数据增强，步骤整理，以后备用

方法一：

self.transforms = transforms.Compose([
                #对输入图像进行裁剪，保持图片中心点不变。transform = CenterCrop(224)。
                transforms.CenterCrop(224),  
                #随机调整图像的亮度，对比度，饱和度和色调。 transform = ColorJitter(0.4, 0.4, 0.4, 0.4)
                transforms.ColorJitter(0.4, 0.5, 0.6, 0.7), 
                #依据degrees参数指定的角度范围，按照均匀分布随机产生一个角度对图像进行旋转。
                transforms.RandomRotation(60),  
                #将形状为 （H x W x C）的输入数据 PIL.Image 或 numpy.ndarray 转换为 (C x H x W)。
                transforms.ToTensor(),
                #图像归一化处理，支持两种方式： 1. 用统一的均值和标准差值对图像的每个通道进行归一化处理； 2. 对每个通道指定不同的均值和标准差值进行归一化处理。
                transforms.Normalize(mean=[127.5, 127.5, 127.5],std=[127.5, 127.5, 127.5],)   
            ])

方法二：

import os
import math
import random
import functools
import numpy as np
import paddle
from PIL import Image, ImageEnhance

random.seed(0)
np.random.seed(0)

DATA_DIM = 224

THREAD = 8
BUF_SIZE = 102400

DATA_DIR = './'

img_mean = np.array([0.485, 0.456, 0.406]).reshape((3, 1, 1))
# 0.485, 0.456, 0.406
img_std = np.array([0.229, 0.224, 0.225]).reshape((3, 1, 1))
# 0.229, 0.224, 0.225


def resize_short(img, target_size):
	percent = float(target_size) / min(img.size[0], img.size[1])
	resized_width = int(round(img.size[0] * percent))
	resized_height = int(round(img.size[1] * percent))
	img = img.resize((resized_width, resized_height), Image.LANCZOS)
	return img

#裁剪

def crop_image(img, target_size, center):
	width, height = img.size
	size = target_size
	if center == True:
		w_start = (width - size) / 2
		h_start = (height - size) / 2
	else:
		w_start = np.random.randint(0, width - size + 1)
		h_start = np.random.randint(0, height - size + 1)
	w_end = w_start + size
	h_end = h_start + size
	img = img.crop((w_start, h_start, w_end, h_end))
	return img


def random_crop(img, size, scale=[0.08, 1.0], ratio=[3. / 4., 4. / 3.]):
	aspect_ratio = math.sqrt(np.random.uniform(*ratio))
	w = 1. * aspect_ratio
	h = 1. / aspect_ratio

	bound = min((float(img.size[0]) / img.size[1]) / (w**2),
                (float(img.size[1]) / img.size[0]) / (h**2))
	scale_max = min(scale[1], bound)
	scale_min = min(scale[0], bound)

	target_area = img.size[0] * img.size[1] * np.random.uniform(scale_min,
                                                             scale_max)
	target_size = math.sqrt(target_area)
	w = int(target_size * w)
	h = int(target_size * h)

	i = np.random.randint(0, img.size[0] - w + 1)
	j = np.random.randint(0, img.size[1] - h + 1)

	img = img.crop((i, j, i + w, j + h))
	img = img.resize((size, size), Image.LANCZOS)
	return img

#角度
def rotate_image(img):
	angle = np.random.randint(-10, 11)
	img = img.rotate(angle)
	return img

#概率的图像增强 
def distort_color(img):
	def random_brightness(img, lower=0.5, upper=1.5):
		e = np.random.uniform(lower, upper)
		return ImageEnhance.Brightness(img).enhance(e)

	def random_contrast(img, lower=0.5, upper=1.5):
		e = np.random.uniform(lower, upper)
		return ImageEnhance.Contrast(img).enhance(e)

	def random_color(img, lower=0.5, upper=1.5):
		e = np.random.uniform(lower, upper)
		return ImageEnhance.Color(img).enhance(e)

	ops = [random_brightness, random_contrast, random_color]
	np.random.shuffle(ops)

	img = ops[0](img)
	img = ops[1](img)
	img = ops[2](img)

	return img

#图片综合处理
def process_image(sample, mode, color_jitter, rotate):
	img_path = sample[0]

	img = Image.open(img_path)
	if mode == 'train':
		if rotate: img = rotate_image(img)
		img = random_crop(img, DATA_DIM)
	else:
		img = resize_short(img, target_size=256)
		img = crop_image(img, target_size=DATA_DIM, center=True)
	if mode == 'train':
		if color_jitter:
			img = distort_color(img)
		if np.random.randint(0, 2) == 1:
			img = img.transpose(Image.FLIP_LEFT_RIGHT)

	if img.mode != 'RGB':
		img = img.convert('RGB')

	img = np.array(img).astype('float32').transpose((2, 0, 1)) / 255
	img -= img_mean
	img /= img_std

	if mode == 'train' or mode == 'val':
		return img, sample[1]
	elif mode == 'test':
		return [img]

#创建reader
def _reader_creator(file_list,
                    mode,
                    shuffle=False,
                    color_jitter=False,
                    rotate=False,
                    data_dir=DATA_DIR):
	def reader():
		
		with open(file_list) as flist:
			full_lines = [line.strip() for line in flist]
			if shuffle:
				np.random.shuffle(full_lines)
			if mode == 'train' and os.getenv('PADDLE_TRAINING_ROLE'):
                # distributed mode if the env var `PADDLE_TRAINING_ROLE` exits
				trainer_id = int(os.getenv("PADDLE_TRAINER_ID", "0"))
				trainer_count = int(os.getenv("PADDLE_TRAINERS", "1"))
				per_node_lines = len(full_lines) // trainer_count
				lines = full_lines[trainer_id * per_node_lines:(trainer_id + 1)
                                   * per_node_lines]
				print(
                    "read images from %d, length: %d, lines length: %d, total: %d"
                    % (trainer_id * per_node_lines, per_node_lines, len(lines),
                       len(full_lines)))
			else:
				lines = full_lines

			for line in lines:
				if mode == 'train' or mode == 'val':
					img_path, label = line.split('\t')
					img_path = img_path.replace("JPEG", "jpeg")
					img_path = os.path.join(data_dir, img_path)
					yield img_path, int(label)
				elif mode == 'test':
                    #img_path = os.path.join(data_dir, line)
					img_path, label = line.split('\t')
					img_path = img_path.replace("JPEG", "jpeg")
					img_path = os.path.join(data_dir, img_path)
					yield [img_path]

	mapper = functools.partial(
		process_image, mode=mode, color_jitter=color_jitter, rotate=rotate)

	mapper = functools.partial(
		process_image, mode=mode, color_jitter=color_jitter, rotate=rotate)

	return paddle.reader.xmap_readers(mapper, reader, THREAD, BUF_SIZE)


def train(data_dir=DATA_DIR):
	file_list = os.path.join(data_dir, 'train_split_list.txt')
	return _reader_creator(
        file_list, 'train', shuffle=True, color_jitter=False, rotate=False, data_dir=data_dir)


def val(data_dir=DATA_DIR):
	file_list = os.path.join(data_dir, 'val_split_list.txt')
	return _reader_creator(file_list, 'val', shuffle=False, data_dir=data_dir)


def test(data_dir=DATA_DIR):
	file_list = os.path.join(data_dir, 'test_list.txt')
	return _reader_creator(file_list, 'test', shuffle=False, data_dir=data_dir)