语义分割图像增强（数据扩充）教程

港控/mmm° 2022-12-19 11:48 201阅读 0赞

参考博客1：https://blog.csdn.net/qianbin3200896/article/details/88656524?utm\_medium=distribute.pc\_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-3.channel\_param&depth\_1-utm\_source=distribute.pc\_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-3.channel\_param  
参考博客2：https://blog.csdn.net/xuhe93/article/details/105826868

博客1的方法很简单：pip install Augmentor 在本地cmd终端下输入，第二点呢 这是默认安装在你pycharm中的默认下环境中，我的默认是3.7py，所以我得切换到3.7下的环境执行。

#导入数据增强工具
    import Augmentor
     
    #确定原始图像存储路径以及掩码文件存储路径
    p = Augmentor.Pipeline("test1")
    p.ground_truth("test2")
     
    #图像旋转： 按照概率0.8执行，最大左旋角度10，最大右旋角度10
    p.rotate(probability=0.8, max_left_rotation=10, max_right_rotation=10)
     
    #图像左右互换： 按照概率0.5执行
    p.flip_left_right(probability=0.5)
     
    #图像放大缩小： 按照概率0.8执行，面积为原始图0.85倍
    p.zoom_random(probability=0.3, percentage_area=0.85)
     
    #最终扩充的数据样本数
    p.sample(20)

执行后，最终在test1文件目录下会生成一个output文件夹，该文件夹中即为增强过后的图片，如下图所示：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3pxeDk1MTEwMg_size_16_color_FFFFFF_t_70_pic_center]  
标签和转换后的图有编号，可以对应上。主要是旋转，对称上下左右翻转，缩放。

在看看第二种方法：代码源博客不全，参考我下面的代码把：

'''''
    
    
    #2   数据增强代码测试
    import glob
    from keras.preprocessing.image import ImageDataGenerator,load_img,img_to_array,array_to_img
    import os
    import Augmentor
    import cv2
    
    class myAugmentation(object):
        """
        一个用于图像增强的类：
        首先：分别读取训练的图片和标签，然后将图片和标签合并用于下一个阶段使用
        然后：使用Keras的预处理来增强图像
        最后：将增强后的图片分解开，分为训练图片和训练标签
        """
    
        def __init__(self, train_path="D:/shujuzengqiang/1", label_path="D:/shujuzengqiang/2", merge_path="D:/shujuzengqiang/merge", aug_merge_path="D:/shujuzengqiang/aug_merge",
                     aug_train_path="D:/shujuzengqiang/aug_train", aug_label_path="D:/shujuzengqiang/aug_label"):
    
            """
            使用glob从路径中得到所有的“.img_type”文件，初始化类：__init__()
            """
            self.train_imgs = glob.glob(train_path + "/*" )
            self.label_imgs = glob.glob(label_path + "/*" )
            self.train_path = train_path
            self.label_path = label_path
            self.merge_path = merge_path
            self.aug_merge_path = aug_merge_path
            self.aug_train_path = aug_train_path
            self.aug_label_path = aug_label_path
            self.slices = len(self.train_imgs)
            self.datagen = ImageDataGenerator(
                rotation_range=180,
                width_shift_range=0.2,
                height_shift_range=0.2,
                shear_range=0.05,
                zoom_range=0.1,
                horizontal_flip=True,
                vertical_flip=True,
                fill_mode='nearest')
            if not os.path.exists(self.merge_path):
                os.mkdir(self.merge_path)
            if not os.path.exists(self.aug_merge_path):
                os.mkdir(self.aug_merge_path)
            if not os.path.exists(self.aug_label_path):
                os.mkdir(self.aug_label_path)
            if not os.path.exists(self.aug_train_path):
                os.mkdir(self.aug_train_path)
    
        def Augmentation(self):
    
            """
            Start augmentation.....
            """
            trains = self.train_imgs
            labels = self.label_imgs
            path_train = self.train_path
            path_label = self.label_path
            path_merge = self.merge_path
            path_aug_merge = self.aug_merge_path
            if len(trains) != len(labels) or len(trains) == 0 or len(trains) == 0:
                print("trains can't match labels")
                return 0
            for i in range(len(trains)):
                img_t = load_img(trains[i])
                img_l = load_img(labels[i])
                x_t = img_to_array(img_t)
                x_l = img_to_array(img_l)
    
                x_t[:, :, 2] = x_l[:, :, 0]
                img_tmp = array_to_img(x_t)
                img_tmp.save(path_merge + "/" + str(i) + ".png")
                img = x_t
                img = img.reshape((1,) + img.shape)
                savedir = path_aug_merge + "/" + str(i)
                if not os.path.lexists(savedir):
                    os.mkdir(savedir)
                self.doAugmentate(img, savedir, str(i))
    
        def doAugmentate(self, img, save_to_dir, save_prefix, batch_size=1, save_format='png', imgnum=10):
            # 增强一张图片的方法
            """
            augmentate one image
            """
            datagen = self.datagen
            i = 0
            for batch in datagen.flow(img,
                                      batch_size=batch_size,
                                      save_to_dir=save_to_dir,
                                      save_prefix=save_prefix,
                                      save_format=save_format):
                i += 1
                if i >= imgnum:
                    break
    
        def splitMerge(self):
            # 将合在一起的图片分开
            """
            split merged image apart
            """
            path_merge = self.aug_merge_path
            path_train = self.aug_train_path
            path_label = self.aug_label_path
    
            for i in range(self.slices):
                path = path_merge + "/" + str(i)
                train_imgs = glob.glob(path + "/*.png")
                savedir = path_train + "/" + str(i)
                if not os.path.lexists(savedir):
                    os.mkdir(savedir)
                savedir = path_label + "/" + str(i)
    
                if not os.path.lexists(savedir):
                    os.mkdir(savedir)
                for imgname in train_imgs:
    
                    midname = imgname[imgname.rindex("\\") + 1:]
                    img = cv2.imread(imgname)
                    img_train = img[:, :, 2]  # cv2 read image rgb->bgr
                    img_label = img[:, :, 0]
                    cv2.imwrite(path_train + "/" + str(i) + "/" + midname, img_train)
                    cv2.imwrite(path_label + "/" + str(i) + "/" + midname, img_label)
    
    
    if __name__ == "__main__":
        aug = myAugmentation()
        aug.Augmentation()
        aug.splitMerge()
    
    
    '''''

里面只需要改路径就行，看看每个文件夹代表什么。每个图片都生成自己单独的文件夹，里面是这个图片的一系列变化，  
![在这里插入图片描述][2020110709512387.png_pic_center]  
![在这里插入图片描述][20201107095133435.png_pic_center]  
主要的效果就是各种角度的旋转，平移，  
def doAugmentate(self, img, save\_to\_dir, save\_prefix, batch\_size=1, save\_format=‘tif’, imgnum=10):  
修改10 可以变换生成的图像数目。  
当然数据增强是针对数据集较小的时候，很多标注的数据集一般都几百张，数据增强可以有效提高数据量，可以扩充训练数据集。但也并非万能的，有时过度信任数据增强会带来负面效果，还会增加网络训练时间。需酌情使用。

阅读参考3：https://blog.csdn.net/JNingWei/article/details/79219838?utm\_medium=distribute.pc\_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.edu\_weight&depth\_1-utm\_source=distribute.pc\_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.edu\_weight

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3pxeDk1MTEwMg_size_16_color_FFFFFF_t_70_pic_center]: /images/20221120/1b66615acc424d8aac7523717ee15e74.png
[2020110709512387.png_pic_center]: /images/20221120/93e703d265e547b99ce363f22b250eb1.png
[20201107095133435.png_pic_center]: /images/20221120/950ebb532aa74d59a908508d187f9363.png