学习笔记12：图像数据增强及学习速率衰减

数据增强

• 常用数据增强方法：

transforms.RandomCrop # 随机位置裁剪
transforms.CenterCrop # 中心位置裁剪
transforms.RandomHorizontalFlip(p = 1) # 随机水平翻转
transforms.RandomVerticalFlip(p = 1) # 随机上下翻转
transforms.RandomRotation # 随机旋转
transforms.ColorJitter(brighter = 1) # 明暗度
transforms.ColorJitter(contrast = 1) # 对比度
transforms.ColorJitter(saturation = 0.5) # 饱和度
transforms.ColorJitter(hue = 0.5) # 随机调整颜色
transforms.RandomGrayscale(p = 0.5) # 随机灰度化

学习速率衰减

学习速率衰减就是每经过几个epoch，学习速率就会降低，一般为指数型衰减

exp_lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size = 5, gamma = 0.9) # 每经过多少个step，衰减为原来的多少
torch.optim.lr_scheduler.MultiStepLR(optimizer, [20, 50, 80], gamma = 0.1) # 哪几个epoch时，衰减为原来的多少
torch.optim.lr_scheduler.ExponentialLR(optimizer, gamma = 0.1) # 按照gamma的epoch次方衰减

注意，要在fit里面加一句

exp_lr_scheduler.step()

完整代码

import torch
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import torch.nn as nn
import torch.nn.functional as F
import torchvision
from torchvision import datasets, transforms, models
import os
import shutil
%matplotlib inline

train_transform = transforms.Compose([
    transforms.Resize(224),
    transforms.RandomCrop(192),
    transforms.RandomHorizontalFlip(),
    transforms.RandomRotation(0.2),
    transforms.ColorJitter(brightness = 0.5),
    transforms.ColorJitter(contrast = 0.5),
    transforms.ToTensor(),
    transforms.Normalize(mean = [0.5, 0.5, 0.5], std = [0.5, 0.5, 0.5])
])
test_transform = transforms.Compose([
    transforms.Resize((192, 192)),
    transforms.ToTensor(),
    transforms.Normalize(mean = [0.5, 0.5, 0.5], std = [0.5, 0.5, 0.5])
])
train_ds = datasets.ImageFolder(
    "E:/datasets2/29-42/29-42/dataset2/4weather/train",
    transform = train_transform
)
test_ds = datasets.ImageFolder(
    "E:/datasets2/29-42/29-42/dataset2/4weather/test",
    transform = test_transform
)
train_dl = torch.utils.data.DataLoader(train_ds, batch_size = 8, shuffle = True)
test_dl = torch.utils.data.DataLoader(test_ds, batch_size = 8)

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

model = models.vgg16(pretrained = True)
for p in model.features.parameters():
    p.requries_grad = False
model.classifier[-1].out_features = 4
model.to(device)

optimizer = torch.optim.Adam(model.parameters(), lr = 0.0001)
epochs = 20
loss_func = torch.nn.CrossEntropyLoss()

exp_lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, 
                                                   step_size = 5,
                                                   gamma = 0.9)

def fit(epoch, model, trainloader, testloader):
    correct = 0
    total = 0
    running_loss = 0
    
    model.train()
    for x, y in trainloader:
        x, y = x.to(device), y.to(device)
        y_pred = model(x)
        loss = loss_func(y_pred, y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        with torch.no_grad():
            y_pred = torch.argmax(y_pred, dim = 1)
            correct += (y_pred == y).sum().item()
            total += y.size(0)
            running_loss += loss.item()

    exp_lr_scheduler.step()    # 规定一个step为一个epoch
    
    epoch_acc = correct / total
    epoch_loss = running_loss / len(trainloader.dataset)
    
    test_correct = 0
    test_total = 0
    test_running_loss = 0
    
    model.eval()
    with torch.no_grad():
        for x, y in testloader:
            x, y = x.to(device), y.to(device)
            y_pred = model(x)
            loss = loss_func(y_pred, y)
            y_pred = torch.argmax(y_pred, dim = 1)
            test_correct += (y_pred == y).sum().item()
            test_total += y.size(0)
            test_running_loss += loss.item()
    epoch_test_acc = test_correct / test_total
    epoch_test_loss = test_running_loss / len(testloader.dataset)
    
    print('epoch: ', epoch, 
          'loss: ', round(epoch_loss, 3),
          'accuracy: ', round(epoch_acc, 3),
          'test_loss: ', round(epoch_test_loss, 3),
          'test_accuracy: ', round(epoch_test_acc, 3))
    
    return epoch_loss, epoch_acc, epoch_test_loss, epoch_test_acc

train_loss = []
train_acc = []
test_loss = []
test_acc = []
for epoch in range(epochs):
    epoch_loss, epoch_acc, epoch_test_loss, epoch_test_acc = fit(epoch, model, train_dl, test_dl)
    train_loss.append(epoch_loss)
    train_acc.append(epoch_acc)
    test_loss.append(epoch_test_loss)
    test_acc.append(epoch_test_acc)

结果展示

准确率有些许的提高