Pytorch学习--图像识别花种类实战（Resnet网络）

 未解决问题：

1.训练和验证的数据不知如何获取分类

2.尝试换一网络模型和数据集，以及迭代次数等参数

 1. 数据处理部分

        1.1数据增强：torchvision中transform模

        数据预处理：Dataloader模块直接读取batch数据

     

# 基于经典网络架构训练图像分类模型
import os
import matplotlib.pyplot as plt
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


#第一步：数据的读取和预处理操作
data_dir = r'C:\Users\Chen\Desktop\看完的视频\PyTorch框架实战\卷积网络实战\flower_data'
train_dir = data_dir + '/train'
valid_dir = data_dir + '/valid'

   1.2: 制作数据源和数据增强 

# data_transforms中指定了所有图像预处理操作

# 文件夹的名字为分类的名字

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  和别人的相同使得处理效果更好
    ]),
    '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])   #要和训练集相同
    ]),}

第三步：batch数据的处理

# ImageFolder假设所有的文件按文件夹保存好，每个文件夹下面存贮同一类别的图片 

batch_size = 2   #这里设置的较小，方面训练

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']}    #总共数据的大小
class_names = image_datasets['train'].classes
#打印image_datasets
#image_datasets
#展示数据：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

2.网络模块设置

迁移学习：用别人的网络和权重来初始化

出现的问题：PytorchStreamReader failed reading zip archive: failed finding central directory

                    这是由于下载resnet152时，网络下载没有完整,

 解决办法：重新下载：找到. C:\Users\Chen/.cache\torch\hub\checkpoints\resnet152-                                       394f9c45.pth 删除相关   PHT文件

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")


model_ft = models.resnet152()
# model_ft

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


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

2.1设置训练的层数

2.2 配置优化器：大多数优化器选择Adim，SGD用的比较少

 

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)

###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   学习率会自动衰减
#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()     

进行数据的训练 

###训练操作
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']]  #学习率

    best_model_wts = copy.deepcopy(model.state_dict())   #将最好的权重存储

    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 

开始训练

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

 

3.网络模型保存与测试

• 模型保存的时候可以带有选择性，例如在验证集中如果当前效果好则保存
• 读取模型进行实际测试

3.1测试网络的效果

#输入一张测试图像，看看网络的返回结果：

probs, classes = predict(image_path, model)
print(probs)
print(classes)
> [ 0.01558163  0.01541934  0.01452626  0.01443549  0.01407339]
> ['70', '3', '45', '62', '55']

3.2加载训练好模型

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

# GPU模式
model_ft = model_ft.to(device)

# 保存文件的名字
filename='seriouscheckpoint.pth'

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

3.3测试数据预处理

• 测试数据处理方法需要跟训练时一直才可以
• crop操作的目的是保证输入的大小是一致的
• 标准化操作也是必须的，用跟训练数据相同的mean和std,但是需要注意一点训练数据是在0-1上进行标准化，所以测试数据也需要先归一化
• PyTorch中颜色通道是第一个维度，跟很多工具包都不一样，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))       #C W H
    
    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)
img.shape

# 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)


output.shape   #output表示对一个batch中每一个数据得到其属于各个类别的可能性

 3.4预测结果

'''得到概率最大的结果'''
_, 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

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()