Pytorch框架实战——102类花卉分类

本篇博文为【唐宇迪】计算机视觉实训营第二天-Pytorch框架实战课程的个人笔记。
代码来自：qiuzitao深度学习之PyTorch实战（十），与视频教学流程记录一致，课程详情可参考该篇。
下文数据集及对应json文件：
链接：https://pan.baidu.com/s/14MO6dP_Zax-DlUFfs-NLww 提取码：j11h

数据可视化

import matplotlib.pyplot as plt
import numpy as np
import torch
from torchvision import transforms, models, datasets
import os
import json

#数据集位置
data_dir = './flower_data/'

#数据增强操作
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，留下224*224的。（随机裁剪得到的数据更多）
        transforms.RandomHorizontalFlip(p=0.5),#随机水平翻转 选择一个概率去翻转，0.5就是50%翻转，50%不翻转
        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(),  #转成tensor的格式
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])#均值，标准差（拿人家算好的）
    ]),
    '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]) #要和训练集保持一致的标准化操作
    ]),
}

batch_size = 16

#制作数据（传入数据集，并作数据增强操作）
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'valid']}
#将数据集按batch制作成一个数据包
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=batch_size, shuffle=True) for x in ['train', 'valid']}
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))  # 还原回去
    image = image.clip(0, 1)
    return image

# 生成画布
fig=plt.figure(figsize=(20, 12))
# 这里batch=16所以用4x4的布局
columns = 4
rows = 4

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

print('classes',classes)

# 数据集标签名的索引（可有可无，个人觉得按照文件夹名来看反而容易查看是否识别正确，如果需要做项目任务，可自行补充上）
with open('cat_to_name.json', 'r') as f:
    cat_to_name = json.load(f)
#print('cat_to_name',cat_to_name)

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]]))])
    ax.set_title("{} ({})".format(str(int(class_names[classes[idx]])), cat_to_name[str(int(class_names[classes[idx]]))]))
    # ax.set_title(str(int(class_names[classes[idx]])))
    plt.imshow(im_convert(inputs[idx]))
plt.show()

输出：（前面是文件夹名，后面是索引到的花的名字，可以查看下是否正确对应所属文件夹，因为我在做的过程中，test测试时显示的类名与所属文件夹对不上，这是文件索引问题，后面的代码稍微改了改索引）

train

下面代码将不进行可视化，直接就是训练的代码。

import os
import torch
from torch import nn
import torch.optim as optim
from torchvision import transforms, models, datasets
# https://pytorch.org/docs/stable/torchvision/index.html  #模块的官方网址，上面例子有教你怎么用
import time
import copy


data_dir = './flower_data/'

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，留下224*224的。（随机裁剪得到的数据更多）
        transforms.RandomHorizontalFlip(p=0.5),#随机水平翻转 选择一个概率去翻转，0.5就是50%翻转，50%不翻转
        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(),  #转成tensor的格式
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])#均值，标准差（拿人家算好的）
    ]),
    '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]) #要和训练集保持一致的标准化操作
    ]),
}

# 自定义batch大小
batch_size = 64

#制作数据（传入数据集，并作数据增强操作）
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'valid']}
#将数据集按batch制作成一个数据包
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=batch_size, shuffle=True) for x in ['train', 'valid']}
class_names = image_datasets['train'].classes

# print('image_datasets',image_datasets)
# print('dataloaders',dataloaders)
# print('dataset_sizes',dataset_sizes)
# print('class_names',class_names)


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")

# 定义该层是否需要训练
# 在数据量小的情况可以采用将前面的网络层冻结，只训练后面fc层。
def set_parameter_requires_grad(model, feature_extracting):
    if feature_extracting:
        for param in model.parameters():
            #如需训练改为True
            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

#改成我们要训练的102类
model_ft, input_size = initialize_model(model_name, 102, feature_extract, use_pretrained=True)
#GPU计算
model_ft = model_ft.to(device)

# 模型保存的文件名（需要保存到别的路径可接着加）
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)

# 查看模型具体框架信息
print('model_ft',model_ft)


# 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()


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)  # 用GPU训练

    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)  # 将input传入GPU计算
                labels = labels.to(device)  # 将labels传入GPU计算

                # 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

model_ft,val_acc_history, train_acc_history, valid_losses, train_losses, LRs = train_model(model_ft,\
                                                                                           dataloaders,\
                                                                                           criterion,\
                                                                                           optimizer_ft,\
                                                                                           num_epochs=20, \
                                                                                           is_inception=(model_name=="inception"))

训练完生成模型权重文件：

test

利用上面训好的模型进行测试：

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    #如果你的电脑没有安装torchvision模块就得去用这个指令安装
from torchvision import transforms, models, datasets
# https://pytorch.org/docs/stable/torchvision/index.html  #模块的官方网址，上面例子有教你怎么用
import imageio
import time
import warnings
import random
import sys
import copy
import json
from PIL import Image

data_dir = './flower_data/'

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，留下224*224的。（随机裁剪得到的数据更多）
        transforms.RandomHorizontalFlip(p=0.5),#随机水平翻转 选择一个概率去翻转，0.5就是50%翻转，50%不翻转
        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(),  #转成tensor的格式
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])#均值，标准差（拿人家算好的）
    ]),
    '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]) #要和训练集保持一致的标准化操作
    ]),
}

batch_size = 16

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']}
class_names = image_datasets['train'].classes

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

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


# 是否用GPU
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

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

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


# GPU模式
model_ft = model_ft.to(device)

# 加载模型文件
filename='checkpoint.pth'

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


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

model_ft.eval()

if train_on_gpu:
    output = model_ft(images.cuda())
else:
    output = model_ft(images)
# print('output.shape',output.shape)

#预测的最优值
_, preds_tensor = torch.max(output, 1)

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

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

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))  # 还原回去
    image = image.clip(0, 1)
    return image

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

测试结果将存入1.png：

做别的分类任务：