使用 GAN 自定义图像
Custom Images with GAN
我下载了这个图片集https://www.kaggle.com/jessicali9530/stanford-dogs-dataset
并将这些图像文件夹提取到我的数据文件夹中
所以现在是这样的
下面是我的代码
from __future__ import print_function
import torch.nn as nn
import torch.optim as optim
import torch.utils.data
import torchvision.datasets as dset
import torchvision.transforms as transforms
import torchvision.utils as vutils
from torch.autograd import Variable
import os
batchSize = 64 # We set the size of the batch.
imageSize = 64 # We set the size of the generated images (64x64).
# Creating the transformations
transform = transforms.Compose([transforms.Scale(imageSize), transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5,
0.5)), ]) # We create a list of transformations (scaling, tensor conversion, normalization) to apply to the input images.
# Loading the dataset
dataset = dset.ImageFolder(root='./data', transform=transform)
dataloader = torch.utils.data.DataLoader(dataset, batch_size=batchSize, shuffle=True,
num_workers=2) # We use dataLoader to get the images of the training set batch by batch.
# Defining the weights_init function that takes as input a neural network m and that will initialize all its weights.
def weights_init(m):
classname = m.__class__.__name__
if classname.find('Conv') != -1:
m.weight.data.normal_(0.0, 0.02)
elif classname.find('BatchNorm') != -1:
m.weight.data.normal_(1.0, 0.02)
m.bias.data.fill_(0)
input_vector = 100
# Create results directory
def create_dir(name):
if not os.path.exists(name):
os.makedirs(name)
# Defining the Generator
class G(nn.Module):
feature_maps = 512
kernel_size = 4
stride = 2
padding = 1
bias = False
def __init__(self):
super(G, self).__init__()
self.main = nn.Sequential(
nn.ConvTranspose2d(input_vector, self.feature_maps, self.kernel_size, 1, 0, bias=self.bias),
nn.BatchNorm2d(self.feature_maps), nn.ReLU(True),
nn.ConvTranspose2d(self.feature_maps, int(self.feature_maps // 2), self.kernel_size, self.stride, self.padding,
bias=self.bias),
nn.BatchNorm2d(int(self.feature_maps // 2)), nn.ReLU(True),
nn.ConvTranspose2d(int(self.feature_maps // 2), int((self.feature_maps // 2) // 2), self.kernel_size, self.stride,
self.padding,
bias=self.bias),
nn.BatchNorm2d(int((self.feature_maps // 2) // 2)), nn.ReLU(True),
nn.ConvTranspose2d((int((self.feature_maps // 2) // 2)), int(((self.feature_maps // 2) // 2) // 2), self.kernel_size,
self.stride, self.padding,
bias=self.bias),
nn.BatchNorm2d(int((self.feature_maps // 2) // 2) // 2), nn.ReLU(True),
nn.ConvTranspose2d(int(((self.feature_maps // 2) // 2) // 2), 3, self.kernel_size, self.stride, self.padding,
bias=self.bias),
nn.Tanh()
)
def forward(self, input):
output = self.main(input)
return output
# Creating the generator
netG = G()
netG.apply(weights_init)
class D(nn.Module):
feature_maps = 64
kernel_size = 4
stride = 2
padding = 1
bias = False
inplace = True
def __init__(self):
super(D, self).__init__()
self.main = nn.Sequential(
nn.Conv2d(3, self.feature_maps, self.kernel_size, self.stride, self.padding, bias=self.bias),
nn.LeakyReLU(0.2, inplace=self.inplace),
nn.Conv2d(self.feature_maps, self.feature_maps * 2, self.kernel_size, self.stride, self.padding,
bias=self.bias),
nn.BatchNorm2d(self.feature_maps * 2), nn.LeakyReLU(0.2, inplace=self.inplace),
nn.Conv2d(self.feature_maps * 2, self.feature_maps * (2 * 2), self.kernel_size, self.stride, self.padding,
bias=self.bias),
nn.BatchNorm2d(self.feature_maps * (2 * 2)), nn.LeakyReLU(0.2, inplace=self.inplace),
nn.Conv2d(self.feature_maps * (2 * 2), self.feature_maps * (2 * 2 * 2), self.kernel_size, self.stride,
self.padding, bias=self.bias),
nn.BatchNorm2d(self.feature_maps * (2 * 2 * 2)), nn.LeakyReLU(0.2, inplace=self.inplace),
nn.Conv2d(self.feature_maps * (2 * 2 * 2), 1, self.kernel_size, 1, 0, bias=self.bias),
nn.Sigmoid()
)
def forward(self, input):
output = self.main(input)
return output.view(-1)
# Creating the discriminator
netD = D()
netD.apply(weights_init)
# Training the DCGANs
criterion = nn.BCELoss()
optimizerD = optim.Adam(netD.parameters(), lr=0.002, betas=(0.5, 0.999))
optimizerG = optim.Adam(netG.parameters(), lr=0.002, betas=(0.5, 0.999))
nb_epochs = 25
for epoch in range(25):
for i, data in enumerate(dataloader, 0):
# 1st Step: Updating the weights of the neural network of the discriminator
netD.zero_grad()
# Training the discriminator with a real image of the dataset
real, _ = data
input = Variable(real)
target = Variable(torch.ones(input.size()[0]))
output = netD(input)
errD_real = criterion(output, target)
# Training the discriminator with a fake image generated by the generator
noise = Variable(torch.randn(input.size()[0], 100, 1, 1))
fake = netG(noise)
target = Variable(torch.zeros(input.size()[0]))
output = netD(fake.detach())
errD_fake = criterion(output, target)
# Backpropagating the total error
errD = errD_real + errD_fake
errD.backward()
optimizerD.step()
# 2nd Step: Updating the weights of the neural network of the generator
netG.zero_grad()
target = Variable(torch.ones(input.size()[0]))
output = netD(fake)
errG = criterion(output, target)
errG.backward()
optimizerG.step()
# 3rd Step: Printing the losses and saving the real images and the generated images of the minibatch every 100 steps
print('[%d/%d][%d/%d] Loss_D: %.4f Loss_G: %.4f' % (epoch, 25, i, len(dataloader), errD.data[0], errG.data[0]))
if i % 100 == 0:
vutils.save_image(real, '%s/real_samples.png' % "./results", normalize=True)
fake = netG(noise)
vutils.save_image(fake.data, '%s/fake_samples_epoch_%03d.png' % ("./results", epoch), normalize=True)
但是当我 运行 它给了我这个错误
RuntimeError: stack expects each tensor to be equal size, but got [3, 64, 85] at entry 0 and [3, 64, 80] at entry 1
这意味着问题出在 for 循环上。
如何更改 for 循环以匹配我的数据集？
我认为错误意味着它试图将图像堆叠成批次，但图像尺寸不同，即第一张图像的尺寸为 3 x 64 x 85，第二张图像的尺寸为 3 x 64 x 80。你'可能需要转换（调整大小）图像，使它们的形状都相同。
尝试使用 transforms.Resize 而不是 transforms.Scale(imageSize)，因为调整大小在具有不同高度和宽度的输入图像上表现不同。将大小参数作为元组传递：
....
transforms.Resize((imageSize, imageSize))
....
我下载了这个图片集https://www.kaggle.com/jessicali9530/stanford-dogs-dataset
并将这些图像文件夹提取到我的数据文件夹中
所以现在是这样的
下面是我的代码
from __future__ import print_function
import torch.nn as nn
import torch.optim as optim
import torch.utils.data
import torchvision.datasets as dset
import torchvision.transforms as transforms
import torchvision.utils as vutils
from torch.autograd import Variable
import os
batchSize = 64 # We set the size of the batch.
imageSize = 64 # We set the size of the generated images (64x64).
# Creating the transformations
transform = transforms.Compose([transforms.Scale(imageSize), transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5,
0.5)), ]) # We create a list of transformations (scaling, tensor conversion, normalization) to apply to the input images.
# Loading the dataset
dataset = dset.ImageFolder(root='./data', transform=transform)
dataloader = torch.utils.data.DataLoader(dataset, batch_size=batchSize, shuffle=True,
num_workers=2) # We use dataLoader to get the images of the training set batch by batch.
# Defining the weights_init function that takes as input a neural network m and that will initialize all its weights.
def weights_init(m):
classname = m.__class__.__name__
if classname.find('Conv') != -1:
m.weight.data.normal_(0.0, 0.02)
elif classname.find('BatchNorm') != -1:
m.weight.data.normal_(1.0, 0.02)
m.bias.data.fill_(0)
input_vector = 100
# Create results directory
def create_dir(name):
if not os.path.exists(name):
os.makedirs(name)
# Defining the Generator
class G(nn.Module):
feature_maps = 512
kernel_size = 4
stride = 2
padding = 1
bias = False
def __init__(self):
super(G, self).__init__()
self.main = nn.Sequential(
nn.ConvTranspose2d(input_vector, self.feature_maps, self.kernel_size, 1, 0, bias=self.bias),
nn.BatchNorm2d(self.feature_maps), nn.ReLU(True),
nn.ConvTranspose2d(self.feature_maps, int(self.feature_maps // 2), self.kernel_size, self.stride, self.padding,
bias=self.bias),
nn.BatchNorm2d(int(self.feature_maps // 2)), nn.ReLU(True),
nn.ConvTranspose2d(int(self.feature_maps // 2), int((self.feature_maps // 2) // 2), self.kernel_size, self.stride,
self.padding,
bias=self.bias),
nn.BatchNorm2d(int((self.feature_maps // 2) // 2)), nn.ReLU(True),
nn.ConvTranspose2d((int((self.feature_maps // 2) // 2)), int(((self.feature_maps // 2) // 2) // 2), self.kernel_size,
self.stride, self.padding,
bias=self.bias),
nn.BatchNorm2d(int((self.feature_maps // 2) // 2) // 2), nn.ReLU(True),
nn.ConvTranspose2d(int(((self.feature_maps // 2) // 2) // 2), 3, self.kernel_size, self.stride, self.padding,
bias=self.bias),
nn.Tanh()
)
def forward(self, input):
output = self.main(input)
return output
# Creating the generator
netG = G()
netG.apply(weights_init)
class D(nn.Module):
feature_maps = 64
kernel_size = 4
stride = 2
padding = 1
bias = False
inplace = True
def __init__(self):
super(D, self).__init__()
self.main = nn.Sequential(
nn.Conv2d(3, self.feature_maps, self.kernel_size, self.stride, self.padding, bias=self.bias),
nn.LeakyReLU(0.2, inplace=self.inplace),
nn.Conv2d(self.feature_maps, self.feature_maps * 2, self.kernel_size, self.stride, self.padding,
bias=self.bias),
nn.BatchNorm2d(self.feature_maps * 2), nn.LeakyReLU(0.2, inplace=self.inplace),
nn.Conv2d(self.feature_maps * 2, self.feature_maps * (2 * 2), self.kernel_size, self.stride, self.padding,
bias=self.bias),
nn.BatchNorm2d(self.feature_maps * (2 * 2)), nn.LeakyReLU(0.2, inplace=self.inplace),
nn.Conv2d(self.feature_maps * (2 * 2), self.feature_maps * (2 * 2 * 2), self.kernel_size, self.stride,
self.padding, bias=self.bias),
nn.BatchNorm2d(self.feature_maps * (2 * 2 * 2)), nn.LeakyReLU(0.2, inplace=self.inplace),
nn.Conv2d(self.feature_maps * (2 * 2 * 2), 1, self.kernel_size, 1, 0, bias=self.bias),
nn.Sigmoid()
)
def forward(self, input):
output = self.main(input)
return output.view(-1)
# Creating the discriminator
netD = D()
netD.apply(weights_init)
# Training the DCGANs
criterion = nn.BCELoss()
optimizerD = optim.Adam(netD.parameters(), lr=0.002, betas=(0.5, 0.999))
optimizerG = optim.Adam(netG.parameters(), lr=0.002, betas=(0.5, 0.999))
nb_epochs = 25
for epoch in range(25):
for i, data in enumerate(dataloader, 0):
# 1st Step: Updating the weights of the neural network of the discriminator
netD.zero_grad()
# Training the discriminator with a real image of the dataset
real, _ = data
input = Variable(real)
target = Variable(torch.ones(input.size()[0]))
output = netD(input)
errD_real = criterion(output, target)
# Training the discriminator with a fake image generated by the generator
noise = Variable(torch.randn(input.size()[0], 100, 1, 1))
fake = netG(noise)
target = Variable(torch.zeros(input.size()[0]))
output = netD(fake.detach())
errD_fake = criterion(output, target)
# Backpropagating the total error
errD = errD_real + errD_fake
errD.backward()
optimizerD.step()
# 2nd Step: Updating the weights of the neural network of the generator
netG.zero_grad()
target = Variable(torch.ones(input.size()[0]))
output = netD(fake)
errG = criterion(output, target)
errG.backward()
optimizerG.step()
# 3rd Step: Printing the losses and saving the real images and the generated images of the minibatch every 100 steps
print('[%d/%d][%d/%d] Loss_D: %.4f Loss_G: %.4f' % (epoch, 25, i, len(dataloader), errD.data[0], errG.data[0]))
if i % 100 == 0:
vutils.save_image(real, '%s/real_samples.png' % "./results", normalize=True)
fake = netG(noise)
vutils.save_image(fake.data, '%s/fake_samples_epoch_%03d.png' % ("./results", epoch), normalize=True)
但是当我 运行 它给了我这个错误
RuntimeError: stack expects each tensor to be equal size, but got [3, 64, 85] at entry 0 and [3, 64, 80] at entry 1
这意味着问题出在 for 循环上。 如何更改 for 循环以匹配我的数据集？
我认为错误意味着它试图将图像堆叠成批次，但图像尺寸不同，即第一张图像的尺寸为 3 x 64 x 85，第二张图像的尺寸为 3 x 64 x 80。你'可能需要转换（调整大小）图像，使它们的形状都相同。
尝试使用 transforms.Resize 而不是 transforms.Scale(imageSize)，因为调整大小在具有不同高度和宽度的输入图像上表现不同。将大小参数作为元组传递：
....
transforms.Resize((imageSize, imageSize))
....