最近在學習深度學習編程,采用的深度學習框架是pytorch,看的書主要是陳云編著的《深度學習框架PyTorch入門與實踐》、廖星宇編著的《深度學習入門之PyTorch》、肖志清的《神經網絡與PyTorch實踐》,都是入門的學習材料,適合初學者。
通過近1個多月的學習,基本算是入門了,后面將深度學習與實踐。這里分享一個《神經網絡與PyTorch實踐》中對抗生成網絡的例子。它是用對抗生成網絡的方法,訓練CIFAR-10的數據集,訓練模型。
生成網絡gnet將大小為(64,11)的潛在張量轉化為大小為(3,32,32)的假數據;鑒別網絡dnet將大小為(3,32,32)的數據轉化為大小為
(1,1,1)的對數賠率張量。下面是整個模型的python代碼,包括(1)數據加載,(2)模型搭建,(3)模型訓練與模型測試。
import torch
import torch.nn as nn
import torch.nn.init as init
import torch.optim
from torch.utils.data import DataLoader
from torchvision.datasets import CIFAR10,CIFAR100
import torchvision.transforms as transforms
from torchvision.utils import save_image
from torchviz import make_dotdataset = CIFAR100(root='./data',download=True,transform= transforms.ToTensor())
dataloader = DataLoader(dataset, batch_size=64, shuffle=True)#check the data
#for batch_idx, data in enumerate(dataloader):
# real_images, _ = data
# print('real_images size = {}'.format(real_images.size()))
# batch_size = real_images.size(0)
# 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)#construct the generator and discrimiter network
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
#construct the generator
gnet= nn.Sequential(#輸入大小 == (64, 1, 1)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)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)
)#define the instance of GeneratorNet
print(gnet)
if torch.cuda.is_available():gnet.to(torch.device('cuda:0'))#construct the discrimator
n_d_feature = 64 #鑒別網絡隱藏層大小
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 = (63,16,16)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) #nn.Sigmoid()
)
print(dnet)
if torch.cuda.is_available():dnet.to(torch.device('cuda:0'))#initialization for gnet and dnet
def weights_init(m):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)gnet.apply(weights_init)
dnet.apply(weights_init)#網絡的訓練和使用
#要構造一個損失函數并對它進行優化
#定義損失
criterion = nn.BCEWithLogitsLoss()
#定義優化器
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))#用于測試的噪聲,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)#save the net to file for check
y=gnet(fixed_noises)
vise_graph = make_dot(y, params=dict(gnet.named_parameters()))
vise_graph.view(filename='gnet')y=dnet(y)
vise_graph = make_dot(y)
vise_graph.view(filename='dnet')#訓練過程
epoch_num=10
for epoch in range(epoch_num):for batch_idx, data in enumerate(dataloader):#載入本批次數據real_images,_ = databatch_size = real_images.size(0)#訓練鑒別網絡labels = torch.ones(batch_size) #設置真實數據對應標簽為1preds = dnet(real_images) #對真實數據進行判別outputs = preds.reshape(-1)dloss_real = criterion(outputs, labels) #真實數據的鑒別損失dmean_real = outputs.sigmoid().mean() #計算鑒別器將多少比例的真實數據判定為真,僅用于輸出顯示noises = torch.randn(batch_size, latent_size, 1,1) #潛在噪聲fake_images = gnet(noises) #生成假數據labels = torch.zeros(batch_size) #假數據對應標簽為0fake = fake_images.detach() #是的梯度的計算不回溯到生成網絡,可用于加快訓練速度。刪去此步,結果不變preds = dnet(fake)outputs = preds.view(-1)dloss_fake = criterion(outputs, labels) #假數據的鑒別損失dmean_fake = outputs.sigmoid().mean() #計算鑒別器將多少比例的假數據判定為真,僅用于輸出顯示dloss = dloss_real+dloss_fakednet.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是被認為時真的preds = dnet(fake_images) #讓假數據通過假別網絡outputs = preds.view(-1)gloss = criterion(outputs, labels) #從真數據看到的損失gmean_fake = outputs.sigmoid().mean() #計算鑒別器將多少比例的假數據判斷為真,僅用于輸出顯示gnet.zero_grad()gloss.backward()goptimizer.step()#輸出本步訓練結果print('[{}/{}]'.format(epoch, epoch_num)+'[{}/{}]'.format(batch_idx, len(dataloader))+'鑒別網絡損失:{:g} 生成網絡損失:{:g}'.format(dloss, gloss)+'真實數據判真比例:{:g} 假數據判真比例:{:g}/{:g}'.format(dmean_real, dmean_fake, gmean_fake))if batch_idx %100 == 0:fake = gnet(fixed_noises) #由固定潛在征糧生成假數據save_image(fake, './data/images_epoch{:02d}_batch{:03d}.png'.format(epoch, batch_idx)) #保存假數據#保存訓練的網絡
torch.save(gnet, 'gnet.pkl')
torch.save(dnet, 'dnet.pkl')
結果如下
?
總結
以上是生活随笔為你收集整理的用pytorch实现对抗生成网络的全部內容,希望文章能夠幫你解決所遇到的問題。
如果覺得生活随笔網站內容還不錯,歡迎將生活随笔推薦給好友。