MachineLP的Github（欢迎follow）：https://github.com/MachineLP
MachineLP的博客目录：小鹏的博客目录
本小节使用torch搭建VAE模型，训练和测试：
（1）定义模型超参数：输入大小、隐含单元、迭代次数、批量大小、学习率。
（2）定义训练数据。
（3）定义模型（定义需要的VAE结构）。
（4）定义损失函数，选用适合的损失函数。
（5）定义优化算法（SGD、Adam等）。
（6）保存模型。
---------------------------------我是可爱的分割线---------------------------------
代码部分：
import os
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision
from torchvision import transforms
from torchvision.utils import save_image
# 判定GPU是否存在
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# 创建一个目录， 用于保存VAE输出的图像保存
sample_dir = 'samples'
if not os.path.exists(sample_dir):
os.makedirs(sample_dir)
# 模型的超参数：输入大小、隐含层、迭代次数、batch_size、学习率。
image_size = 784
h_dim = 400
z_dim = 20
num_epochs = 15
batch_size = 128
learning_rate = 1e-3
# MNIST 数据集
dataset = torchvision.datasets.MNIST(root='./data',
train=True,
transform=transforms.ToTensor(),
download=True)
# 构建数据管道， 使用自己的数据集请参考：https://blog.csdn.net/u014365862/article/details/80506147
data_loader = torch.utils.data.DataLoader(dataset=dataset,
batch_size=batch_size,
shuffle=True)
# VAE 模型
class VAE(nn.Module):
def __init__(self, image_size=784, h_dim=400, z_dim=20):
super(VAE, self).__init__()
self.fc1 = nn.Linear(image_size, h_dim)
self.fc2 = nn.Linear(h_dim, z_dim)
self.fc3 = nn.Linear(h_dim, z_dim)
self.fc4 = nn.Linear(z_dim, h_dim)
self.fc5 = nn.Linear(h_dim, image_size)
def encode(self, x):
h = F.relu(self.fc1(x))
return self.fc2(h), self.fc3(h)
# 用语两个z_dim相加。
def reparameterize(self, mu, log_var):
std = torch.exp(log_var/2)
eps = torch.randn_like(std)
return mu + eps * std
def decode(self, z):
h = F.relu(self.fc4(z))
return F.sigmoid(self.fc5(h))
def forward(self, x):
mu, log_var = self.encode(x)
z = self.reparameterize(mu, log_var)
x_reconst = self.decode(z)
return x_reconst, mu, log_var
# 定义模型。
model = VAE().to(device)
# 定义优化算法
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# 训练模型
for epoch in range(num_epochs):
for i, (x, _) in enumerate(data_loader):
# Forward pass
x = x.to(device).view(-1, image_size)
x_reconst, mu, log_var = model(x)
# 计算重构误差和KL变换
# For KL divergence, see Appendix B in VAE paper or http://yunjey47.tistory.com/43
reconst_loss = F.binary_cross_entropy(x_reconst, x, size_average=False)
kl_div = - 0.5 * torch.sum(1 + log_var - mu.pow(2) - log_var.exp())
# 后向传播+调整参数
loss = reconst_loss + kl_div
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 每10个batch打印一次数据
if (i+1) % 10 == 0:
print ("Epoch[{}/{}], Step [{}/{}], Reconst Loss: {:.4f}, KL Div: {:.4f}"
.format(epoch+1, num_epochs, i+1, len(data_loader), reconst_loss.item(), kl_div.item()))
# 模型测试部分
# 测试阶段不需要计算梯度，注意
with torch.no_grad():
# Save the sampled images
z = torch.randn(batch_size, z_dim).to(device)
out = model.decode(z).view(-1, 1, 28, 28)
save_image(out, os.path.join(sample_dir, 'sampled-{}.png'.format(epoch+1)))
# 保存重构后的图片
out, _, _ = model(x)
x_concat = torch.cat([x.view(-1, 1, 28, 28), out.view(-1, 1, 28, 28)], dim=3)
save_image(x_concat, os.path.join(sample_dir, 'reconst-{}.png'.format(epoch+1)))加餐1：在自己数据集上使用：
其中，train.txt中的数据格式：
gender/0male/0(2).jpg 1
gender/0male/0(3).jpeg 1
gender/0male/0(1).jpg 0
test.txt中的数据格式如下：
gender/0male/0(3).jpeg 1
gender/0male/0(1).jpg 0
gender/1female/1(6).jpg 1
代码部分：
import os
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms
from torchvision.utils import save_image
from PIL import Image
# 判定GPU是否存在
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# 创建一个目录， 用于保存VAE输出的图像保存
sample_dir = 'samples'
if not os.path.exists(sample_dir):
os.makedirs(sample_dir)
# 模型的超参数：输入大小、隐含层、迭代次数、batch_size、学习率。
image_size = 784
h_dim = 400
z_dim = 20
num_epochs = 15
batch_size = 2
learning_rate = 1e-3
def default_loader(path):
# 注意要保证每个batch的tensor大小时候一样的。
return Image.open(path).convert('RGB')
class MyDataset(Dataset):
def __init__(self, txt, transform=None, target_transform=None, loader=default_loader):
fh = open(txt, 'r')
imgs = []
for line in fh:
line = line.strip('\n')
# line = line.rstrip()
words = line.split(' ')
imgs.append((words[0],int(words[1])))
self.imgs = imgs
self.transform = transform
self.target_transform = target_transform
self.loader = loader
def __getitem__(self, index):
fn, label = self.imgs[index]
img = self.loader(fn)
if self.transform is not None:
img = self.transform(img)
return img,label
def __len__(self):
return len(self.imgs)
def get_loader(dataset='train.txt', crop_size=128, image_size=28, batch_size=2, mode='train', num_workers=1):
"""Build and return a data loader."""
transform = []
if mode == 'train':
transform.append(transforms.RandomHorizontalFlip())
transform.append(transforms.CenterCrop(crop_size))
transform.append(transforms.Resize(image_size))
transform.append(transforms.ToTensor())
transform.append(transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)))
transform = transforms.Compose(transform)
train_data=MyDataset(txt=dataset, transform=transform)
data_loader = DataLoader(dataset=train_data,
batch_size=batch_size,
shuffle=(mode=='train'),
num_workers=num_workers)
return data_loader
# 注意要保证每个batch的tensor大小时候一样的。
# data_loader = DataLoader(train_data, batch_size=2,shuffle=True)
data_loader = get_loader('train.txt', batch_size=batch_size)
print(len(data_loader))
test_loader = get_loader('test.txt', batch_size=batch_size)
print(len(test_loader))
# VAE 模型
class VAE(nn.Module):
def __init__(self, image_size=784, h_dim=400, z_dim=20):
super(VAE, self).__init__()
self.fc1 = nn.Linear(image_size, h_dim)
self.fc2 = nn.Linear(h_dim, z_dim)
self.fc3 = nn.Linear(h_dim, z_dim)
self.fc4 = nn.Linear(z_dim, h_dim)
self.fc5 = nn.Linear(h_dim, image_size)
def encode(self, x):
h = F.relu(self.fc1(x))
return self.fc2(h), self.fc3(h)
# 用语两个z_dim相加。
def reparameterize(self, mu, log_var):
std = torch.exp(log_var/2)
eps = torch.randn_like(std)
return mu + eps * std
def decode(self, z):
h = F.relu(self.fc4(z))
return F.sigmoid(self.fc5(h))
def forward(self, x):
mu, log_var = self.encode(x)
z = self.reparameterize(mu, log_var)
x_reconst = self.decode(z)
return x_reconst, mu, log_var
# 定义模型。
model = VAE().to(device)
# 定义优化算法
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# 训练模型
for epoch in range(num_epochs):
for i, (x, _) in enumerate(data_loader):
# Forward pass
x = x.to(device).view(-1, image_size)
x_reconst, mu, log_var = model(x)
# 计算重构误差和KL变换
# For KL divergence, see Appendix B in VAE paper or http://yunjey47.tistory.com/43
reconst_loss = F.binary_cross_entropy(x_reconst, x, size_average=False)
kl_div = - 0.5 * torch.sum(1 + log_var - mu.pow(2) - log_var.exp())
# 后向传播+调整参数
loss = reconst_loss + kl_div
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 每10个batch打印一次数据
if (i+1) % 10 == 0:
print ("Epoch[{}/{}], Step [{}/{}], Reconst Loss: {:.4f}, KL Div: {:.4f}"
.format(epoch+1, num_epochs, i+1, len(data_loader), reconst_loss.item(), kl_div.item()))
# 模型测试部分
# 测试阶段不需要计算梯度，注意
with torch.no_grad():
# Save the sampled images
z = torch.randn(batch_size, z_dim).to(device)
out = model.decode(z).view(-1, 1, 28, 28)
save_image(out, os.path.join(sample_dir, 'sampled-{}.png'.format(epoch+1)))
# 保存重构后的图片
out, _, _ = model(x)
x_concat = torch.cat([x.view(-1, 1, 28, 28), out.view(-1, 1, 28, 28)], dim=3)
save_image(x_concat, os.path.join(sample_dir, 'reconst-{}.png'.format(epoch+1)))---------------------------------我是可爱的分割线---------------------------------
总结：
本节torch实现VAE，可以自行替换需要的网络结构进行训练。
上面加餐部分需要生成自己的txt文件（数据+标签），可以参考这个，自己以前调试用的：https://github.com/MachineLP/py_workSpace/blob/master/g_img_path.py
torch系列：
2. torch02：logistic regression--MNIST识别
4. torch04：全连接神经网络--MNIST识别和自己数据集
6. torch06：ResNet--Cifar识别和自己数据集
8. torch08：RNN--word_language_model
9. torch09：variational_autoencoder(VAE)--MNIST和自己数据集
283
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
