深度学习工具

自创数据集（img）

在当前目录下新建dataset，并在文件夹中，将图片分类在各自文件夹中，文件夹名为标签名

import os
import random

# 选取60%作为训练数据集
train_radio = 0.6
text_radio = 1 - train_radio

root_data = r'dataset'

train_list, test_list = [], []
data_list = []

class_flag = -1
for a, b, c in os.walk(root_data):
    print(a)
    for i in range(len(c)):
        data_list.append(os.path.join(a, c[i]))

    for i in range(0, int(len(c) * train_radio)):
        train_data = os.path.join(a, c[i]) + '\t' + str(class_flag) + '\n'
        train_list.append(train_data)

    for i in range(int(len(c) * train_radio), len(c)):
        test_data = os.path.join(a, c[i]) + '\t' + str(class_flag) + '\n'
        test_list.append(test_data)

    class_flag += 1

print(train_list)
# 将列表中元素顺序随机打乱
random.shuffle(train_list)
random.shuffle(test_list)

with open('train.txt', 'w', encoding='utf-8') as f:
    for train_img in train_list:
        f.write(str(train_img))

with open('text.txt', 'w', encoding='utf-8') as f:
    for test_img in test_list:
        f.write(test_img)

会在当前目录下，生成train.txt、test.txt，在会随机给不同的类分一个数字作为标签

前面的图片路径为输入的x、后面的数字为标签y

转换为DataLoader

将自己的数据集转换为torch可接受的DataLoader，CreateDateloader.py

import torch
from PIL import Image

import torchvision.transforms as transforms
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True

from torch.utils.data import Dataset

# 数据归一化与标准化

# 图像标准化
transform_BZ= transforms.Normalize(
    mean=[0.5, 0.5, 0.5],# 取决于数据集
    std=[0.5, 0.5, 0.5]
)


class LoadData(Dataset):
    def __init__(self, txt_path, train_flag=True):
        self.imgs_info = self.get_images(txt_path)
        self.train_flag = train_flag

        self.train_tf = transforms.Compose([
                transforms.Resize(224),
                transforms.RandomHorizontalFlip(),
                transforms.RandomVerticalFlip(),
                transforms.ToTensor(),
                transform_BZ
            ])
        self.val_tf = transforms.Compose([
                transforms.Resize(224),
                transforms.ToTensor(),
                transform_BZ
            ])

    def get_images(self, txt_path):
        with open(txt_path, 'r', encoding='utf-8') as f:
            imgs_info = f.readlines()
            imgs_info = list(map(lambda x:x.strip().split('\t'), imgs_info))
        return imgs_info

    def padding_black(self, img):
        w, h  = img.size
        scale = 224. / max(w, h)
        img_fg = img.resize([int(x) for x in [w * scale, h * scale]])
        size_fg = img_fg.size
        size_bg = 224
        img_bg = Image.new("RGB", (size_bg, size_bg))
        img_bg.paste(img_fg, ((size_bg - size_fg[0]) // 2,
                              (size_bg - size_fg[1]) // 2))
        img = img_bg
        return img

    def __getitem__(self, index):
        img_path, label = self.imgs_info[index]
        img = Image.open(img_path)
        img = img.convert('RGB')
        img = self.padding_black(img)
        if self.train_flag:
            img = self.train_tf(img)
        else:
            img = self.val_tf(img)
        label = int(label)

        return img, label

    def __len__(self):
        return len(self.imgs_info)


if __name__ == "__main__":
    train_dataset = LoadData("train.txt", True)
    print("数据个数：", len(train_dataset))
    train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                               batch_size=10,
                                               shuffle=True)
    for image, label in train_loader:
        print(image.shape)
        print(image)
        # img = transform_BZ(image)
        # print(img)
        print(label)

    # test_dataset = Data_Loader("test.txt", False)
    # print("数据个数：", len(test_dataset))
    # test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
    #                                            batch_size=10,
    #                                            shuffle=True)
    # for image, label in test_loader:
    #     print(image.shape)
    #     print(label)

运行的结果为数据个数，以及每张图片的张量

开始定义模型

import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor, Lambda, Compose
import matplotlib.pyplot as plt
from CreateDataloader import LoadData


# 采用torchvision里面的datasets里面的FashionMNIST数据集，该数据集在第一次用时需要下载，
# 数据集分为训练集（用于模型训练）和测试集（验证模型性能）
# 下面是训练集
# training_data = datasets.FashionMNIST(  # FashionMNIST
#     root="data",
#     train=True,
#     download=True,
#     transform=ToTensor(),   # 数据预处理
# )
#
# # 下面是测试集，同样需要下载
# test_data = datasets.FashionMNIST(
#     root="data",
#     train=False,
#     download=True,
#     transform=ToTensor(),
# )

#


# 定义网络模型
class NeuralNetwork(nn.Module):
    def __init__(self):
        super(NeuralNetwork, self).__init__()
        # 碾平，将数据碾平为一维
        self.flatten = nn.Flatten()
        # 定义linear_relu_stack，由以下众多层构成
        self.linear_relu_stack = nn.Sequential(
            # 全连接层
            nn.Linear(3*224*224, 512),
            # ReLU激活函数
            nn.ReLU(),
            # 全连接层
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, 6),
            nn.ReLU()
        )
    # x为传入数据
    def forward(self, x):
        # x先经过碾平变为1维
        x = self.flatten(x)
        # 随后x经过linear_relu_stack
        logits = self.linear_relu_stack(x)
        # 输出logits
        return logits



# 定义训练函数，需要
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    # 从数据加载器中读取batch（一次读取多少张，即批次数），X(图片数据)，y（图片真实标签）。
    for batch, (X, y) in enumerate(dataloader):
        # 将数据存到显卡
        X, y = X.cuda(), y.cuda()

        # 得到预测的结果pred
        pred = model(X)

        # 计算预测的误差
        # print(pred,y)
        loss = loss_fn(pred, y)

        # 反向传播，更新模型参数
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        # 每训练100次，输出一次当前信息
        if batch % 100 == 0:
            loss, current = loss.item(), batch * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")


def test(dataloader, model):
    size = len(dataloader.dataset)
    print("size = ",size)
    # 将模型转为验证模式
    model.eval()
    # 初始化test_loss 和 correct， 用来统计每次的误差
    test_loss, correct = 0, 0
    # 测试时模型参数不用更新，所以no_gard()
    # 非训练， 推理期用到
    with torch.no_grad():
        # 加载数据加载器，得到里面的X（图片数据）和y(真实标签）
        for X, y in dataloader:
            # 将数据转到GPU
            X, y = X.cuda(), y.cuda()
            # 将图片传入到模型当中就，得到预测的值pred
            pred = model(X)
            # 计算预测值pred和真实值y的差距
            test_loss += loss_fn(pred, y).item()
            # 统计预测正确的个数
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()
    test_loss /= size
    correct /= size
    print("correct = ",correct)
    print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")



if __name__=='__main__':
    batch_size = 16

    # # 给训练集和测试集分别创建一个数据集加载器
    train_data = LoadData("train.txt", True)
    valid_data = LoadData("test.txt", False)

    # num_workers：cpu用来加载数据的子进程数  pin_memory：是否将数据保存在pin memory区，pin memory中的数据转到GPU会快一些
    train_dataloader = DataLoader(dataset=train_data, num_workers=4, pin_memory=True, batch_size=batch_size, shuffle=True)
    test_dataloader = DataLoader(dataset=valid_data, num_workers=4, pin_memory=True, batch_size=batch_size)

    for X, y in test_dataloader:
        print("Shape of X [N, C, H, W]: ", X.shape)
        print("Shape of y: ", y.shape, y.dtype)
        break


    # 如果显卡可用，则用显卡进行训练
    device = "cuda" if torch.cuda.is_available() else "cpu"
    print("Using {} device".format(device))

    # 调用刚定义的模型，将模型转到GPU（如果可用）
    model = NeuralNetwork().to(device)

    print(model)

    # 定义损失函数，计算相差多少，交叉熵，
    loss_fn = nn.CrossEntropyLoss()

    # 定义优化器，用来训练时候优化模型参数，随机梯度下降法
    optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)  # 初始学习率


    # 一共训练5次
    epochs = 5
    for t in range(epochs):
        print(f"Epoch {t+1}\n-------------------------------")
        train(train_dataloader, model, loss_fn, optimizer)
        test(test_dataloader, model)
    print("Done!")

    # 保存训练好的模型
    # torch.save(model.state_dict(), "model.pth")
    # print("Saved PyTorch Model State to model.pth")



    # 读取训练好的模型，加载训练好的参数
    model = NeuralNetwork()
    model.load_state_dict(torch.load("model.pth"))


    # # 定义所有类别
    # classes = [
    #     "T-shirt/top",
    #     "Trouser",
    #     "Pullover",
    #     "Dress",
    #     "Coat",
    #     "Sandal",
    #     "Shirt",
    #     "Sneaker",
    #     "Bag",
    #     "Ankle boot",
    # ]
    #
    # # 模型进入验证阶段
    # model.eval()
    #
    # x, y = test_data[0][0], test_data[0][1]
    # with torch.no_grad():
    #     pred = model(x)
    #     predicted, actual = classes[pred[0].argmax(0)], classes[y]
    #     print(f'Predicted: "{predicted}", Actual: "{actual}"')