DCGAN基於深度卷積生成對抗網絡的實例 ——CIFAR-10圖像的生成

代碼摘要：

1.讀取數據

2.搭建鑑別網絡和生成網絡

3.初始化網絡的權重值

4.訓練鑑別網絡和生成網絡（時間大概需要幾個小時）

root路徑可以自己設置 

"分批讀取CIFAR-10圖片並將部分批次保存爲圖片文件"

from torch.utils.data import DataLoader
from torchvision.datasets import CIFAR10
import torchvision.transforms as transforms
from torchvision.utils import save_image

dataset = CIFAR10(root='./data', download=True,
        transform=transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=64, shuffle=True)#喂入大小是把原來數據集中的多少圖片組合成一張圖片
batch_size=64
for batch_idx, data in enumerate(dataloader):
    if batch_idx==len(dataloader)-1:
        continue   
    real_images, _ = data

    print ('#{} has {} images.'.format(batch_idx, batch_size))
    if batch_idx % 100 == 0:
        path = './data/CIFAR10_shuffled_batch{:03d}.png'.format(batch_idx)
        save_image(real_images, path, normalize=True)

運行結果部分展示：

"搭建生成網絡和鑑別網絡"
"隱藏的卷積層(即除了最後的輸出卷積層外)的輸出都需要經過規範化操作"
import torch.nn as nn

# 搭建生成網絡
latent_size = 64 # 潛在大小
n_channel = 3 # 輸出通道數
n_g_feature = 64 # 生成網絡隱藏層大小
"生成網絡採用了四層轉置卷積操作"
gnet = nn.Sequential(
        # 輸入大小 = (64, 1, 1)
        #有點像互相關的反操作，(x-4)/1=1-->x=4
        nn.ConvTranspose2d(latent_size, 4 * n_g_feature, kernel_size=4,
        bias=False),
        nn.BatchNorm2d(4 * n_g_feature),
        nn.ReLU(),
        # 大小 = (256, 4, 4)
        #{x+2(填充)-4(核尺寸)+2(步長)}/2=4-->x=8
        nn.ConvTranspose2d(4 * n_g_feature, 2 * n_g_feature, kernel_size=4,
                stride=2, padding=1, bias=False),
        nn.BatchNorm2d(2 * n_g_feature),
        nn.ReLU(),
        # 大小 = (128, 8, 8)
        nn.ConvTranspose2d(2 * n_g_feature, n_g_feature, kernel_size=4,
                stride=2, padding=1, bias=False),
        nn.BatchNorm2d(n_g_feature),
        nn.ReLU(),
        # 大小 = (64, 16, 16)
        nn.ConvTranspose2d(n_g_feature, n_channel, kernel_size=4,
                stride=2, padding=1),
        nn.Sigmoid(),
        # 圖片大小 = (3, 32, 32)
        )
print (gnet)

# 搭建鑑別網絡
n_d_feature = 64 # 鑑別網絡隱藏層大小
"鑑別網絡採用了4層互相關操作"
dnet = nn.Sequential( 
        # 圖片大小 = (3, 32, 32)
        nn.Conv2d(n_channel, n_d_feature, kernel_size=4,
                stride=2, padding=1),
        nn.LeakyReLU(0.2),
        # 大小 = (64, 16, 16)
        nn.Conv2d(n_d_feature, 2 * n_d_feature, kernel_size=4,
                stride=2, padding=1, bias=False),
        nn.BatchNorm2d(2 * n_d_feature),
        nn.LeakyReLU(0.2),
        # 大小 = (128, 8, 8)
        nn.Conv2d(2 * n_d_feature, 4 * n_d_feature, kernel_size=4,
                stride=2, padding=1, bias=False),
        nn.BatchNorm2d(4 * n_d_feature),
        nn.LeakyReLU(0.2),
        # 大小 = (256, 4, 4)
        nn.Conv2d(4 * n_d_feature, 1, kernel_size=4),
        # 對數賠率張量大小 = (1, 1, 1)
        )
print(dnet)

代碼運行的部分結果：

"初始化權重值"
import torch.nn.init as init

def weights_init(m): # 用於初始化權重值的函數
    if type(m) in [nn.ConvTranspose2d, nn.Conv2d]:
        init.xavier_normal_(m.weight)
    elif type(m) == nn.BatchNorm2d:
        init.normal_(m.weight, 1.0, 0.02)
        init.constant_(m.bias, 0)
#調用apply()函數，torch.nn.Module類實例會遞歸地讓自己成爲weights_init()裏面函數的m
gnet.apply(weights_init)
dnet.apply(weights_init)

"訓練生成網絡和鑑別網絡並輸出圖片"
import torch
import torch.optim

# 損失
criterion = nn.BCEWithLogitsLoss()

# 優化器
#Adam優化器的默認學習率n=0.01,過高，應減小爲0.002，動量參數默認0.9，會造成震盪，減小爲0.5
goptimizer = torch.optim.Adam(gnet.parameters(),
        lr=0.0002, betas=(0.5, 0.999))
doptimizer = torch.optim.Adam(dnet.parameters(), 
        lr=0.0002, betas=(0.5, 0.999))

# 用於測試的固定噪聲,用來查看相同的潛在張量在訓練過程中生成圖片的變換
batch_size = 64
fixed_noises = torch.randn(batch_size, latent_size, 1, 1)

# 訓練過程
epoch_num = 10
for epoch in range(epoch_num):
    for batch_idx, data in enumerate(dataloader):
        if batch_idx==len(dataloader)-1: #剔除最後一張是(16,3,32,32)
            continue   
        # 載入本批次數據
        real_images, _ = data#real_images(64,3,32,32)
        
        # 訓練鑑別網絡
        labels = torch.ones(batch_size) # 真實數據對應標籤爲1(64,)
        preds = dnet(real_images) # 對真實數據進行判別(64,1,1,1)
      
        outputs = preds.reshape(-1)#(64,)
        dloss_real = criterion(outputs, labels) # 真實數據的鑑別器損失
        dmean_real = outputs.sigmoid().mean() # 計算鑑別器將多少比例的真數據判定爲真,僅用於輸出顯示
        
        noises = torch.randn(batch_size, latent_size, 1, 1) # 潛在噪聲(64,64,1,1)
        fake_images = gnet(noises) # 生成假數據(64,3,32,32)
        labels = torch.zeros(batch_size) # 假數據對應標籤爲0
        fake = fake_images.detach()# 使得梯度的計算不回溯到生成網絡,可用於加快訓練速度.刪去此步結果不變
        preds = dnet(fake) # 對假數據進行鑑別
        outputs = preds.view(-1)
        dloss_fake = criterion(outputs, labels) # 假數據的鑑別器損失
        dmean_fake = outputs.sigmoid().mean()
                # 計算鑑別器將多少比例的假數據判定爲真,僅用於輸出顯示
        
        dloss = dloss_real + dloss_fake # 總的鑑別器損失
        dnet.zero_grad()
        dloss.backward()
        doptimizer.step()
        
        # 訓練生成網絡
        labels = torch.ones(batch_size)
                # 生成網絡希望所有生成的數據都被認爲是真數據
        preds = dnet(fake_images) # 把假數據通過鑑別網絡
        outputs = preds.view(-1)
        gloss = criterion(outputs, labels) # 真數據看到的損失
        gmean_fake = outputs.sigmoid().mean()
                # 計算鑑別器將多少比例的假數據判定爲真,僅用於輸出顯示
        gnet.zero_grad()
        gloss.backward()
        goptimizer.step()
        
        # 輸出本步訓練結果
        if batch_idx % 100 == 0:
            print('[{}/{}]'.format(epoch, epoch_num) +
                    '[{}/{}]'.format(batch_idx, len(dataloader)) +
                    '鑑別網絡損失:{:g} 生成網絡損失:{:g}'.format(dloss, gloss) +
                    '真數據判真比例:{:g} 假數據判真比例:{:g}/{:g}'.format(
                    dmean_real, dmean_fake, gmean_fake))
            fake = gnet(fixed_noises) # 由固定潛在張量生成假數據
            save_image(fake, # 保存假數據
                    './data/images_epoch{:02d}_batch{:03d}.png'.format(
                    epoch, batch_idx))

代碼運行結果：人工停止的結果

 

生成的假圖像：

依次是第0論的0,300,600，第1輪的100