深度学习入门之Pytorch 数据增强的实现

import sys
sys.path.append('..')

from PIL import Image
from torchvision import transforms as tfs

# 读入一张图片
im = Image.open('./cat.png')
im

# 比例缩放
print('before scale, shape: {}'.format(im.size))
new_im = tfs.Resize((100, 200))(im)
print('after scale, shape: {}'.format(new_im.size))
new_im

# 随机裁剪出 100 x 100 的区域
random_im1 = tfs.RandomCrop(100)(im)
random_im1

# 中心裁剪出 100 x 100 的区域
center_im = tfs.CenterCrop(100)(im)
center_im

# 随机水平翻转
h_filp = tfs.RandomHorizontalFlip()(im)
h_filp

# 随机竖直翻转
v_flip = tfs.RandomVerticalFlip()(im)
v_flip

rot_im = tfs.RandomRotation(45)(im)
rot_im

# 亮度
bright_im = tfs.ColorJitter(brightness=1)(im) # 随机从 0 ~ 2 之间亮度变化，1 表示原图
bright_im

# 对比度
contrast_im = tfs.ColorJitter(contrast=1)(im) # 随机从 0 ~ 2 之间对比度变化，1 表示原图
contrast_im

# 颜色
color_im = tfs.ColorJitter(hue=0.5)(im) # 随机从 -0.5 ~ 0.5 之间对颜色变化
color_im

im_aug = tfs.Compose([
  tfs.Resize(120),
  tfs.RandomHorizontalFlip(),
  tfs.RandomCrop(96),
  tfs.ColorJitter(brightness=0.5, contrast=0.5, hue=0.5)
])

import matplotlib.pyplot as plt
%matplotlib inline
nrows = 3
ncols = 3
figsize = (8, 8)
_, figs = plt.subplots(nrows, ncols, figsize=figsize)
for i in range(nrows):
  for j in range(ncols):
    figs[i][j].imshow(im_aug(im))
    figs[i][j].axes.get_xaxis().set_visible(False)
    figs[i][j].axes.get_yaxis().set_visible(False)
plt.show()

import numpy as np
import torch
from torch import nn
import torch.nn.functional as F
from torch.autograd import Variable
from torchvision.datasets import CIFAR10
from utils import train, resnet
from torchvision import transforms as tfs
# 使用数据增强
def train_tf(x):
  im_aug = tfs.Compose([
    tfs.Resize(120),
    tfs.RandomHorizontalFlip(),
    tfs.RandomCrop(96),
    tfs.ColorJitter(brightness=0.5, contrast=0.5, hue=0.5),
    tfs.ToTensor(),
    tfs.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
  ])
  x = im_aug(x)
  return x

def test_tf(x):
  im_aug = tfs.Compose([
    tfs.Resize(96),
    tfs.ToTensor(),
    tfs.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
  ])
  x = im_aug(x)
  return x

train_set = CIFAR10('./data', train=True, transform=train_tf)
train_data = torch.utils.data.DataLoader(train_set, batch_size=64, shuffle=True)
test_set = CIFAR10('./data', train=False, transform=test_tf)
test_data = torch.utils.data.DataLoader(test_set, batch_size=128, shuffle=False)

net = resnet(3, 10)
optimizer = torch.optim.SGD(net.parameters(), lr=0.01)
criterion = nn.CrossEntropyLoss()
train(net, train_data, test_data, 10, optimizer, criterion)

# 不使用数据增强
def data_tf(x):
  im_aug = tfs.Compose([
    tfs.Resize(96),
    tfs.ToTensor(),
    tfs.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
  ])
  x = im_aug(x)
  return x

train_set = CIFAR10('./data', train=True, transform=data_tf)
train_data = torch.utils.data.DataLoader(train_set, batch_size=64, shuffle=True)
test_set = CIFAR10('./data', train=False, transform=data_tf)
test_data = torch.utils.data.DataLoader(test_set, batch_size=128, shuffle=False)

net = resnet(3, 10)
optimizer = torch.optim.SGD(net.parameters(), lr=0.01)
criterion = nn.CrossEntropyLoss()
train(net, train_data, test_data, 10, optimizer, criterion)