import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import torchvision

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

device

device(type='cuda')

torchvision.datasets.MNIST(root, train=True, transform=None, target_transform=None, download=False)

train_ds = torchvision.datasets.CIFAR10('data', 
                                      train=True, 
                                      transform=torchvision.transforms.ToTensor(), # 將數(shù)據(jù)類型轉(zhuǎn)化為Tensor
                                      download=True)

test_ds  = torchvision.datasets.CIFAR10('data', 
                                      train=False, 
                                      transform=torchvision.transforms.ToTensor(), # 將數(shù)據(jù)類型轉(zhuǎn)化為Tensor
                                      download=True)

Files already downloaded and verified
Files already downloaded and verified

batch_size = 32

train_dl = torch.utils.data.DataLoader(train_ds, 
                                       batch_size=batch_size, 
                                       shuffle=True)

test_dl  = torch.utils.data.DataLoader(test_ds, 
                                       batch_size=batch_size)

# 取一個(gè)批次查看數(shù)據(jù)格式
# 數(shù)據(jù)的shape為：[batch_size, channel, height, weight]
# 其中batch_size為自己設(shè)定，channel，height和weight分別是圖片的通道數(shù)，高度和寬度。
imgs, labels = next(iter(train_dl))
imgs.shape

import numpy as np

 # 指定圖片大小，圖像大小為20寬、5高的繪圖(單位為英寸inch)
plt.figure(figsize=(20, 5)) 
for i, imgs in enumerate(imgs[:20]):
    # 維度縮減
    npimg = imgs.numpy().transpose((1, 2, 0))
    # 將整個(gè)figure分成2行10列，繪制第i+1個(gè)子圖。
    plt.subplot(2, 10, i+1)
    plt.imshow(npimg, cmap=plt.cm.binary)
    plt.axis('off')

torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode=‘zeros', device=None, dtype=None)

torch.nn.Linear(in_features, out_features, bias=True, device=None, dtype=None)

torch.nn.MaxPool2d(kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False)

import torch.nn.functional as F

num_classes = 10  # 圖片的類別數(shù)

class Model(nn.Module):
     def __init__(self):
        super().__init__()
         # 特征提取網(wǎng)絡(luò)
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3)   # 第一層卷積,卷積核大小為3*3
        self.pool1 = nn.MaxPool2d(kernel_size=2)       # 設(shè)置池化層，池化核大小為2*2
        self.conv2 = nn.Conv2d(64, 64, kernel_size=3)  # 第二層卷積,卷積核大小為3*3   
        self.pool2 = nn.MaxPool2d(kernel_size=2) 
        self.conv3 = nn.Conv2d(64, 128, kernel_size=3) # 第二層卷積,卷積核大小為3*3   
        self.pool3 = nn.MaxPool2d(kernel_size=2) 
                                      
        # 分類網(wǎng)絡(luò)
        self.fc1 = nn.Linear(512, 256)          
        self.fc2 = nn.Linear(256, num_classes)
     # 前向傳播
     def forward(self, x):
        x = self.pool1(F.relu(self.conv1(x)))     
        x = self.pool2(F.relu(self.conv2(x)))
        x = self.pool3(F.relu(self.conv3(x)))
        
        x = torch.flatten(x, start_dim=1)

        x = F.relu(self.fc1(x))
        x = self.fc2(x)
       
        return x

from torchinfo import summary
# 將模型轉(zhuǎn)移到GPU中（我們模型運(yùn)行均在GPU中進(jìn)行）
model = Model().to(device)

summary(model)

=================================================================
Layer (type:depth-idx)                   Param #
=================================================================
Model                                    --
├─Conv2d: 1-1                            1,792
├─MaxPool2d: 1-2                         --
├─Conv2d: 1-3                            36,928
├─MaxPool2d: 1-4                         --
├─Conv2d: 1-5                            73,856
├─MaxPool2d: 1-6                         --
├─Linear: 1-7                            131,328
├─Linear: 1-8                            2,570
=================================================================
Total params: 246,474
Trainable params: 246,474
Non-trainable params: 0
=================================================================

loss_fn    = nn.CrossEntropyLoss() # 創(chuàng)建損失函數(shù)
learn_rate = 1e-2 # 學(xué)習(xí)率
opt        = torch.optim.SGD(model.parameters(),lr=learn_rate)

# 訓(xùn)練循環(huán)
def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)  # 訓(xùn)練集的大小，一共60000張圖片
    num_batches = len(dataloader)   # 批次數(shù)目，1875（60000/32）

    train_loss, train_acc = 0, 0  # 初始化訓(xùn)練損失和正確率
    
    for X, y in dataloader:  # 獲取圖片及其標(biāo)簽
        X, y = X.to(device), y.to(device)
        
        # 計(jì)算預(yù)測(cè)誤差
        pred = model(X)          # 網(wǎng)絡(luò)輸出
        loss = loss_fn(pred, y)  # 計(jì)算網(wǎng)絡(luò)輸出和真實(shí)值之間的差距，targets為真實(shí)值，計(jì)算二者差值即為損失
        
        # 反向傳播
        optimizer.zero_grad()  # grad屬性歸零
        loss.backward()        # 反向傳播
        optimizer.step()       # 每一步自動(dòng)更新
        
        # 記錄acc與loss
        train_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()
        train_loss += loss.item()
            
    train_acc  /= size
    train_loss /= num_batches

    return train_acc, train_loss

def test (dataloader, model, loss_fn):
    size        = len(dataloader.dataset)  # 測(cè)試集的大小，一共10000張圖片
    num_batches = len(dataloader)          # 批次數(shù)目，313（10000/32=312.5，向上取整）
    test_loss, test_acc = 0, 0
    
    # 當(dāng)不進(jìn)行訓(xùn)練時(shí)，停止梯度更新，節(jié)省計(jì)算內(nèi)存消耗
    with torch.no_grad():
        for imgs, target in dataloader:
            imgs, target = imgs.to(device), target.to(device)
            
            # 計(jì)算loss
            target_pred = model(imgs)
            loss        = loss_fn(target_pred, target)
            
            test_loss += loss.item()
            test_acc  += (target_pred.argmax(1) == target).type(torch.float).sum().item()

    test_acc  /= size
    test_loss /= num_batches

    return test_acc, test_loss

epochs     = 10
train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []

for epoch in range(epochs):
    model.train()
    epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)
    
    model.eval()
    epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
    
    train_acc.append(epoch_train_acc)
    train_loss.append(epoch_train_loss)
    test_acc.append(epoch_test_acc)
    test_loss.append(epoch_test_loss)
    
    template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%，Test_loss:{:.3f}')
    print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print('Done')