預處理之邊緣填充

補充：transform.invert 預處理逆操作

from PIL import Image
from torchvision import transforms
import torch
import numpy as np

def transform_invert(img_, transform_train):
    """
    将data 進行反transfrom操作
    :param img_: tensor
    :param transform_train: torchvision.transforms
    :return: PIL image
    """
    if 'Normalize' in str(transform_train):
        # 分析transforms裡的Normalize
        norm_transform = list(filter(lambda x: isinstance(x, transforms.Normalize), transform_train.transforms))
        mean = torch.tensor(norm_transform[0].mean, dtype=img_.dtype, device=img_.device)
        std = torch.tensor(norm_transform[0].std, dtype=img_.dtype, device=img_.device)
        img_.mul_(std[:, None, None]).add_(mean[:, None, None])  # 廣播三個次元 乘标準差 加均值

    img_ = img_.transpose(0, 2).transpose(0, 1)  # C*H*W --> H*W*C

    # 如果有ToTensor，那麼之前數值就會被壓縮至0-1之間。現在需要反變換回來，也就是乘255
    if 'ToTensor' in str(transform_train):
        img_ = np.array(img_) * 255

    # 先将np的元素轉換為uint8資料類型，然後轉換為PIL.Image類型
    if img_.shape[2] == 3:  # 若通道數為3 需要轉為RGB類型
        img_ = Image.fromarray(img_.astype('uint8')).convert('RGB')
    elif img_.shape[2] == 1:  # 若通道數為1 需要壓縮張量的次元至2D
        img_ = Image.fromarray(img_.astype('uint8').squeeze())
    else:
        raise Exception("Invalid img shape, expected 1 or 3 in axis 2, but got {}!".format(img_.shape[2]))

    return img_

if __name__ == '__main__':
    
    img = Image.open(r"./test.jpg").convert('RGB')
    img_transform = transforms.Compose([transforms.ToTensor()])
    img_tensor = img_transform(img)
    # img_tensor.unsqueeze_(dim=0)    # C*H*W to B*C*H*W
    print(img_tensor)
    print(img_tensor.shape)
    
    img = transform_invert(img_tensor, img_transform)  # input: shape=[c h w]
    img.show()      

邊緣填充：Pad

功能：對圖檔邊緣進行填充

主要參數說明：

1. padding :設定填充大小

   當為a時，上下左右均填充a個像素

   當為(a, b)時，上下填充b個像素，左右填充a個像素

   當為(a, b, c, d)時，左，上，右，下分别填充a, b, c, d

2. padding_mode :填充模式，有4種模式，constant、 edge、 reflect和symmetric
3. fill ：padding_mode 是constant時， 設定填充的像素值，(R，G, B) or (Gray)

from PIL import Image
from torchvision import transforms
from utils import transform_invert


if __name__ == '__main__':
    # 1.讀取圖像
    img = Image.open(r"./test.jpg").convert('RGB')
    # 2.确定預處理方式
    img_transform = transforms.Compose([transforms.Resize((300,300)),  # 重置大小為300*300
                                        transforms.Pad(120,fill=(0,0,0),padding_mode='constant'), # 填充0
                                        transforms.ToTensor()  # 轉Tensor型變量
                                        ])
    # 3.進行預處理
    img_tensor = img_transform(img)
    # 4.逆Transform變換
    img = transform_invert(img_tensor, img_transform)  # input: shape=[c h w]
    # 5.進行預處理效果展示
    img.show()      

from PIL import Image
from torchvision import transforms
from utils import transform_invert


if __name__ == '__main__':
    # 1.讀取圖像
    img = Image.open(r"./test.jpg").convert('RGB')
    # 2.确定預處理方式
    img_transform = transforms.Compose([transforms.Resize((300,300)),  # 重置大小為300*300
                                        transforms.Pad(120,fill=(0,255,0),padding_mode='constant'), # 填充為綠色
                                        transforms.ToTensor()  # 轉Tensor型變量
                                        ])
    # 3.進行預處理
    img_tensor = img_transform(img)
    # 4.逆Transform變換
    img = transform_invert(img_tensor, img_transform)  # input: shape=[c h w]
    # 5.進行預處理效果展示
    img.show()      

鏡像填充

from PIL import Image
from torchvision import transforms
from utils import transform_invert


if __name__ == '__main__':
    # 1.讀取圖像
    img = Image.open(r"./test.jpg").convert('RGB')
    # 2.确定預處理方式
    img_transform = transforms.Compose([transforms.Resize((300,300)),  # 重置大小為300*300
                                        transforms.Pad(120,fill=(0,255,0),padding_mode='reflect'), # 填充0
                                        transforms.ToTensor()  # 轉Tensor型變量
                                        ])
    # 3.進行預處理
    img_tensor = img_transform(img)
    # 4.逆Transform變換
    img = transform_invert(img_tensor, img_transform)  # input: shape=[c h w]
    # 5.進行預處理效果展示
    img.show()