistudio/work/VOCdata

In [ ]

!unzip test.zip

执行下面两段代码来将VOC格式数据集转换成YOLOV5标准格式

In [2]

%cd /home/aistudio/work/VOCdata/
import os
import random
trainval_percent = 0.1
train_percent = 0.9
xmlfilepath = '/home/aistudio/work/VOCdata/Annotations'  #xml文件存放地址
if not os.path.exists('ImageSets/'):
    os.makedirs('ImageSets/')
 
total_xml = os.listdir(xmlfilepath)
num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)
ftrainval = open('ImageSets/trainval.txt', 'w')
ftest = open('ImageSets/test.txt', 'w')
ftrain = open('ImageSets/train.txt', 'w')
fval = open('ImageSets/val.txt', 'w')
for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftest.write(name)
        else:
            fval.write(name)
    else:
        ftrain.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

/home/aistudio/work/VOCdata

In [3]

%cd /home/aistudio/work/VOCdata/
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
sets = ['train', 'test','val']
Imgpath = '/home/aistudio/work/VOCdata/images'    #图片文件夹
xmlfilepath = '/home/aistudio/work/VOCdata/Annotations/'  #xml文件存放地址
ImageSets_path='ImageSets/'
classes = ['cat','dog']   # 识别目标种类
def convert(size, box):
    dw = 1. / size[0]
    dh = 1. / size[1]
    x = (box[0] + box[1]) / 2.0
    y = (box[2] + box[3]) / 2.0
    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(image_id):
    in_file = open(xmlfilepath+'%s.xml' % (image_id))
    out_file = open('labels/%s.txt' % (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 &#