Dota数据集切割以及保存为yolo和voc格式——HBB

Dota数据集切割以及保存为yolo和voc格式——HBB

  • 从DOTA1.5的标注中生成YOLO格式标注——HBB
  • 根据得到的YOLO格式转换成PASCAL VOC格式
  • 验证VOC格式 的正确性
  • 可视化结果展示
  • 总结

针对dota目标检测数据集,对image size大于1920的图像进行切割,重叠250个像素点,并且会沿着最后的边缘切割出1920*1920的图像
百度云链接为:链接:https://pan.baidu.com/s/17sabm7k-rZsc5TIvN3pdhw
提取码:nedl


从DOTA1.5的标注中生成YOLO格式标注——HBB

需要修改的位置
Dota数据集切割以及保存为yolo和voc格式——HBB_第1张图片

from PIL import Image,ImageDraw
import numpy as np
import os
import matplotlib.pyplot as plt

def get_anno(x1,y1,x2,y2,a,c,file):
    l1 = a[:,0] < x2-5
    l2 = a[:,1] < y2-5
    l3 = a[:,2] > x1+5
    l4 = a[:,3] > y1+5
    l12 = np.logical_and(l1,l2)
    l23 = np.logical_and(l3,l4)
    l = np.logical_and(l23,l12)
    a = a[l]
    c = c[l]
    a[:,::2] -= x1
    a[:,1::2] -= y1
    a[:,:2] = (a[:,:2] + a[:,2:])/2
    a[:,2:] = (a[:,2:] - a[:,:2])*2
    a[:,::2] /= (x2-x1)
    a[:, 1::2] /= (y2 - y1)

    with open(file,'w+')as f:
        for c_,a_ in zip(c,a):
            c_ = classnames_v1_5.index(c_)
            f.write(str(c_)+' ')
            for a__ in a_:
                f.write(str(a__)+' ')
            f.write('\n')
def read_txt(txt):
    with open(txt,'r')as f:
        a = f.readlines()[2:]
        c = [i.split(' ')[8] for i in a]
        a = [i.split(' ')[:6] for i in a]
        a = np.array(a,dtype=float)
        a = np.concatenate([a[:,:2],a[:,-2:]],axis=1)
    return a,np.array(c,dtype=object)

classnames_v1_5 = ['plane', 'baseball-diamond', 'bridge', 'ground-track-field', 'small-vehicle',
                   'large-vehicle', 'ship', 'tennis-court','basketball-court', 'storage-tank',
                   'soccer-ball-field', 'roundabout', 'harbor', 'swimming-pool', 'helicopter',
                   'container-crane']

ann_file = r'F:\work\zsj\dota\val\images\DOTA-v1.5_val_hbb'
yolo_file = r'F:\work\zsj\dota\val\images\txt'
png_file = r'F:\work\zsj\dota\val\images\images'
jpg_file = r'F:\work\zsj\dota\val\images\jpg'
for file,img in zip(os.listdir(ann_file),os.listdir(png_file)):
    jpg = jpg_file + '\\' + img.replace('png','jpg')
    png = png_file + '\\' + img
    yolo = yolo_file + '\\' + file
    ann = ann_file + '\\' + file
    try:
        a, c = read_txt(ann)
        image = Image.open(png)
        q = 0
        if image.size[0] > 1920 or image.size[1] > 1920:
            for i in range(image.size[0] // 1600):
                for j in range(image.size[1] // 1600):
                    img_ = image.crop((i * 1600, j * 1600, i * 1600 + 1920, j * 1600 + 1920))
                    jpg_ = jpg.replace('.jpg', '%d.jpg' % q)
                    yolo_ = yolo.replace('.txt', '%d.txt' % q)
                    get_anno(i * 1600, j * 1600, i * 1600 + 1920, j * 1600 + 1920, a, c, yolo_)
                    img_.save(jpg_)
                    q += 1
                img_ = image.crop((i * 1600, image.size[1] - 1920, i * 1600 + 1920, image.size[1]))
                jpg_ = jpg.replace('.jpg', '%d.jpg' % q)
                yolo_ = yolo.replace('.txt', '%d.txt' % q)
                get_anno(i * 1600, image.size[1] - 1920, i * 1600 + 1920, image.size[1], a, c, yolo_)
                img_.save(jpg_)
                q += 1
            for j in range(image.size[1] // 1600):
                img_ = image.crop((image.size[0] - 1920, j * 1600, image.size[0], j * 1600 + 1920))
                jpg_ = jpg.replace('.jpg', '%d.jpg' % q)
                yolo_ = yolo.replace('.txt', '%d.txt' % q)
                get_anno(image.size[0] - 1920, j * 1600, image.size[0], j * 1600 + 1920, a, c, yolo_)
                img_.save(jpg_)
                q += 1
            img_ = image.crop((image.size[0] - 1920, image.size[1] - 1920, image.size[0], image.size[1]))
            jpg_ = jpg.replace('.jpg', '%d.jpg' % q)
            yolo_ = yolo.replace('.txt', '%d.txt' % q)
            get_anno(image.size[0] - 1920, image.size[1] - 1920, image.size[0], image.size[1], a, c, yolo_)
            img_.save(jpg_)
            q += 1
        else:
            # jpg_ = jpg.replace('.jpg', '%d.jpg' % q)
            # yolo_ = yolo.replace('.txt', '%d.txt' % q)
            get_anno(0, 0, image.size[0], image.size[1], a, c, yolo)
            image.save(jpg)
        # print(img + ' finished!')
    except:
        print(img + 'failed')

根据得到的YOLO格式转换成PASCAL VOC格式

需要进行修改的位置
Dota数据集切割以及保存为yolo和voc格式——HBB_第2张图片

__Author__ = "Shliang"
__Email__ = "[email protected]"

import os
import xml.etree.ElementTree as ET
from xml.dom.minidom import Document
import cv2
import multiprocessing
from tqdm import tqdm
'''
import xml
xml.dom.minidom.Document().writexml()
def writexml(self,
             writer: Any,
             indent: str = "",
             addindent: str = "",
             newl: str = "",
             encoding: Any = None) -> None
'''

class YOLO2VOCConvert:
    def __init__(self, txts_path, xmls_path, imgs_path):
        self.txts_path = txts_path   # 标注的yolo格式标签文件路径
        self.xmls_path = xmls_path   # 转化为voc格式标签之后保存路径
        self.imgs_path = imgs_path   # 读取读片的路径个图片名字,存储到xml标签文件中
        self.classes = ['granulocyte', 'mitotic figure', 'tumor cell', 'other/ambigous cells',
                        'binucleated cell', 'multinukleated cell', 'Mitotic figure lookalike']

    # 从所有的txt文件中提取出所有的类别, yolo格式的标签格式类别为数字 0,1,...
    # writer为True时,把提取的类别保存到'./Annotations/classes.txt'文件中
    def search_all_classes(self, writer=False):
        # 读取每一个txt标签文件,取出每个目标的标注信息
        all_names = set()
        txts = os.listdir(self.txts_path)
        # 使用列表生成式过滤出只有后缀名为txt的标签文件
        txts = [txt for txt in txts if txt.split('.')[-1] == 'txt']
        print(len(txts), txts)
        # 11 ['0002030.txt', '0002031.txt', ... '0002039.txt', '0002040.txt']
        for txt in txts:
            txt_file = os.path.join(self.txts_path, txt)
            with open(txt_file, 'r') as f:
                objects = f.readlines()
                for object in objects:
                    object = object.strip().split(' ')
                    print(object)  # ['2', '0.506667', '0.553333', '0.490667', '0.658667']
                    all_names.add(int(object[0]))
            # print(objects)  # ['2 0.506667 0.553333 0.490667 0.658667\n', '0 0.496000 0.285333 0.133333 0.096000\n', '8 0.501333 0.412000 0.074667 0.237333\n']

        print("所有的类别标签:", all_names, "共标注数据集:%d张" % len(txts))
        return list(all_names)

    def yolo2voc(self):
        # 创建一个保存xml标签文件的文件夹
        if not os.path.exists(self.xmls_path):
            os.mkdir(self.xmls_path)

        # 把上面的两个循环改写成为一个循环:
        imgs = os.listdir(self.imgs_path)
        txts = os.listdir(self.txts_path)
        txts = [txt for txt in txts if not txt.split('.')[0] == "classes"]  # 过滤掉classes.txt文件
        print(txts)

        # 注意,这里保持图片的数量和标签txt文件数量相等,且要保证名字是一一对应的   (后面改进,通过判断txt文件名是否在imgs中即可)
        if len(imgs) == len(txts):   # 注意:./Annotation_txt 不要把classes.txt文件放进去
            map_imgs_txts = [(img, txt) for img, txt in zip(imgs, txts)]
            txts = [txt for txt in txts if txt.split('.')[-1] == 'txt']
            print(len(txts), txts)
            for img_name, txt_name in map_imgs_txts:
                # 读取图片的尺度信息
                print("读取图片:", img_name)
                img = cv2.imread(os.path.join(self.imgs_path, img_name))
                height_img, width_img, depth_img = img.shape
                print(height_img, width_img, depth_img)   # h 就是多少行(对应图片的高度), w就是多少列(对应图片的宽度)

                # 获取标注文件txt中的标注信息
                all_objects = []
                txt_file = os.path.join(self.txts_path, txt_name)
                with open(txt_file, 'r') as f:
                    objects = f.readlines()
                    for object in objects:
                        object = object.strip().split(' ')
                        all_objects.append(object)
                        print(object)  # ['2', '0.506667', '0.553333', '0.490667', '0.658667']

                # 创建xml标签文件中的标签
                xmlBuilder = Document()
                # 创建annotation标签,也是根标签
                annotation = xmlBuilder.createElement("annotation")

                # 给标签annotation添加一个子标签
                xmlBuilder.appendChild(annotation)

                # 创建子标签folder
                folder = xmlBuilder.createElement("folder")
                # 给子标签folder中存入内容,folder标签中的内容是存放图片的文件夹,例如:JPEGImages
                folderContent = xmlBuilder.createTextNode(self.imgs_path.split('/')[-1])  # 标签内存
                folder.appendChild(folderContent)  # 把内容存入标签
                annotation.appendChild(folder)   # 把存好内容的folder标签放到 annotation根标签下

                # 创建子标签filename
                filename = xmlBuilder.createElement("filename")
                # 给子标签filename中存入内容,filename标签中的内容是图片的名字,例如:000250.jpg
                filenameContent = xmlBuilder.createTextNode(txt_name.split('.')[0] + '.jpg')  # 标签内容
                filename.appendChild(filenameContent)
                annotation.appendChild(filename)

                # 把图片的shape存入xml标签中
                size = xmlBuilder.createElement("size")
                # 给size标签创建子标签width
                width = xmlBuilder.createElement("width")  # size子标签width
                widthContent = xmlBuilder.createTextNode(str(width_img))
                width.appendChild(widthContent)
                size.appendChild(width)   # 把width添加为size的子标签
                # 给size标签创建子标签height
                height = xmlBuilder.createElement("height")  # size子标签height
                heightContent = xmlBuilder.createTextNode(str(height_img))  # xml标签中存入的内容都是字符串
                height.appendChild(heightContent)
                size.appendChild(height)  # 把width添加为size的子标签
                # 给size标签创建子标签depth
                depth = xmlBuilder.createElement("depth")  # size子标签width
                depthContent = xmlBuilder.createTextNode(str(depth_img))
                depth.appendChild(depthContent)
                size.appendChild(depth)  # 把width添加为size的子标签
                annotation.appendChild(size)   # 把size添加为annotation的子标签

                # 每一个object中存储的都是['2', '0.506667', '0.553333', '0.490667', '0.658667']一个标注目标
                for object_info in all_objects:
                    # 开始创建标注目标的label信息的标签
                    object = xmlBuilder.createElement("object")  # 创建object标签
                    # 创建label类别标签
                    # 创建name标签
                    imgName = xmlBuilder.createElement("name")  # 创建name标签
                    imgNameContent = xmlBuilder.createTextNode(self.classes[int(object_info[0])])
                    imgName.appendChild(imgNameContent)
                    object.appendChild(imgName)  # 把name添加为object的子标签

                    # 创建pose标签
                    pose = xmlBuilder.createElement("pose")
                    poseContent = xmlBuilder.createTextNode("Unspecified")
                    pose.appendChild(poseContent)
                    object.appendChild(pose)  # 把pose添加为object的标签

                    # 创建truncated标签
                    truncated = xmlBuilder.createElement("truncated")
                    truncatedContent = xmlBuilder.createTextNode("0")
                    truncated.appendChild(truncatedContent)
                    object.appendChild(truncated)

                    # 创建difficult标签
                    difficult = xmlBuilder.createElement("difficult")
                    difficultContent = xmlBuilder.createTextNode("0")
                    difficult.appendChild(difficultContent)
                    object.appendChild(difficult)

                    # 先转换一下坐标
                    # (objx_center, objy_center, obj_width, obj_height)->(xmin,ymin, xmax,ymax)
                    x_center = float(object_info[1])*width_img + 1
                    y_center = float(object_info[2])*height_img + 1
                    xminVal = int(x_center - 0.5*float(object_info[3])*width_img)   # object_info列表中的元素都是字符串类型
                    yminVal = int(y_center - 0.5*float(object_info[4])*height_img)
                    xmaxVal = int(x_center + 0.5*float(object_info[3])*width_img)
                    ymaxVal = int(y_center + 0.5*float(object_info[4])*height_img)



                    # 创建bndbox标签(三级标签)
                    bndbox = xmlBuilder.createElement("bndbox")
                    # 在bndbox标签下再创建四个子标签(xmin,ymin, xmax,ymax) 即标注物体的坐标和宽高信息
                    # 在voc格式中,标注信息:左上角坐标(xmin, ymin) (xmax, ymax)右下角坐标
                    # 1、创建xmin标签
                    xmin = xmlBuilder.createElement("xmin")  # 创建xmin标签(四级标签)
                    xminContent = xmlBuilder.createTextNode(str(xminVal))
                    xmin.appendChild(xminContent)
                    bndbox.appendChild(xmin)
                    # 2、创建ymin标签
                    ymin = xmlBuilder.createElement("ymin")  # 创建ymin标签(四级标签)
                    yminContent = xmlBuilder.createTextNode(str(yminVal))
                    ymin.appendChild(yminContent)
                    bndbox.appendChild(ymin)
                    # 3、创建xmax标签
                    xmax = xmlBuilder.createElement("xmax")  # 创建xmax标签(四级标签)
                    xmaxContent = xmlBuilder.createTextNode(str(xmaxVal))
                    xmax.appendChild(xmaxContent)
                    bndbox.appendChild(xmax)
                    # 4、创建ymax标签
                    ymax = xmlBuilder.createElement("ymax")  # 创建ymax标签(四级标签)
                    ymaxContent = xmlBuilder.createTextNode(str(ymaxVal))
                    ymax.appendChild(ymaxContent)
                    bndbox.appendChild(ymax)

                    object.appendChild(bndbox)
                    annotation.appendChild(object)  # 把object添加为annotation的子标签
                f = open(os.path.join(self.xmls_path, txt_name.split('.')[0]+'.xml'), 'w')
                xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
                f.close()




import matplotlib.pyplot as plt
def yolo2voc(img_name,txt_name,xmls_path,imgs_path,txts_path,classes):
    print("读取图片:", img_name)
    img = cv2.imread(os.path.join(imgs_path, img_name))
    height_img, width_img, depth_img = img.shape
    # height_img, width_img, depth_img = 640,640,3
    # print(height_img, width_img, depth_img)   # h 就是多少行(对应图片的高度), w就是多少列(对应图片的宽度)

    # 获取标注文件txt中的标注信息
    all_objects = []
    txt_file = os.path.join(txts_path, txt_name)
    with open(txt_file, 'r') as f:
        objects = f.readlines()
        for object in objects:
            object = object.strip().split(' ')
            all_objects.append(object)
            print(object)  # ['2', '0.506667', '0.553333', '0.490667', '0.658667']

    # 创建xml标签文件中的标签
    xmlBuilder = Document()
    # 创建annotation标签,也是根标签
    annotation = xmlBuilder.createElement("annotation")

    # 给标签annotation添加一个子标签
    xmlBuilder.appendChild(annotation)

    # 创建子标签folder
    folder = xmlBuilder.createElement("folder")
    # 给子标签folder中存入内容,folder标签中的内容是存放图片的文件夹,例如:JPEGImages
    folderContent = xmlBuilder.createTextNode(imgs_path.split('/')[-1])  # 标签内存
    folder.appendChild(folderContent)  # 把内容存入标签
    annotation.appendChild(folder)   # 把存好内容的folder标签放到 annotation根标签下

    # 创建子标签filename
    filename = xmlBuilder.createElement("filename")
    # 给子标签filename中存入内容,filename标签中的内容是图片的名字,例如:000250.jpg
    filenameContent = xmlBuilder.createTextNode(txt_name.split('.')[0] + '.jpg')  # 标签内容
    filename.appendChild(filenameContent)
    annotation.appendChild(filename)

    # 把图片的shape存入xml标签中
    size = xmlBuilder.createElement("size")
    # 给size标签创建子标签width
    width = xmlBuilder.createElement("width")  # size子标签width
    widthContent = xmlBuilder.createTextNode(str(width_img))
    width.appendChild(widthContent)
    size.appendChild(width)   # 把width添加为size的子标签
    # 给size标签创建子标签height
    height = xmlBuilder.createElement("height")  # size子标签height
    heightContent = xmlBuilder.createTextNode(str(height_img))  # xml标签中存入的内容都是字符串
    height.appendChild(heightContent)
    size.appendChild(height)  # 把width添加为size的子标签
    # 给size标签创建子标签depth
    depth = xmlBuilder.createElement("depth")  # size子标签width
    depthContent = xmlBuilder.createTextNode(str(depth_img))
    depth.appendChild(depthContent)
    size.appendChild(depth)  # 把width添加为size的子标签
    annotation.appendChild(size)   # 把size添加为annotation的子标签

    # 每一个object中存储的都是['2', '0.506667', '0.553333', '0.490667', '0.658667']一个标注目标
    for object_info in all_objects:
        # 开始创建标注目标的label信息的标签
        object = xmlBuilder.createElement("object")  # 创建object标签
        # 创建label类别标签
        # 创建name标签
        imgName = xmlBuilder.createElement("name")  # 创建name标签
        imgNameContent = xmlBuilder.createTextNode(classes[int(object_info[0])])
        imgName.appendChild(imgNameContent)
        object.appendChild(imgName)  # 把name添加为object的子标签

        # 创建pose标签
        pose = xmlBuilder.createElement("pose")
        poseContent = xmlBuilder.createTextNode("Unspecified")
        pose.appendChild(poseContent)
        object.appendChild(pose)  # 把pose添加为object的标签

        # 创建truncated标签
        truncated = xmlBuilder.createElement("truncated")
        truncatedContent = xmlBuilder.createTextNode("0")
        truncated.appendChild(truncatedContent)
        object.appendChild(truncated)

        # 创建difficult标签
        difficult = xmlBuilder.createElement("difficult")
        difficultContent = xmlBuilder.createTextNode("0")
        difficult.appendChild(difficultContent)
        object.appendChild(difficult)

        # 先转换一下坐标
        # (objx_center, objy_center, obj_width, obj_height)->(xmin,ymin, xmax,ymax)
        x_center = float(object_info[1])*width_img + 1
        y_center = float(object_info[2])*height_img + 1
        xminVal = int(x_center - 0.5*float(object_info[3])*width_img)   # object_info列表中的元素都是字符串类型
        yminVal = int(y_center - 0.5*float(object_info[4])*height_img)
        xmaxVal = int(x_center + 0.5*float(object_info[3])*width_img)
        ymaxVal = int(y_center + 0.5*float(object_info[4])*height_img)



        # 创建bndbox标签(三级标签)
        bndbox = xmlBuilder.createElement("bndbox")
        # 在bndbox标签下再创建四个子标签(xmin,ymin, xmax,ymax) 即标注物体的坐标和宽高信息
        # 在voc格式中,标注信息:左上角坐标(xmin, ymin) (xmax, ymax)右下角坐标
        # 1、创建xmin标签
        xmin = xmlBuilder.createElement("xmin")  # 创建xmin标签(四级标签)
        xminContent = xmlBuilder.createTextNode(str(xminVal))
        xmin.appendChild(xminContent)
        bndbox.appendChild(xmin)
        # 2、创建ymin标签
        ymin = xmlBuilder.createElement("ymin")  # 创建ymin标签(四级标签)
        yminContent = xmlBuilder.createTextNode(str(yminVal))
        ymin.appendChild(yminContent)
        bndbox.appendChild(ymin)
        # 3、创建xmax标签
        xmax = xmlBuilder.createElement("xmax")  # 创建xmax标签(四级标签)
        xmaxContent = xmlBuilder.createTextNode(str(xmaxVal))
        xmax.appendChild(xmaxContent)
        bndbox.appendChild(xmax)
        # 4、创建ymax标签
        ymax = xmlBuilder.createElement("ymax")  # 创建ymax标签(四级标签)
        ymaxContent = xmlBuilder.createTextNode(str(ymaxVal))
        ymax.appendChild(ymaxContent)
        bndbox.appendChild(ymax)

        object.appendChild(bndbox)
        annotation.appendChild(object)  # 把object添加为annotation的子标签
    f = open(os.path.join(xmls_path, txt_name.split('.')[0]+'.xml'), 'w')
    xmlBuilder.writexml(f, indent='\t', newl='\n', addindent='\t', encoding='utf-8')
    f.close()
def print_error(value):
    print("error: ", value)

if __name__ == '__main__':
    print('开始运行主线程')
    multiprocessing.freeze_support()
    multiprocessing.Process()
    pool = multiprocessing.Pool(multiprocessing.cpu_count())
    txts_path1 = r'F:\work\zsj\dota\txt'
    xmls_path1 = r'F:\work\zsj\dota\xml'
    imgs_path1 = r'F:\work\zsj\dota\jpg'
    classes = ['plane', 'baseball-diamond', 'bridge', 'ground-track-field', 'small-vehicle',
                   'large-vehicle', 'ship', 'tennis-court','basketball-court', 'storage-tank',
                   'soccer-ball-field', 'roundabout', 'harbor', 'swimming-pool', 'helicopter',
                   'container-crane']


    # with open('new_classes.txt', 'r') as f:
    #     classes = f.readlines()
    #     classes = [i.split('\n')[0] for i in classes]

    #
    if not os.path.exists(xmls_path1):
        os.mkdir(xmls_path1)

    # 把上面的两个循环改写成为一个循环:
    imgs = os.listdir(imgs_path1)
    txts = os.listdir(txts_path1)
    txts = [txt for txt in txts if not txt.split('.')[0] == "classes"]  # 过滤掉classes.txt文件
    print(txts)

    # 注意,这里保持图片的数量和标签txt文件数量相等,且要保证名字是一一对应的   (后面改进,通过判断txt文件名是否在imgs中即可)
    if len(imgs) == len(txts):   # 注意:./Annotation_txt 不要把classes.txt文件放进去
        map_imgs_txts = [(img, txt) for img, txt in zip(imgs, txts)]
        txts = [txt for txt in txts if txt.split('.')[-1] == 'txt']
        print(len(txts), txts)
        num_q = 0
        with tqdm(total=len(map_imgs_txts),desc='',postfix=dict,mininterval=0.3)as pbar:
            for img_name, txt_name in map_imgs_txts:
                num_q += 1
                pool.apply_async(func=yolo2voc, args=[img_name, txt_name, xmls_path1, imgs_path1, txts_path1, classes],
                                 callback=print_error)
                # pbar.set_postfix(**{'sample:',num_q})
                # pbar.set_postfix(**{'sample:',num_q})
                pbar.update(1)
            pool.close()
            pool.join()
            print('主线程运行结束')

验证VOC格式 的正确性

需要修改的位置Dota数据集切割以及保存为yolo和voc格式——HBB_第3张图片

import matplotlib.pyplot as plt
import cv2
from lxml import etree
import os
import numpy as np
xml = r'F:\work\zsj\yolox-pytorch-main\VOCdevkit\VOC2007\Annotations\3_.xml'
img = r'F:\work\zsj\yolox-pytorch-main\VOCdevkit\VOC2007\JPEGImages\3_.jpg'

for xml,img in zip(os.listdir(r'F:\work\zsj\dota\xml'),os.listdir(r'F:\work\zsj\dota\jpg')):
    xml = r'F:\work\zsj\dota\xml' + '\\' + xml
    img = r'F:\work\zsj\dota\jpg' + '\\' + img
    a = open(xml, 'r')
    tree = etree.parse(a)
    objects = tree.xpath('.//object')
    a = []
    for obj in objects:
        i = []
        i.append(obj.xpath('./bndbox/xmin/text()')[0])
        i.append(obj.xpath('./bndbox/ymin/text()')[0])
        i.append(obj.xpath('./bndbox/xmax/text()')[0])
        i.append(obj.xpath('./bndbox/ymax/text()')[0])
        a.append(i)
    a = np.array(a, dtype='int')
    print(a)

    img = cv2.imread(img)
    for i in a:
        cv2.rectangle(img, i[:2], i[2:4], (0, 255, 0), 2)
    plt.imshow(img)
    plt.show()

可视化结果展示

Dota数据集切割以及保存为yolo和voc格式——HBB_第4张图片

Dota数据集切割以及保存为yolo和voc格式——HBB_第5张图片

总结

对dota数据切割是为了验证小目标检测模型的性能,因此主要是对像素较大的图像进行切割并保存为1920尺寸,但是存在原本较小的图像,那么这些图像的尺寸将不变化。

你可能感兴趣的:(深度学习基础,目标检测,人工智能,计算机视觉)