Albumentations Tutorial for Data Augmentation (Pytorch focused)

对比torchvision优势

1.Faster than torchvision on every batch
2.Support for more tasks like segmentation and detection which is a lot harder to do in torchvision

images：

cat_dogs：数据集每个文件夹里有相应的图片文件

1.classification.py

import cv2
import albumentations as A
import numpy as np
from utils import plot_examples
from PIL import Image

image = Image.open("images/elon.jpeg")

transform = A.Compose(
    [
        A.Resize(width=1920, height=1080),
        A.RandomCrop(width=1280, height=720),
        A.Rotate(limit=40, p=0.9, border_mode=cv2.BORDER_CONSTANT),
        # limit 个数 0.9的概率
        A.HorizontalFlip(p=0.5),
        A.VerticalFlip(p=0.1),
        A.RGBShift(r_shift_limit=25, g_shift_limit=25, b_shift_limit=25, p=0.9),
        A.OneOf([
            A.Blur(blur_limit=3, p=0.5),
            A.ColorJitter(p=0.5),
        ], p=1.0),
    ]
)

images_list = [image]
image = np.array(image)
for i in range(15):
    augmentations = transform(image=image)
    augmented_img = augmentations["image"]
    images_list.append(augmented_img)
plot_examples(images_list)

2.segmentation.py

import cv2
import albumentations as A
import numpy as np
from utils import plot_examples
from PIL import Image

image = Image.open("images/elon.jpeg")
mask = Image.open("images/mask.jpeg")
mask2 = Image.open("images/second_mask.jpeg")

transform = A.Compose(
    [
        A.Resize(width=1920, height=1080),
        A.RandomCrop(width=1280, height=720),
        A.Rotate(limit=40, p=0.9, border_mode=cv2.BORDER_CONSTANT),
        A.HorizontalFlip(p=0.5),
        A.VerticalFlip(p=0.1),
        A.RGBShift(r_shift_limit=25, g_shift_limit=25, b_shift_limit=25, p=0.9),
        A.OneOf([
            A.Blur(blur_limit=3, p=0.5),
            A.ColorJitter(p=0.5),
        ], p=1.0),
    ]
)

images_list = [image]
image = np.array(image)
mask = np.array(mask) # np.asarray(mask), np.array(mask)
mask2 = np.array(mask2)
for i in range(4):
    augmentations = transform(image=image, masks=[mask, mask2])
    augmented_img = augmentations["image"]
    augmented_masks = augmentations["masks"]
    images_list.append(augmented_img)
    images_list.append(augmented_masks[0])
    images_list.append(augmented_masks[1])
plot_examples(images_list)

3.detection.py

import cv2
import albumentations as A
import numpy as np
from utils import plot_examples
from PIL import Image

image = cv2.imread("images/cat.jpg")
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# 颜色空间转换函数
bboxes = [[13, 170, 224, 410]]
# list[list[]]

# Pascal_voc (x_min, y_min, x_max, y_max), YOLO, COCO

transform = A.Compose(
    [
        A.Resize(width=1920, height=1080),
        A.RandomCrop(width=1280, height=720),
        A.Rotate(limit=40, p=0.9, border_mode=cv2.BORDER_CONSTANT),
        A.HorizontalFlip(p=0.5),
        A.VerticalFlip(p=0.1),
        A.RGBShift(r_shift_limit=25, g_shift_limit=25, b_shift_limit=25, p=0.9),
        A.OneOf([
            A.Blur(blur_limit=3, p=0.5),
            A.ColorJitter(p=0.5),
        ], p=1.0),
    ], bbox_params=A.BboxParams(format="pascal_voc", min_area=2048,
                                min_visibility=0.3, label_fields=[])
)

images_list = [image]
saved_bboxes = [bboxes[0]]
for i in range(15):
    augmentations = transform(image=image, bboxes=bboxes)
    augmented_img = augmentations["image"]

    if len(augmentations["bboxes"]) == 0:
        continue

    images_list.append(augmented_img)
    saved_bboxes.append(augmentations["bboxes"][0])

plot_examples(images_list, saved_bboxes)

full_pytorch_example

import torch
import numpy as np
import cv2
from PIL import Image
import torch.nn as nn
import albumentations as A
from albumentations.pytorch import ToTensorV2
from torch.utils.data import Dataset
import os

class ImageFolder(Dataset):
    def __init__(self, root_dir, transform=None):
        super(ImageFolder, self).__init__()
        self.data = []
        #[(cat_0.jpg,0),...,(dog_0.jpg,1)]
        self.root_dir = root_dir
        self.transform = transform
        self.class_names = os.listdir(root_dir)

        for index, name in enumerate(self.class_names):
            files = os.listdir(os.path.join(root_dir, name))
            self.data += list(zip(files, [index]*len(files)))

    def __len__(self):
        return len(self.data)

    def __getitem__(self, index):
        img_file, label = self.data[index]
        root_and_dir = os.path.join(self.root_dir, self.class_names[label])
        image = np.array(Image.open(os.path.join(root_and_dir, img_file)))

        if self.transform is not None:
            augmentations = self.transform(image=image)
            # 可以加 bboxes = bboxes
            image = augmentations["image"]

        return image, label


transform = A.Compose(
    [
        A.Resize(width=1920, height=1080),
        A.RandomCrop(width=1280, height=720),
        A.Rotate(limit=40, p=0.9, border_mode=cv2.BORDER_CONSTANT),
        A.HorizontalFlip(p=0.5),
        A.VerticalFlip(p=0.1),
        A.RGBShift(r_shift_limit=25, g_shift_limit=25, b_shift_limit=25, p=0.9),
        A.OneOf([
            A.Blur(blur_limit=3, p=0.5),
            A.ColorJitter(p=0.5),
        ], p=1.0),
        # ToTensor() -> Normalize(mean,stds)
        A.Normalize(
            mean=[0, 0, 0],
            std=[1, 1, 1],
            max_pixel_value=255,
        ),
        ToTensorV2(),
    ]
)

dataset = ImageFolder(root_dir="cat_dogs", transform=transform)

for x,y in dataset:
    print(x.shape)