# 下載數(shù)據(jù)集
from torchvision import datasets, transforms

train_set = datasets.MNIST("data",train=True,download=True, transform=transforms.ToTensor(),)
test_set = datasets.MNIST("data",train=False,download=True, transform=transforms.ToTensor(),)

import os
import matplotlib.pyplot as plt
import torch
from PIL import Image
from torch import nn
from torch.nn import Conv2d, Linear, ReLU
from torch.nn import MaxPool2d
from torchvision import transforms
from torchvision.datasets import MNIST
from torch.utils.data import DataLoader


# Dataset:創(chuàng)建數(shù)據(jù)集的函數(shù)；__init__:初始化數(shù)據(jù)內(nèi)容和標(biāo)簽
# __geyitem:獲取數(shù)據(jù)內(nèi)容和標(biāo)簽
# __len__:獲取數(shù)據(jù)集大小
# daataloader:數(shù)據(jù)加載類，接受來自dataset已經(jīng)加載好的數(shù)據(jù)集
# torchbision:圖形庫，包含預(yù)訓(xùn)練模型，加載數(shù)據(jù)的函數(shù)、圖片變換，裁剪、旋轉(zhuǎn)等
# torchtext:處理文本的工具包，將不同類型的額文件轉(zhuǎn)換為datasets

# 預(yù)處理：將兩個(gè)步驟整合在一起
transform = transforms.Compose({
    transforms.ToTensor(),  # 將灰度圖片像素值（0~255）轉(zhuǎn)為Tensor（0~1），方便后續(xù)處理
    # transforms.Normalize((0.1307,),(0.3081)),    # 歸一化，均值0，方差1;mean:各通道的均值std：各通道的標(biāo)準(zhǔn)差inplace：是否原地操作
})

# 加載數(shù)據(jù)集
# 訓(xùn)練數(shù)據(jù)集
train_data = MNIST(root='./data', train=True, transform=transform, download=True)
train_loader = DataLoader(dataset=train_data, batch_size=64, shuffle=True)
# transform：指示加載的數(shù)據(jù)集應(yīng)用的數(shù)據(jù)預(yù)處理的規(guī)則，shuffle：洗牌，是否打亂輸入數(shù)據(jù)順序
# 測(cè)試數(shù)據(jù)集
test_data = MNIST(root="./data", train=False, transform=transform, download=True)
test_loader = DataLoader(dataset=test_data, batch_size=64, shuffle=True)

train_data_size = len(train_data)
test_data_size = len(test_data)
print("訓(xùn)練數(shù)據(jù)集的長(zhǎng)度：{}".format(train_data_size))
print("測(cè)試數(shù)據(jù)集的長(zhǎng)度：{}".format(test_data_size))

class MnistModel(nn.Module):
    def __init__(self):
        super(MnistModel, self).__init__()
        self.conv1 = Conv2d(in_channels=1, out_channels=10, kernel_size=5, stride=1, padding=0)
        self.maxpool1 = MaxPool2d(2)
        self.conv2 = Conv2d(in_channels=10, out_channels=20, kernel_size=5, stride=1, padding=0)
        self.maxpool2 = MaxPool2d(2)
        self.linear1 = Linear(320, 128)
        self.linear2 = Linear(128, 64)
        self.linear3 = Linear(64, 10)
        self.relu = ReLU()

    def forward(self, x):
        x = self.relu(self.maxpool1(self.conv1(x)))
        x = self.relu(self.maxpool2(self.conv2(x)))
        x = x.view(x.size(0), -1)
        x = self.linear1(x)
        x = self.linear2(x)
        x = self.linear3(x)

        return x

# 損失函數(shù)CrossentropyLoss
model = MnistModel()#實(shí)例化
criterion = nn.CrossEntropyLoss()   # 交叉熵?fù)p失，相當(dāng)于Softmax+Log+NllLoss
# 線性多分類模型Softmax,給出最終預(yù)測(cè)值對(duì)于10個(gè)類別出現(xiàn)的概率，Log:將乘法轉(zhuǎn)換為加法，減少計(jì)算量，保證函數(shù)的單調(diào)性
# NLLLoss:計(jì)算損失，此過程不需要手動(dòng)one-hot編碼，NLLLoss會(huì)自動(dòng)完成

# SGD，優(yōu)化器，梯度下降算法e
optimizer = torch.optim.SGD(model.parameters(), lr=0.14)#lr:學(xué)習(xí)率

# 模型訓(xùn)練
def train():
    # index = 0
    for index, data in enumerate(train_loader):#獲取訓(xùn)練數(shù)據(jù)以及對(duì)應(yīng)標(biāo)簽
        # for data in train_loader:
       input, target = data   # input為輸入數(shù)據(jù)，target為標(biāo)簽
       y_predict = model(input) #模型預(yù)測(cè)
       loss = criterion(y_predict, target)
       optimizer.zero_grad() #梯度清零
       loss.backward()#loss值反向傳播
       optimizer.step()#更新參數(shù)
       # index += 1
       if index % 100 == 0: # 每一百次保存一次模型，打印損失
           torch.save(model.state_dict(), "./model/model.pkl")   # 保存模型
           torch.save(optimizer.state_dict(), "./model/optimizer.pkl")
           print("訓(xùn)練次數(shù)為：{}，損失值為：{}".format(index, loss.item() ))

# 加載模型
if os.path.exists('./model/model.pkl'):
   model.load_state_dict(torch.load("./model/model.pkl"))#加載保存模型的參數(shù)

# 模型測(cè)試
def test():
    correct = 0     # 正確預(yù)測(cè)的個(gè)數(shù)
    total = 0   # 總數(shù)
    with torch.no_grad():   # 測(cè)試不用計(jì)算梯度
        for data in test_loader:
            input, target = data
            output = model(input)   # output輸出10個(gè)預(yù)測(cè)取值，概率最大的為預(yù)測(cè)數(shù)
            probability, predict = torch.max(input=output.data, dim=1)    # 返回一個(gè)元祖，第一個(gè)為最大概率值，第二個(gè)為最大概率值的下標(biāo)
            # loss = criterion(output, target)
            total += target.size(0)  # target是形狀為（batch_size,1)的矩陣，使用size（0）取出該批的大小
            correct += (predict == target).sum().item()  # predict 和target均為（batch_size,1)的矩陣，sum求出相等的個(gè)數(shù)
        print("測(cè)試準(zhǔn)確率為：%.6f" %(correct / total))

def test_mydata():
    image = Image.open('./test/test_two.png')   #讀取自定義手寫圖片
    image = image.resize((28, 28))   # 裁剪尺寸為28*28
    image = image.convert('L')  # 轉(zhuǎn)換為灰度圖像
    transform = transforms.ToTensor()
    image = transform(image)
    image = image.resize(1, 1, 28, 28)
    output = model(image)
    probability, predict = torch.max(output.data, dim=1)
    print("此手寫圖片值為：%d,其最大概率為：%.2f " % (predict[0], probability))
    plt.title("此手寫圖片值為：{}".format((int(predict))), fontname='SimHei')
    plt.imshow(image.squeeze())
    plt.show()

#測(cè)試識(shí)別函數(shù)
if __name__ == '__main__':
    #訓(xùn)練與測(cè)試
    for i in range(15):#訓(xùn)練和測(cè)試進(jìn)行15輪
        print({"————————第{}輪測(cè)試開始——————".format (i + 1)})
        train()
        test(）

# 測(cè)試主函數(shù)
if __name__ == '__main__':
    test_mydata()

import os
import matplotlib.pyplot as plt
import torch
from PIL import Image
from torch import nn
from torch.nn import Conv2d, Linear, ReLU
from torch.nn import MaxPool2d
from torchvision import transforms
from torchvision.datasets import MNIST
from torch.utils.data import DataLoader


# Dataset:創(chuàng)建數(shù)據(jù)集的函數(shù)；__init__:初始化數(shù)據(jù)內(nèi)容和標(biāo)簽
# __geyitem:獲取數(shù)據(jù)內(nèi)容和標(biāo)簽
# __len__:獲取數(shù)據(jù)集大小
# daataloader:數(shù)據(jù)加載類，接受來自dataset已經(jīng)加載好的數(shù)據(jù)集
# torchbision:圖形庫，包含預(yù)訓(xùn)練模型，加載數(shù)據(jù)的函數(shù)、圖片變換，裁剪、旋轉(zhuǎn)等
# torchtext:處理文本的工具包，將不同類型的額文件轉(zhuǎn)換為datasets

# 預(yù)處理：將兩個(gè)步驟整合在一起
transform = transforms.Compose({
    transforms.ToTensor(),  # 將灰度圖片像素值（0~255）轉(zhuǎn)為Tensor（0~1），方便后續(xù)處理
    # transforms.Normalize((0.1307,),(0.3081)),    # 歸一化，均值0，方差1;mean:各通道的均值std：各通道的標(biāo)準(zhǔn)差inplace：是否原地操作
})

# normalize執(zhí)行以下操作：image=(image-mean)/std?????
# input[channel] = (input[channel] - mean[channel]) / std[channel]

# 加載數(shù)據(jù)集
# 訓(xùn)練數(shù)據(jù)集
train_data = MNIST(root='./data', train=True, transform=transform, download=True)
train_loader = DataLoader(dataset=train_data, batch_size=64, shuffle=True)
# transform：指示加載的數(shù)據(jù)集應(yīng)用的數(shù)據(jù)預(yù)處理的規(guī)則，shuffle：洗牌，是否打亂輸入數(shù)據(jù)順序
# 測(cè)試數(shù)據(jù)集
test_data = MNIST(root="./data", train=False, transform=transform, download=True)
test_loader = DataLoader(dataset=test_data, batch_size=64, shuffle=True)

train_data_size = len(train_data)
test_data_size = len(test_data)
print("訓(xùn)練數(shù)據(jù)集的長(zhǎng)度：{}".format(train_data_size))
print("測(cè)試數(shù)據(jù)集的長(zhǎng)度：{}".format(test_data_size))
# print(test_data)
# print(train_data)


class MnistModel(nn.Module):
    def __init__(self):
        super(MnistModel, self).__init__()
        self.conv1 = Conv2d(in_channels=1, out_channels=10, kernel_size=5, stride=1, padding=0)
        self.maxpool1 = MaxPool2d(2)
        self.conv2 = Conv2d(in_channels=10, out_channels=20, kernel_size=5, stride=1, padding=0)
        self.maxpool2 = MaxPool2d(2)
        self.linear1 = Linear(320, 128)
        self.linear2 = Linear(128, 64)
        self.linear3 = Linear(64, 10)
        self.relu = ReLU()

    def forward(self, x):
        x = self.relu(self.maxpool1(self.conv1(x)))
        x = self.relu(self.maxpool2(self.conv2(x)))
        x = x.view(x.size(0), -1)
        x = self.linear1(x)
        x = self.linear2(x)
        x = self.linear3(x)

        return x


# 損失函數(shù)CrossentropyLoss
model = MnistModel()#實(shí)例化
criterion = nn.CrossEntropyLoss()   # 交叉熵?fù)p失，相當(dāng)于Softmax+Log+NllLoss
# 線性多分類模型Softmax,給出最終預(yù)測(cè)值對(duì)于10個(gè)類別出現(xiàn)的概率，Log:將乘法轉(zhuǎn)換為加法，減少計(jì)算量，保證函數(shù)的單調(diào)性
# NLLLoss:計(jì)算損失，此過程不需要手動(dòng)one-hot編碼，NLLLoss會(huì)自動(dòng)完成

# SGD，優(yōu)化器，梯度下降算法e
optimizer = torch.optim.SGD(model.parameters(), lr=0.14)#lr:學(xué)習(xí)率


# 模型訓(xùn)練
def train():
    # index = 0
    for index, data in enumerate(train_loader):#獲取訓(xùn)練數(shù)據(jù)以及對(duì)應(yīng)標(biāo)簽
        # for data in train_loader:
       input, target = data   # input為輸入數(shù)據(jù)，target為標(biāo)簽
       y_predict = model(input) #模型預(yù)測(cè)
       loss = criterion(y_predict, target)
       optimizer.zero_grad() #梯度清零
       loss.backward()#loss值反向傳播
       optimizer.step()#更新參數(shù)
       # index += 1
       if index % 100 == 0: # 每一百次保存一次模型，打印損失
           torch.save(model.state_dict(), "./model/model.pkl")   # 保存模型
           torch.save(optimizer.state_dict(), "./model/optimizer.pkl")
           print("訓(xùn)練次數(shù)為：{}，損失值為：{}".format(index, loss.item() ))

# 加載模型
if os.path.exists('./model/model.pkl'):
   model.load_state_dict(torch.load("./model/model.pkl"))#加載保存模型的參數(shù)


# 模型測(cè)試
def test():
    correct = 0     # 正確預(yù)測(cè)的個(gè)數(shù)
    total = 0   # 總數(shù)
    with torch.no_grad():   # 測(cè)試不用計(jì)算梯度
        for data in test_loader:
            input, target = data
            output = model(input)   # output輸出10個(gè)預(yù)測(cè)取值，概率最大的為預(yù)測(cè)數(shù)
            probability, predict = torch.max(input=output.data, dim=1)    # 返回一個(gè)元祖，第一個(gè)為最大概率值，第二個(gè)為最大概率值的下標(biāo)
            # loss = criterion(output, target)
            total += target.size(0)  # target是形狀為（batch_size,1)的矩陣，使用size（0）取出該批的大小
            correct += (predict == target).sum().item()  # predict 和target均為（batch_size,1)的矩陣，sum求出相等的個(gè)數(shù)
        print("測(cè)試準(zhǔn)確率為：%.6f" %(correct / total))


#測(cè)試識(shí)別函數(shù)
if __name__ == '__main__':
    #訓(xùn)練與測(cè)試
    for i in range(15):#訓(xùn)練和測(cè)試進(jìn)行5輪
        print({"————————第{}輪測(cè)試開始——————".format (i + 1)})
        train()
        test()


def test_mydata():
    image = Image.open('./test/test_two.png')   #讀取自定義手寫圖片
    image = image.resize((28, 28))   # 裁剪尺寸為28*28
    image = image.convert('L')  # 轉(zhuǎn)換為灰度圖像
    transform = transforms.ToTensor()
    image = transform(image)
    image = image.resize(1, 1, 28, 28)
    output = model(image)
    probability, predict = torch.max(output.data, dim=1)
    print("此手寫圖片值為：%d,其最大概率為：%.2f " % (predict[0], probability))
    plt.title("此手寫圖片值為：{}".format((int(predict))), fontname='SimHei')
    plt.imshow(image.squeeze())
    plt.show()

# 測(cè)試主函數(shù)
# if __name__ == '__main__':
#     test_mydata()