图像识别模块解读
1.首先进行的图像预处理

data_transforms = {
    'train': transforms.Compose([transforms.RandomRotation(45),#随机旋转，-45到45度之间随机选
        transforms.CenterCrop(224),#对图片做裁剪
        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),#防止数据过大，
        transforms.CenterCrop(224),#为了图片格式一致
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])#预处理的方式应该是一样的
    ]),
}

对参数的详细解析：
transforms.RandomRotation(45)
transforms.RandomRotation(45) 是一个图像变换操作，它可以随机旋转图像。参数 45 表示旋转的角度范围为 -45 到 45 度之间的任意角度。当应用该变换操作时，每次旋转的角度将在这个范围内随机选择。这种随机性可以增加数据的多样性，提高模型的鲁棒性。
RandomVerticalFlip(p=0.5)是一种数据增强技术，用于图像处理中的数据增强。它的作用是以一定的概率p对图像进行垂直翻转，从而增加训练数据的多样性。
ColorJitter是PyTorch中的一种数据增强技术，用于在训练过程中对图像进行随机颜色变换。它可以改变图像的亮度、对比度、饱和度和色调。
transforms.RandomGrayscale(p=0.025),#概率转换成灰度率，3通道就是R=G=B
transforms.ToTensor()转换成张量。
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])#均值，标准差

image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'valid']}

datasets.ImageFolder函数会自动将data_dir目录下的子目录作为不同的类别，并将每个子目录中的图像文件加载为对应类别的样本。同时，通过data_transforms[x]可以对图像数据进行预处理操作，例如缩放、裁剪、旋转等。
使用Dataloader加载数据

dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=batch_size, shuffle=True) for x in ['train', 'valid']}

读取放入的类别

class_names = image_datasets['train'].classes

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

上述代码的作用是将tensor类型的图片数据恢复成image。

dataiter = iter(dataloaders['valid'])
inputs, classes = dataiter.next()
print("classname:",class_names)

for idx in range(0,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()

上述代码的作用是取出一个batch中的图像取出，显示出来对应的类别和图像。
2.对数据进行进行的处理和测试之后，开始进行模型的选定。
使用残差网络进行模型的训练，使用gpu进行训练。
2.1在使用模型的同时，我们也在使用人家的参数，更新参数只更新最后一层的全连接层。代码设置如下：

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，使用人家训练好的特征来做
feature_extract = True

#选定特定的gpu进行训练
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)
#参数不要求变动，直接利用别的参数
def set_parameter_requires_grad(model, feature_extracting):
    if feature_extracting:
        for param in model.parameters():
            param.requires_grad = False

接下来实例化我们要使用的模型Resnet152（）。
初始化模型，这里使用了官网给出的使用模板。模板如下。

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
        """
        #加载模型

        model_ft = models.resnet152(pretrained=use_pretrained)
        set_parameter_requires_grad(model_ft, feature_extract)
        #最后的得到的参数
        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

这里解析一下要求改的部分。因为我们最终的输出层数和我们要使用的模型的输出不一样，所以我们要对最后输出的模型进行修改。
我们进行模型的初始化

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

确定训练要使用的设备

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

可以指定要存放训练好的模型的文件名，这里指定，训练完成的模型的保存为checkpoint.pth

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)

上述代码的作用是根据设置的是否使用人家训练好的参数，是否进行反向传播。将需要修改参数的参数放入到params_to_update列表中。
将需要进行训练的参数放入到优化器中，方便进行优化。设置优化器代码如下。

optimizer_ft = optim.Adam(params_to_update, lr=1e-2)

设置完成优化器之后，开始进行随时函数的设置，代码如下：

criterion = nn.NLLLoss()

设置训练函数

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 = []
    #存放学习过程中的学习率的变化
    LRs = [optimizer.param_groups[0]['lr']]
    # 将参数进行了保存
    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,设置了阶段
                with torch.set_grad_enabled(phase == 'train'):
                    #这个不会执行，参考的官网，考虑的因素比较多
                    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

修改为训练模型中所有的参数，不使用人家训练好的参数。

# 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()
# 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"))

加载模型进行预测测试
filename=‘checkpoint.pth’

加载模型

checkpoint = torch.load(filename)
best_acc = checkpoint['best_acc']
model_ft.load_state_dict(checkpoint['state_dict'])



#测试的数据要和训练的数据的格式一样
#测试的数据要和训练的数据的格式一样
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
dataiter = iter(dataloaders['valid'])
images, labels = dataiter.next()

model_ft.eval()
train_on_gpu = torch.cuda.is_available()
if train_on_gpu:
    output = model_ft(images.cuda())
else:
    output = model_ft(images)
_, preds_tensor = torch.max(output, 1)#选择概率值最大的一个
fig=plt.figure(figsize=(20, 20))
columns =4
rows = 2
preds = np.squeeze(preds_tensor.numpy()) if not train_on_gpu else np.squeeze(preds_tensor.cpu().numpy())
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()