深度学习炼丹-数据增强

import cv2
import matplotlib.pyplot as plt
from PIL import Image
import numpy as np

def show_images(imgs, num_rows, num_cols, titles=None, scale=8.5):
    """Plot a list of images.

    Defined in :numref:`sec_utils`"""
    figsize = (num_cols * scale, num_rows * scale)
    _, axes = plt.subplots(num_rows, num_cols, figsize=figsize)
    axes = axes.flatten()
    for i, (ax, img) in enumerate(zip(axes, imgs)):
        try:
            img = np.array(img)
        except:
            pass
        ax.imshow(img)
        ax.axes.get_xaxis().set_visible(False)
        ax.axes.get_yaxis().set_visible(False)
        if titles:
            ax.set_title(titles[i])
    return axes
  
# Some Geometric Transformation of Images
class GeometricTransAug(object):
    def __init__(self, image_path):
        img = Image.open(image_path) # load the image
        self.img_np = np.array(img) # convert PIL image to numpy array
        self.rows, self.cols, self.ch = self.img_np.shape
        self.geometry_trans_aug_visual(self.img_np)
        
    def resize_aug(self, img_np):
        # 直接设置了缩放因子, 缩放原大小的2倍
        res = cv2.resize(img_np, None, fx=2, fy=2, interpolation = cv2.INTER_CUBIC)
        return res
    
    def warpAffine_aug(self, img_np):
        # 先构建转换矩阵, 将图像像素点整体进行(100,50)位移：
        M = np.float32([[1,0,100],[0,1,50]]) 
        res = cv2.warpAffine(img_np, M,(self.cols, self.rows))
        return res
    
    def rotation_aug(self, img_np):
        rows, cols, ch = img_np.shape
        # 先构建转换矩阵,图像相对于中心旋转90度而不进行任何缩放。
        M = cv2.getRotationMatrix2D((self.cols/2, self.rows/2), 90, 1) 
        res = cv2.warpAffine(img_np, M, (self.cols, self.rows))
        return res
    
    def radial_trans_aug(self, img_np):
        # 仿射变换需要从原图像中找到三个点以及他们在输出图像中的位置
        pts1 = np.float32([[50,50],[200,50],[50,200]])
        pts2 = np.float32([[10,100],[200,50],[100,250]])
        # 通过 getAffineTransform 创建一个 2x3 的转换矩阵
        M = cv2.getAffineTransform(pts1,pts2)

        res = cv2.warpAffine(img_np, M, dsize = (self.cols, self.rows))
        return res
    
    def perspective_trans_aug(self, img_np):
        # 透视变换需要一个 3x3 变换矩阵
        pts1 = np.float32([[56,65],[368,52],[28,387],[389,390]])
        pts2 = np.float32([[0,0],[300,0],[0,300],[300,300]])

        M = cv2.getPerspectiveTransform(pts1,pts2)
        # dsize: size of the output image.
        res = cv2.warpPerspective(img_np, M, dsize = (300,300))
        
        return res
    
    def geometry_trans_aug_visual(self, img_np):
        res1 = self.resize_aug(img_np)
        res2 = self.warpAffine_aug(img_np)
        res3 = self.rotation_aug(img_np)
        res4 = self.radial_trans_aug(img_np)
        res5 = self.perspective_trans_aug(img_np)
        imgs = [res1, res2, res3, res4, res5]
        aug_titles = ["resize_aug", "warpAffine_aug", "rotation_aug", "radial_trans_aug", "perspective_trans_aug"]
        # show_images 函数前文已经给出，这里不再复制过来
        axes = show_images(imgs, 2, 3, titles=aug_titles, scale=8.5)
            
if __name__ == '__main__': 
    img_path = 'Koalainputimage.jpeg'
    geometry_trans_aug = GeometricTransAug(img_path)
    img_np2 = geometry_trans_aug.img_np
    print(img_np2.shape)

# 为了节省空间，这里不再列出导入相应库的代码和show_images函数
img_PIL = Image.open('astronaut.jpeg')
print(img_PIL.size)
# if you change the seed, make sure that the randomly-applied transforms
# properly show that the image can be both transformed and *not* transformed!
torch.manual_seed(0)
# size 参数: desired output size.
resized_imgs = [transforms.Resize(size=size)(orig_img) for size in (30, 50, 100, orig_img.size)]
show_images(resized_imgs, 1, 4)