基于经典网络架构训练图像分类模型

数据预处理部分

1、数据增强：torchvision模块中的transforms模块自带功能。
2、数据预处理： torchvision中的transforms模块也帮我们实现了。
3、DataLoader： 读取batch数据

网络模块设置

1、加载预训练模型，利用人家训练好的权重文件来继续训练我们自己的模型
2、修改成我们自己的任务， 需把最后的head层修改，一般就是最后的全连接层，改成我们自己的任务。
3、训练时可以全部训练，也可以训练我们自己的任务层， 因为前几层都是用来做滕峥提取的。

网络模型的保存和测试

1、我们可以选择最好的模型进行保存
2、读取模型进行实际测试

一、导入库函数

import os
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import torch
from torch import nn
import torch.optim as optim
import torchvision
#pip install torchvision
from torchvision import transforms, models, datasets
#https://pytorch.org/docs/stable/torchvision/index.html
import imageio
import time
import warnings
import random
import sys
import copy
import json
from PIL import Image

1、数据读取与预处理操作

data_dir = './flower_data/'
train_dir = data_dir + '/train'
valid_dir = data_dir + '/valid'

2、制作好数据源

data_transforms中指定了所有图像的预处理操作
ImageFolder 假设所有文件按照文件夹保存好， 每个文件夹下存放相同类别的图像，文件名为类别的名字。

data_transforms = {
    'train': transforms.Compose([transforms.RandomRotation(45),#随机旋转，-45到45度之间随机选
        transforms.CenterCrop(224),#从中心开始裁剪
        transforms.RandomHorizontalFlip(p=0.5),#随机水平翻转 选择一个概率概率
        transforms.RandomVerticalFlip(p=0.5),#随机垂直翻转
        transforms.ColorJitter(brightness=0.2, contrast=0.1, saturation=0.1, hue=0.1),#参数1为亮度，参数2为对比度，参数3为饱和度，参数4为色相
        transforms.RandomGrayscale(p=0.025),#概率转换成灰度率，3通道就是R=G=B
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])#均值，标准差
    ]),
    'valid': transforms.Compose([transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
}

batch_size = 8

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

image_datasets

dataLoaders

datasets_sizes

3、读取标签对应的实际类别名字

with open('cat_to_name.json', 'r') as f:
	 cat_to_name = json.load(f)

cat_to_name

4、展示下数据
注意tensor的数据需要转换成numpy的格式，而且还需要还原回标准化的结果

def im_convert(tensor):
    """ 展示数据"""
    
    image = tensor.to("cpu").clone().detach()
    image = image.numpy().squeeze()
    image = image.transpose(1,2,0)
    image = image * np.array((0.229, 0.224, 0.225)) + np.array((0.485, 0.456, 0.406))
    image = image.clip(0, 1)

    return image

fig=plt.figure(figsize=(20, 12))
columns = 4
rows = 2

dataiter = iter(dataloaders['valid'])
inputs, classes = dataiter.next()

for idx in range (columns*rows):
    ax = fig.add_subplot(rows, columns, idx+1, xticks=[], yticks=[])
    ax.set_title(cat_to_name[str(int(class_names[classes[idx]]))])
    plt.imshow(im_convert(inputs[idx]))
plt.show()

加载models中提供的模型，并且直接用训练好的权重参数当作初始参数

model_name = 'resnet'  #可选的比较多 ['resnet', 'alexnet', 'vgg', 'squeezenet', 'densenet', 'inception']
#是否用人家训练好的特征来做
feature_extract = True 

# 是否用GPU训练
train_on_gpu = torch.cuda.is_available()

if not train_on_gpu:
    print('CUDA is not available.  Training on CPU ...')
else:
    print('CUDA is available!  Training on GPU ...')
    
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

def set_parameter_requires_grad(model, feature_extracting):
    if feature_extracting:
        for param in model.parameters():
            param.requires_grad = False
         

model_ft = models.resnet152()
model_ft

参考pytorch官网例子

def initialize_model(model_name, num_classes, feature_extract, use_pretrained=True):
    # 选择合适的模型，不同模型的初始化方法稍微有点区别
    model_ft = None
    input_size = 0

    if model_name == "resnet":
        """ Resnet152
        """
        model_ft = models.resnet152(pretrained=use_pretrained)
        set_parameter_requires_grad(model_ft, feature_extract)
        num_ftrs = model_ft.fc.in_features
        model_ft.fc = nn.Sequential(nn.Linear(num_ftrs, 102),
                                   nn.LogSoftmax(dim=1))
        input_size = 224

    elif model_name == "alexnet":
        """ Alexnet
        """
        model_ft = models.alexnet(pretrained=use_pretrained)
        set_parameter_requires_grad(model_ft, feature_extract)
        num_ftrs = model_ft.classifier[6].in_features
        model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
        input_size = 224

    elif model_name == "vgg":
        """ VGG11_bn
        """
        model_ft = models.vgg16(pretrained=use_pretrained)
        set_parameter_requires_grad(model_ft, feature_extract)
        num_ftrs = model_ft.classifier[6].in_features
        model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
        input_size = 224

    elif model_name == "squeezenet":
        """ Squeezenet
        """
        model_ft = models.squeezenet1_0(pretrained=use_pretrained)
        set_parameter_requires_grad(model_ft, feature_extract)
        model_ft.classifier[1] = nn.Conv2d(512, num_classes, kernel_size=(1,1), stride=(1,1))
        model_ft.num_classes = num_classes
        input_size = 224

    elif model_name == "densenet":
        """ Densenet
        """
        model_ft = models.densenet121(pretrained=use_pretrained)
        set_parameter_requires_grad(model_ft, feature_extract)
        num_ftrs = model_ft.classifier.in_features
        model_ft.classifier = nn.Linear(num_ftrs, num_classes)
        input_size = 224

    elif model_name == "inception":
        """ Inception v3
        Be careful, expects (299,299) sized images and has auxiliary output
        """
        model_ft = models.inception_v3(pretrained=use_pretrained)
        set_parameter_requires_grad(model_ft, feature_extract)
        # Handle the auxilary net
        num_ftrs = model_ft.AuxLogits.fc.in_features
        model_ft.AuxLogits.fc = nn.Linear(num_ftrs, num_classes)
        # Handle the primary net
        num_ftrs = model_ft.fc.in_features
        model_ft.fc = nn.Linear(num_ftrs,num_classes)
        input_size = 299

    else:
        print("Invalid model name, exiting...")
        exit()

    return model_ft, input_size

1、设置哪些层需要训练

model_ft, input_size = initialize_model(model_name, 102, feature_extract, use_pretrained=True)

#GPU计算
model_ft = model_ft.to(device)

# 模型保存
filename='checkpoint.pth'

# 是否训练所有层
params_to_update = model_ft.parameters()
print("Params to learn:")
if feature_extract:
    params_to_update = []
    for name,param in model_ft.named_parameters():
        if param.requires_grad == True:
            params_to_update.append(param)
            print("\t",name)
else:
    for name,param in model_ft.named_parameters():
        if param.requires_grad == True:
            print("\t",name)

model_ft

2、优化器设置

# 优化器设置
optimizer_ft = optim.Adam(params_to_update, lr=1e-2)
scheduler = optim.lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)#学习率每7个epoch衰减成原来的1/10
#最后一层已经LogSoftmax()了，所以不能nn.CrossEntropyLoss()来计算了，nn.CrossEntropyLoss()相当于logSoftmax()和nn.NLLLoss()整合
criterion = nn.NLLLoss()

3、训练模块

def train_model(model, dataloaders, criterion, optimizer, num_epochs=25, is_inception=False,filename=filename):
    since = time.time()
    best_acc = 0
    """
    checkpoint = torch.load(filename)
    best_acc = checkpoint['best_acc']
    model.load_state_dict(checkpoint['state_dict'])
    optimizer.load_state_dict(checkpoint['optimizer'])
    model.class_to_idx = checkpoint['mapping']
    """
    model.to(device)

    val_acc_history = []
    train_acc_history = []
    train_losses = []
    valid_losses = []
    LRs = [optimizer.param_groups[0]['lr']]

    best_model_wts = copy.deepcopy(model.state_dict())

    for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)

        # 训练和验证
        for phase in ['train', 'valid']:
            if phase == 'train':
                model.train()  # 训练
            else:
                model.eval()   # 验证

            running_loss = 0.0
            running_corrects = 0

            # 把数据都取个遍
            for inputs, labels in dataloaders[phase]:
                inputs = inputs.to(device)
                labels = labels.to(device)

                # 清零
                optimizer.zero_grad()
                # 只有训练的时候计算和更新梯度
                with torch.set_grad_enabled(phase == 'train'):
                    if is_inception and phase == 'train':
                        outputs, aux_outputs = model(inputs)
                        loss1 = criterion(outputs, labels)
                        loss2 = criterion(aux_outputs, labels)
                        loss = loss1 + 0.4*loss2
                    else:#resnet执行的是这里
                        outputs = model(inputs)
                        loss = criterion(outputs, labels)

                    _, preds = torch.max(outputs, 1)

                    # 训练阶段更新权重
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()

                # 计算损失
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)
                
            epoch_loss = running_loss / len(dataloaders[phase].dataset)
            epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)
            
            
            time_elapsed = time.time() - since
            print('Time elapsed {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
            print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))
            

            # 得到最好那次的模型
            if phase == 'valid' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())
                state = {
                  'state_dict': model.state_dict(),
                  'best_acc': best_acc,
                  'optimizer' : optimizer.state_dict(),
                }
                torch.save(state, filename)
            if phase == 'valid':
                val_acc_history.append(epoch_acc)
                valid_losses.append(epoch_loss)
                scheduler.step(epoch_loss)
            if phase == 'train':
                train_acc_history.append(epoch_acc)
                train_losses.append(epoch_loss)
        
        print('Optimizer learning rate : {:.7f}'.format(optimizer.param_groups[0]['lr']))
        LRs.append(optimizer.param_groups[0]['lr'])
        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))

    # 训练完后用最好的一次当做模型最终的结果
    model.load_state_dict(best_model_wts)
    return model, val_acc_history, train_acc_history, valid_losses, train_losses, LRs 

4、开始训练

train_acc_history, valid_losses, train_losses, LRs  = train_model(model_ft, dataloaders, criter

5、在继续训练所有的层

for param in model_ft.parameters():
    param.requires_grad = True

# 再继续训练所有的参数，学习率调小一点
optimizer = optim.Adam(params_to_update, lr=1e-4)
scheduler = optim.lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)

# 损失函数
criterion = nn.NLLLoss()

# Load the checkpoint

checkpoint = torch.load(filename)
best_acc = checkpoint['best_acc']
model_ft.load_state_dict(checkpoint['state_dict'])
optimizer.load_state_dict(checkpoint['optimizer'])
#model_ft.class_to_idx = checkpoint['mapping']

model_ft, val_acc_history, train_acc_history, valid_losses, train_losses, LRs  = train_model(model_ft, dataloaders, criterion, optimizer, num_epochs=10, is_inception=(model_name=="inception"))

6、加载训练好的模型

model_ft, input_size = initialize_model(model_name, 102, feature_extrace, use_pretrain=True)

model_ft = model_ft_to(device)

filename = 'seriouscheckpoint.pth'
# 加载模型
checkpoint = torch.load(filename)
best_acc = checkpoint['best_acc']
model_ft.load_state_dict(checkpoint['state_dict'])

测试数据预处理

1、测试数据需要和训练时的数据一致
2、crop操作目的是保证数据数据的尺寸是一致的 3、标准化的目的是和训练数据相同的mean和std,
需要注意的是训练数据实在0-1 上进行标准化的， 所以测试数据也需要进行归一化。
4、 pytorch中的颜色通道是在第一个维度，需要转换。

def process_image(image_path):
    # 读取测试数据
    img = Image.open(image_path)
    # Resize,thumbnail方法只能进行缩小，所以进行了判断
    if img.size[0] > img.size[1]:
        img.thumbnail((10000, 256))
    else:
        img.thumbnail((256, 10000))
    # Crop操作
    left_margin = (img.width-224)/2
    bottom_margin = (img.height-224)/2
    right_margin = left_margin + 224
    top_margin = bottom_margin + 224
    img = img.crop((left_margin, bottom_margin, right_margin,   
                      top_margin))
    # 相同的预处理方法
    img = np.array(img)/255
    mean = np.array([0.485, 0.456, 0.406]) #provided mean
    std = np.array([0.229, 0.224, 0.225]) #provided std
    img = (img - mean)/std
    
    # 注意颜色通道应该放在第一个位置
    img = img.transpose((2, 0, 1))
    
    return img

def imshow(image, ax=None, title=None):
    """展示数据"""
    if ax is None:
        fig, ax = plt.subplots()
    
    # 颜色通道还原
    image = np.array(image).transpose((1, 2, 0))
    
    # 预处理还原
    mean = np.array([0.485, 0.456, 0.406])
    std = np.array([0.229, 0.224, 0.225])
    image = std * image + mean
    image = np.clip(image, 0, 1)
    
    ax.imshow(image)
    ax.set_title(title)
    
    return ax

image_path = 'image_06621.jpg'
img = process_image(image_path)
imshow(img)

# 得到一个batch的测试数据
dataiter = iter(dataloaders['valid'])
images, labels = dataiter.next()

model_ft.eval()

if train_on_gpu:
    output = model_ft(images.cuda())
else:
    output = model_ft(images)

_, preds_tensor = torch.max(output, 1)

preds = np.squeeze(preds_tensor.numpy()) if not train_on_gpu else np.squeeze(preds_tensor.cpu().numpy())
preds

展示预测结果

fig=plt.figure(figsize=(20, 20))
columns =4
rows = 2

for idx in range (columns*rows):
    ax = fig.add_subplot(rows, columns, idx+1, xticks=[], yticks=[])
    plt.imshow(im_convert(images[idx]))
    ax.set_title("{} ({})".format(cat_to_name[str(preds[idx])], cat_to_name[str(labels[idx].item())]),
                 color=("green" if cat_to_name[str(preds[idx])]==cat_to_name[str(labels[idx].item())] else "red"))
plt.show()