ResNet50的猫狗分类训练及预测

相比于之前写的ResNet18，下面的ResNet50写得更加工程化一点，这还适用与其他分类。

我的代码文件结构

　　

1. 数据处理

　　首先已经对数据做好了分类

　　

　　文件夹结构是这样

　　开始划分数据集

　　split_data.py

import os

import random

import shutil

def move_file(target_path, save_train_path, save_val_pathm, scale=0.1):

    file_list = os.listdir(target_path)

    random.shuffle(file_list)

    number = int(len(file_list) * scale)

    train_list = file_list[number:]

    val_list = file_list[:number]

    for file in train_list:

        target_file_path = os.path.join(target_path, file)

        save_file_path = os.path.join(save_train_path, file)

        shutil.copyfile(target_file_path, save_file_path)

    for file in val_list:

        target_file_path = os.path.join(target_path, file)

        save_file_path = os.path.join(save_val_pathm, file)

        shutil.copyfile(target_file_path, save_file_path)

def split_classify_data(base_path, save_path, scale=0.1):

    folder_list = os.listdir(base_path)

    for folder in folder_list:

        target_path = os.path.join(base_path, folder)

        save_train_path = os.path.join(save_path, 'train', folder)

        save_val_path = os.path.join(save_path, 'val', folder)

        if not os.path.exists(save_train_path):

            os.makedirs(save_train_path)

        if not os.path.exists(save_val_path):

            os.makedirs(save_val_path)

        move_file(target_path, save_train_path, save_val_path, scale)

        print(folder, 'finish!')

if __name__ == '__main__':

    base_path = r'C:\Users\Administrator.DESKTOP-161KJQD\Desktop\save_dir'

    save_path = r'C:\Users\Administrator.DESKTOP-161KJQD\Desktop\dog_cat'

    # 验证集比例

    scale = 0.1

    split_classify_data(base_path, save_path, scale)

　　运行完以上代码的到的文件夹结构

　　　　

　　一个训练集数据，一个验证集数据

　　

2.数据集的导入

　　我这个文件写了一个数据集的导入和一个学习率更新的函数。数据导入是通用的

　　tools.py

import os

import time

import cv2

import numpy as np

import torch

import torch.nn as nn

import torch.nn.functional as F

import torch.optim as optim

import torchvision

from torch.autograd.variable import Variable

from torch.utils.tensorboard import SummaryWriter

from torchvision import datasets, transforms

from torch.utils.data import Dataset, DataLoader

from torch.optim.lr_scheduler import ExponentialLR, LambdaLR

from torchvision.models import ResNet50_Weights

from tqdm import tqdm

from classify_cfg import *

mean = MEAN

std = STD

def get_dataset(base_dir='', input_size=160):

    dateset = dict()

    transform_train = transforms.Compose([

        # 分辨率重置为input_size

        transforms.Resize(input_size),

        transforms.RandomRotation(15),

        # 对加载的图像作归一化处理， 并裁剪为[input_sizexinput_sizex3]大小的图像(因为这图片像素不一致直接统一)

        transforms.CenterCrop(input_size),

        transforms.ToTensor(),

        transforms.Normalize(mean=mean, std=std)

    ])

    transform_val = transforms.Compose([

        transforms.Resize(input_size),

        transforms.RandomRotation(15),

        transforms.CenterCrop(input_size),

        transforms.ToTensor(),

        transforms.Normalize(mean=mean, std=std)

    ])

    base_dir_train = os.path.join(base_dir, 'train')

    train_dataset = datasets.ImageFolder(root=base_dir_train, transform=transform_train)

    # print("train_dataset=" + repr(train_dataset[1][0].size()))

    # print("train_dataset.class_to_idx=" + repr(train_dataset.class_to_idx))

    # print(train_dataset.classes)

    classes = train_dataset.classes

    # classes = train_dataset.class_to_idx

    classes_num = len(train_dataset.classes)

    base_dir_val = os.path.join(base_dir, 'val')

    val_dataset = datasets.ImageFolder(root=base_dir_val, transform=transform_val)

    dateset['train'] = train_dataset

    dateset['val'] = val_dataset

    return dateset, classes, classes_num

def update_lr(epoch, epochs):

    """

    假设开始的学习率lr是0.001，训练次数epochs是100

    当epoch<33时是lr * 1

    当33<=epoch<=66 时是lr * 0.5

    当66<epoch时是lr * 0.1

    """

    if epoch == 0 or epochs // 3 > epoch:

        return 1

    elif (epochs // 3 * 2 >= epoch) and (epochs // 3 <= epoch):

        return 0.5

    else:

        return 0.1

3.训练模型

　　数据集导入好了以后，选择模型，选择优化器等等，然后开始训练。

　　mytrain.py

import os

import time

import cv2

import numpy as np

import torch

import torch.nn as nn

import torch.optim as optim

import torchvision

from torch.autograd.variable import Variable

from torch.utils.tensorboard import SummaryWriter

from torch.utils.data import Dataset, DataLoader

from torch.optim.lr_scheduler import ExponentialLR, LambdaLR

from torchvision.models import ResNet50_Weights

# from tqdm import tqdm

from classify_cfg import *

from tools import get_dataset, update_lr

def train(model, dateset, epochs, batch_size, device, optimizer, scheduler, criterion, save_path):

    train_loader = DataLoader(dateset.get('train'), batch_size=batch_size, shuffle=True)

    val_loader = DataLoader(dateset.get('val'), batch_size=batch_size, shuffle=True)

    # 保存为tensorboard文件

    write = SummaryWriter(save_path)

    # 训练过程写入txt

    f = open(os.path.join(save_path, 'log.txt'), 'w', encoding='utf-8')

    best_acc = 0

    for epoch in range(epochs):

        train_correct = 0.0

        model.train()

        sum_loss = 0.0

        accuracy = -1

        total_num = len(train_loader.dataset)

        # print(total_num, len(train_loader))

        # loop = tqdm(enumerate(train_loader), total=len(train_loader))

        batch_count = 0

        for batch_idx, (data, target) in enumerate(train_loader):

            start_time = time.time()

            data, target = Variable(data).to(device), Variable(target).to(device)

            output = model(data)

            loss = criterion(output, target)

            optimizer.zero_grad()

            loss.backward()

            optimizer.step()

            print_loss = loss.data.item()

            sum_loss += print_loss

            train_predict = torch.max(output.data, 1)[1]

            if torch.cuda.is_available():

                train_correct += (train_predict.cuda() == target.cuda()).sum()

            else:

                train_correct += (train_predict == target).sum()

            accuracy = (train_correct / total_num) * 100

            # loop.set_description(f'Epoch [{epoch+1}/{epochs}]')

            # loop.set_postfix(loss=loss.item(), acc='{:.3f}'.format(accuracy))

            batch_count += len(data)

            end_time = time.time()

            s = f'Epoch:[{epoch+1}/{epochs}] Batch:[{batch_count}/{total_num}] train_acc: {"{:.2f}".format(accuracy)} ' \

                f'train_loss: {"{:.3f}".format(loss.item())} time: {int((end_time-start_time)*1000)} ms'

            # print(f'Epoch:[{epoch+1}/{epochs}]', f'Batch:[{batch_count}/{total_num}]',

            #       'train_acc:', '{:.2f}'.format(accuracy), 'train_loss:', '{:.3f}'.format(loss.item()),

            #       'time:', f'{int((end_time-start_time)*1000)} ms')

            print(s)

            f.write(s+'\n')

        write.add_scalar('train_acc', accuracy, epoch)

        write.add_scalar('train_loss', loss.item(), epoch)

        # print(optimizer.param_groups[0]['lr'])

        scheduler.step()

        if best_acc < accuracy:

            best_acc = accuracy

            torch.save(model, os.path.join(save_path, 'best.pt'))

        if epoch+1 == epochs:

            torch.save(model, os.path.join(save_path, 'last.pt'))

        # 预测验证集

        # if (epoch+1) % 5 == 0 or epoch+1 == epochs:

        model.eval()

        test_loss = 0.0

        correct = 0.0

        total_num = len(val_loader.dataset)

        # print(total_num, len(val_loader))

        with torch.no_grad():

            for data, target in val_loader:

                data, target = Variable(data).to(device), Variable(target).to(device)

                output = model(data)

                loss = criterion(output, target)

                _, pred = torch.max(output.data, 1)

                if torch.cuda.is_available():

                    correct += torch.sum(pred.cuda() == target.cuda())

                else:

                    correct += torch.sum(pred == target)

                print_loss = loss.data.item()

                test_loss += print_loss

            acc = correct / total_num * 100

            avg_loss = test_loss / len(val_loader)

        s = f"val acc: {'{:.2f}'.format(acc)} val loss: {'{:.3f}'.format(avg_loss)}"

        # print('val acc: ', '{:.2f}'.format(acc), 'val loss: ', '{:.3f}'.format(avg_loss))

        print(s)

        f.write(s+'\n')

        write.add_scalar('val_acc', acc, epoch)

        write.add_scalar('val_loss', avg_loss, epoch)

        # loop.set_postfix(val_loss='{:.3f}'.format(avg_loss), val_acc='{:.3f}'.format(acc))

    f.close()

if __name__ == '__main__':

    device = DEVICE

    epochs = EPOCHS

    batch_size = BATCH_SIZE

    input_size = INPUT_SIZE

    lr = LR

    # ---------------------------训练-------------------------------------

    # 图片的路径

    base_dir = r'C:\Users\Administrator.DESKTOP-161KJQD\Desktop\dog_cat'

    # 保存的路径

    save_path = r'C:\Users\Administrator.DESKTOP-161KJQD\Desktop\dog_cat_save'

    dateset, classes, classes_num = get_dataset(base_dir, input_size=input_size)

    # model = torchvision.models.resnet50(pretrained=True)

    model = torchvision.models.resnet50(weights=ResNet50_Weights.IMAGENET1K_V1)

    num_ftrs = model.fc.in_features

    model.fc = nn.Linear(num_ftrs, classes_num)

    model.to(DEVICE)

    # # 损失函数,交叉熵损失函数

    criteon = nn.CrossEntropyLoss()

    # 选择优化器

    optimizer = optim.SGD(model.parameters(), lr=lr)

    # 学习率更新

    # scheduler = ExponentialLR(optimizer, gamma=0.9)

    scheduler = LambdaLR(optimizer, lr_lambda=lambda epoch: update_lr(epoch, epochs))

    # 开始训练

    train(model, dateset, epochs, batch_size, device, optimizer, scheduler, criteon, save_path)

    # 将label保存起来

    with open(os.path.join(save_path, 'labels.txt'), 'w', encoding='utf-8') as f:

        f.write(f'{classes_num} {classes}')

　　训练结束以后，在保存路径下会得到下面的文件

　　

　　最好的模型，最后一次的模型，标签的列表，训练的记录和tensorboard记录

　　在该路径下执行 tensorboard --logdir=.

　　

　　然后在浏览器打开给出的地址，即可看到数据训练过程的绘图

4.对图片进行预测

　　考虑对于用户来说，用户是在网页或者手机上上传一张图片进行预测，所以这边是采用二进制数据。

　　mypredict.py

　　

import cv2

import numpy as np

import torch

from classify_cfg import *

def img_process(img_betys, img_size, device):

    img_arry = np.asarray(bytearray(img_betys), dtype='uint8')

    # im0 = cv2.imread(img_betys)

    im0 = cv2.imdecode(img_arry, cv2.IMREAD_COLOR)

    image = cv2.resize(im0, (img_size, img_size))

    image = np.float32(image) / 255.0

    image[:, :, ] -= np.float32(mean)

    image[:, :, ] /= np.float32(std)

    image = image.transpose((2, 0, 1))

    im = torch.from_numpy(image).unsqueeze(0)

    im = im.to(device)

    return im

def predict(model_path, img, device):

    model = torch.load(model_path)

    model.to(device)

    model.eval()

    predicts = model(img)

    # print(predicts)

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

    pred = torch.squeeze(preds)

    # print(pred)

    return pred

if __name__ == '__main__':

    mean = MEAN

    std = STD

    device = DEVICE

    classes = ['狗', '猫']

    # # 预测

    model_path = r'C:\Users\Administrator.DESKTOP-161KJQD\Desktop\dog_cat_save\best.pt'

    img_path = r'C:\Users\Administrator.DESKTOP-161KJQD\Desktop\save_dir\狗\000000.jpg'

    with open(img_path, 'rb') as f:

        img_betys = f.read()

    img =img_process(img_betys, 160, device)

    # print(img.shape)

    # print(img)

    pred = predict(model_path, img, device)

    print(classes[int(pred)])

ResNet50的猫狗分类训练及预测的相关教程结束。