PaddlePaddle 图像分割7日打卡营 class1 图像数据增强实现

        第一次比较完整地参加在线的训练营，也相对认真地实现了课程作业。通过这次训练营，比较直观地了解了图像分割网络的基本原理，并对几个经典的网络做了代码实现。

        其中第一次作业的图像数据增强部分代码实现留下的印象比较深，涉及到一些图像处理和Numpy数组操作的技巧，自己纯手工实现，贴出来以供参考。

import cv2
import numpy as np

class Compose(object):
    def __init__(self, transforms):
        self.transforms = transforms
    def __call__(self, image, label=None):
        for t in self.transforms:
            image, label = t(image, label)
        return image, label


class Normalize(object):
    def __init__(self, mean_val, std_val, val_scale=1):
        # set val_scale = 1 if mean and std are in range (0,1)
        # set val_scale to other value, if mean and std are in range (0,255)
        self.mean = np.array(mean_val, dtype=np.float32)
        self.std = np.array(std_val, dtype=np.float32)
        self.val_scale = 1/255.0 if val_scale==1 else 1
    def __call__(self, image, label=None):
        image = image.astype(np.float32)
        image = image * self.val_scale
        image = image - self.mean
        image = image * (1 / self.std)
        return image, label


class ConvertDataType(object):
    def __call__(self, image, label=None):
        if label is not None:
            label = label.astype(np.int64)
        return image.astype(np.float32), label


class Pad(object):
    def __init__(self, size, ignore_label=255, mean_val=0, val_scale=1):
        # set val_scale to 1 if mean_val is in range (0, 1)
        # set val_scale to 255 if mean_val is in range (0, 255) 
        factor = 255 if val_scale == 1 else 1

        self.size = size
        self.ignore_label = ignore_label
        self.mean_val=mean_val
        # from 0-1 to 0-255
        if isinstance(self.mean_val, (tuple,list)):
            self.mean_val = [int(x* factor) for x in self.mean_val]
        else:
            self.mean_val = int(self.mean_val * factor)


    def __call__(self, image, label=None):
        h, w, c = image.shape
        pad_h = max(self.size - h, 0)
        pad_w = max(self.size - w, 0)

        pad_h_half = int(pad_h / 2)
        pad_w_half = int(pad_w / 2)

        if pad_h > 0 or pad_w > 0:

            image = cv2.copyMakeBorder(image,
                                       top=pad_h_half,
                                       left=pad_w_half,
                                       bottom=pad_h - pad_h_half,
                                       right=pad_w - pad_w_half,
                                       borderType=cv2.BORDER_CONSTANT,
                                       value=self.mean_val)
            if label is not None:
                label = cv2.copyMakeBorder(label,
                                           top=pad_h_half,
                                           left=pad_w_half,
                                           bottom=pad_h - pad_h_half,
                                           right=pad_w - pad_w_half,
                                           borderType=cv2.BORDER_CONSTANT,
                                           value=self.ignore_label)
        return image, label


# TODO
class CenterCrop(object):
    def __init__(self, size):
        self.size = size
    
    def __call__(self, image, label):
        h, w = image.shape[:2]

        h_start = int((h - self.size) / 2)
        w_start = int((w - self.size) / 2)

        image = image[h_start:h_start+self.size, w_start:w_start+self.size, :]
        label = label[h_start:h_start+self.size, w_start:w_start+self.size, :]

        return image, label


# TODO
class Resize(object):
    @staticmethod
    def resize(srcimg, height, width):
        if(len(srcimg.shape) > 2):
            dstimg = cv2.resize(srcimg, (height, width), interpolation=cv2.INTER_NEAREST)
        else:
            dstimg = cv2.resize(srcimg, (height, width), interpolation=cv2.INTER_LINEAR)
        return dstimg



# TODO
class RandomFlip(object):
    def __call__(self, image, label):
        if(np.random.randint(2) % 2 == 1):
            image = np.fliplr(image)
            label = np.fliplr(label)
        return image, label


# TODO
class RandomCrop(object):
    def __init__(self, size=256):
        self.size = size
    
    def __call__(self, image, label):
        h, w = label.shape[:2]

        crop_y = np.random.randint(0, h-self.size)
        crop_x = np.random.randint(0, w-self.size)

        image = image[crop_y:crop_y + self.size, crop_x:crop_x + self.size, :]
        label = label[crop_y:crop_y + self.size, crop_x:crop_x + self.size]

        return image, label

# TODO
class Scale(object):
    def __init__(self, scale):
        self.scale = scale

    def __call__(self, image, label):
        h, w = image.shape[:2]
        h_new, w_new = int(h * self.scale), int(w * self.scale)
        image = Resize.resize(image, h_new, w_new)
        label = Resize.resize(label, h_new, w_new)

        centercrop = CenterCrop(h)

        return centercrop(image, label)

        
    

# TODO
class RandomScale(object):
    def __init__(self, scale_max):
        self.scale_max = scale_max

    def __call__(self, image, label):
        scale = 1.0 + np.random.rand() * (self.scale_max - 1.0)
        h, w = image.shape[:2]
        h_new, w_new = int(h * scale), int(w * scale)
        image = Resize.resize(image, h_new, w_new)
        label = Resize.resize(label, h_new, w_new)

        centercrop = CenterCrop(h)

        return centercrop(image, label)





def main():
    image = cv2.imread('./work/dummy_data/JPEGImages/2008_000064.jpg')
    label = cv2.imread('./work/dummy_data/GroundTruth_trainval_png/2008_000064.png')
    result_dir = './work/transformed/'

    # TODO: crop_size
    image = Resize.resize(image, 480, 640)
    label = Resize.resize(label, 480, 640)
    # TODO: Transform: RandomSacle, RandomFlip, Pad, RandomCrop
    compose = Compose([
        RandomCrop(256),
        RandomScale(2.0),
        RandomFlip(),
        Pad(256)
    ])
    for i in range(10):
        # TODO: call transform
        dstimg, dstlab = compose(image, label)
        # TODO: save image
        cv2.imwrite(result_dir + str(i) + '_image.jpg', dstimg)
        cv2.imwrite(result_dir + str(i) + '_label.jpg', dstlab)

if __name__ == "__main__":
    main()

课程链接：https://aistudio.baidu.com/aistudio/education/group/info/1767