PyTorch简明教程 | 3-迁移学习实例

from __future__ import print_function, division

import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy

plt.ion()


#1- 加载数据和预处理
# 训练的时候会做数据增强和归一化
# 而验证的时候只做归一化

data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
        ]),
    'val': transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
        ]),

}

data_dir = '../data/'
image_dataset = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) 
                for x in ['train', 'val']}
dataloaders = {x: torch.utils.data.DataLoader(image_dataset[x], batch_size=4,
                shuffle=True, num_workers=4)
                for x in ['train', 'val']}
data_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes

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


#2- 可视化图片
def imshow(inp, title=None):
    inp = inp.numpy().transpose((1, 2, 0))
    mean = np.array([0.485, 0.456, 0.406])
    std = np.array([0.229, 0.224, 0.225])
    inp = std * inp + mean
    inp = np.clip(inp, 0, 1)
    plt.imshow(inp)
    if title is not None:
        plt.title(title)
    plt.pause(0.001)


# 得到一个batch的数据
inputs, classes = next(iter(dataloaders['train']))

# 把batch张图片拼接成一个大图
out = torchvision.utils.make_grid(inputs)

imshow(out, title=[class_names[x] for x in classes])

#3- 训练模型
#完成learning rate的自适应 和 保存最好的模型
def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
    since = time.time()
    
    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0
    
    for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)
        
        # 每个epoch都分为训练和验证阶段
        for phase in ['train', 'val']:
            if phase == 'train':
                scheduler.step()
                model.train()  # 训练阶段
            else:
                model.eval()   # 验证阶段
            
            running_loss = 0.0
            running_corrects = 0
            
            # 变量数据集
            for inputs, labels in dataloaders[phase]:
                inputs = inputs.to(device)
                labels = labels.to(device)
            
            # 参数梯度清空
            optimizer.zero_grad()
            
            # forward
            # 只有训练的时候track用于梯度计算的历史信息。
            with torch.set_grad_enabled(phase == 'train'):
                outputs = model(inputs)
                _, preds = torch.max(outputs, 1)
                loss = criterion(outputs, labels)
                
                # 如果是训练，那么需要backward和更新参数 
                if phase == 'train':
                    loss.backward()
                    optimizer.step()
            
            # 统计
            running_loss += loss.item() * inputs.size(0)
            running_corrects += torch.sum(preds == labels.data)
            
            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects.double() / dataset_sizes[phase]
            
            print('{} Loss: {:.4f} Acc: {:.4f}'.format(
                phase, epoch_loss, epoch_acc))
            
            # 保存验证集上的最佳模型
            if phase == 'val' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())
            
            print()
    
    time_elapsed = time.time() - since
    print('Training complete in {:.0f}m {:.0f}s'.format(
        time_elapsed // 60, time_elapsed % 60))
    print('Best val Acc: {:4f}'.format(best_acc))
    
    # 加载最优模型
    model.load_state_dict(best_model_wts)
    return model


#4- 可视化结果

def visualize_model(model, num_images=6):
    was_training = model.training
    model.eval()
    images_so_far = 0
    fig = plt.figure()
    
    with torch.no_grad():
        for i, (inputs, labels) in enumerate(dataloaders['val']):
            inputs = inputs.to(device)
            labels = labels.to(device)
            
            outputs = model(inputs)
            _, preds = torch.max(outputs, 1)
            
            for j in range(inputs.size()[0]):
                images_so_far += 1
                ax = plt.subplot(num_images//2, 2, images_so_far)
                ax.axis('off')
                ax.set_title('predicted: {}'.format(class_names[preds[j]]))
                imshow(inputs.cpu().data[j])
                
                if images_so_far == num_images:
                    model.train(mode=was_training)
                    return
        model.train(mode=was_training)

#5- fine-tuning 所有参数
#因为类别不一样需要删掉原来的全连接层，换成新的全连接层。这里我们让所有的模型参数都可以调整，包括新加的全连接层和预训练的层。
model_ft = models.resnet18(pretrained=True)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 2)

model_ft = model_ft.to(device)

criterion = nn.CrossEntropyLoss()

# 所有的参数都可以训练
optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)

# 每7个epoch learning rate变为原来的10% 
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)

model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
    num_epochs=25)

#6- fine-tuning最后一层参数
#可以固定住前面层的参数，只训练最后一层，时间快一倍
model_conv = torchvision.models.resnet18(pretrained=True)
for param in model_conv.parameters():
    param.requires_grad = False

# 新加的层默认requires_grad=True 
num_ftrs = model_conv.fc.in_features
model_conv.fc = nn.Linear(num_ftrs, 2)

model_conv = model_conv.to(device)

criterion = nn.CrossEntropyLoss()

# 值训练最后一个全连接层。
optimizer_conv = optim.SGD(model_conv.fc.parameters(), lr=0.001, momentum=0.9)

exp_lr_scheduler = lr_scheduler.StepLR(optimizer_conv, step_size=7, gamma=0.1)

model_conv = train_model(model_conv, criterion, optimizer_conv,
    exp_lr_scheduler, num_epochs=25)