我正在嘗試在簡單的 GAN 中用 png 格式的未標記自定義影像替換來自 pytorch 的標準化資料，例如 MNIST 和 CIFAR。不幸的是，大多數示例總是使用這樣的資料集，并且沒有展示將自定義資料準備和實施到 GAN 中的程序。我已將我的 png 影像（336*336，RGB）存盤在 VS Code 的作業目錄中。你能給我一個關于如何前進的建議嗎？您可以在下面找到我想用我自己的影像替換 mnist 以生成新影像的當前代碼（從#Preparing Training Data 到 #Plotting Samples：
import torch
from torch import nn
import math
import matplotlib.pyplot as plt
import torchvision
import torchvision.transforms as transforms
torch.manual_seed(111)
# DEVICE
device = ""
if torch.cuda.is_available():
device = torch.device("cuda")
else:
device = torch.device("cpu")
print(device)
***# PREPARING TRAINING DATA
transform = transforms.Compose(
[transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))]
)
# LOADING DATA
train_set = torchvision.datasets.MNIST(
root=".", train=True, download=True, transform=transform
)
# CREATE DATALOADER
batch_size = 32
train_loader = torch.utils.data.DataLoader(
train_set, batch_size=batch_size, shuffle=True
)***
# PLOTTING SAMPLES
real_samples, mnist_labels = next(iter(train_loader))
for i in range(16):
ax = plt.subplot(4, 4, i 1)
plt.imshow(real_samples[i].reshape(28, 28), cmap="gray_r")
plt.xticks([])
plt.yticks([])
plt.show()′
# IMPLEMENTING DISCRIMINATOR AND GENERATOR
class Discriminator(nn.Module):
def __init__(self):
super().__init__()
self.model = nn.Sequential(
nn.Linear(784, 1024),
nn.ReLU(),
nn.Dropout(0.3),
nn.Linear(1024, 512),
nn.ReLU(),
nn.Dropout(0.3),
nn.Linear(512, 256),
nn.ReLU(),
nn.Dropout(0.3),
nn.Linear(256, 1),
nn.Sigmoid(),
)
def forward(self, x):
x = x.view(x.size(0), 784)
output = self.model(x)
return output
discriminator = Discriminator().to(device=device)
class Generator(nn.Module):
def __init__(self):
super().__init__()
self.model = nn.Sequential(
nn.Linear(100, 256),
nn.ReLU(),
nn.Linear(256, 512),
nn.ReLU(),
nn.Linear(512, 1024),
nn.ReLU(),
nn.Linear(1024, 784),
nn.Tanh(),
)
def forward(self, x):
output = self.model(x)
output = output.view(x.size(0), 1, 28, 28)
return output
generator = Generator().to(device=device)
# TRAINING PARAMS
lr = 0.0001
num_epochs = 100
loss_function = nn.BCELoss()
optimizer_discriminator = torch.optim.Adam(discriminator.parameters(), lr=lr)
optimizer_generator = torch.optim.Adam(generator.parameters(), lr=lr)
# TRAINING LOOP
for epoch in range(num_epochs):
for n, (real_samples, mnist_labels) in enumerate(train_loader):
# Data for training the discriminator
real_samples = real_samples.to(device=device)
real_samples_labels = torch.ones((batch_size, 1)).to(
device=device
)
latent_space_samples = torch.randn((batch_size, 100)).to(
device=device
)
generated_samples = generator(latent_space_samples)
generated_samples_labels = torch.zeros((batch_size, 1)).to(
device=device
)
all_samples = torch.cat((real_samples, generated_samples))
all_samples_labels = torch.cat(
(real_samples_labels, generated_samples_labels)
)
# Training the discriminator
discriminator.zero_grad()
output_discriminator = discriminator(all_samples)
loss_discriminator = loss_function(
output_discriminator, all_samples_labels
)
loss_discriminator.backward()
optimizer_discriminator.step()
# Data for training the generator
latent_space_samples = torch.randn((batch_size, 100)).to(
device=device
)
# Training the generator
generator.zero_grad()
generated_samples = generator(latent_space_samples)
output_discriminator_generated = discriminator(generated_samples)
loss_generator = loss_function(
output_discriminator_generated, real_samples_labels
)
loss_generator.backward()
optimizer_generator.step()
# Show loss
if n == batch_size - 1:
print(f"Epoch: {epoch} Loss D.: {loss_discriminator}")
print(f"Epoch: {epoch} Loss G.: {loss_generator}")
# SAMPLES
latent_space_samples = torch.randn(batch_size, 100).to(device=device)
generated_samples = generator(latent_space_samples)
generated_samples = generated_samples.cpu().detach()
for i in range(16):
ax = plt.subplot(4, 4, i 1)
plt.imshow(generated_samples[i].reshape(28, 28), cmap="gray_r")
plt.xticks([])
plt.yticks([])
plt.show()′′′
uj5u.com熱心網友回復：
在您上面分享的示例中，您正在嘗試在單通道影像上訓練您的生成器。具體來說，您的生成器和鑒別器層被撰寫來處理維度影像，1x28x28這些維度是 MNIST 或 Fashion-MNIST 資料集的維度。
我假設您正在嘗試訓練彩色影像（3 個通道）或不同的維度，在您的情況下 - 3x336x336。在您的示例中，我添加了一個tensor transform，它首先將任何尺寸的輸入影像轉換為尺寸 - 的影像3x28x28。
以下是用于創建自定義資料集和自定義資料加載器的代碼示例。
from glob import glob
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms
from skimage import io
path = 'your/image/path'
image_paths = glob(path '/*.jpg')
img_size = 28
batch_size = 32
transform = transforms.Compose(
[
transforms.ToPILImage(),
transforms.Resize(img_size),
transforms.CenterCrop(img_size),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5]),
]
)
class ImageDataset(Dataset):
def __init__(self, paths, transform):
self.paths = paths
self.transform = transform
def __len__(self):
return len(self.paths)
def __getitem__(self, index):
image_path = self.paths[index]
image = io.imread(image_path)
if self.transform:
image_tensor = self.transform(image)
return image_tensor
dataset = ImageDataset(image_paths, transform)
train_loader = DataLoader(dataset, batch_size=batch_size, num_workers=1, shuffle=True)
資料加載器生成維度的影像張量 -batch_size x img_channels x img_dim x img_dim在本例中為 - 32x3x28x28。
import torch
import torch.nn as nn
device = 'cuda' if torch.cuda.is_available() else 'cpu'
class Discriminator(nn.Module):
def __init__(self):
super().__init__()
self.model = nn.Sequential(
nn.Linear(784*3, 2048),
nn.ReLU(),
nn.Dropout(0.3),
nn.Linear(2048, 1024),
nn.ReLU(),
nn.Dropout(0.3),
nn.Linear(1024, 512),
nn.ReLU(),
nn.Dropout(0.3),
nn.Linear(512, 256),
nn.ReLU(),
nn.Dropout(0.3),
nn.Linear(256, 1),
nn.Sigmoid(),
)
def forward(self, x):
x = x.view(x.size(0), 784*3) # change required for 3 channel image
output = self.model(x)
return output
discriminator = Discriminator().to(device=device)
class Generator(nn.Module):
def __init__(self):
super().__init__()
self.model = nn.Sequential(
nn.Linear(100, 256),
nn.ReLU(),
nn.Linear(256, 512),
nn.ReLU(),
nn.Linear(512, 1024),
nn.ReLU(),
nn.Linear(1024, 2048),
nn.ReLU(),
nn.Linear(2048, 784*3),
nn.Tanh(),
)
def forward(self, x):
output = self.model(x)
output = output.view(x.size(0), 3, 28, 28)
return output
generator = Generator().to(device=device)
# TRAINING PARAMS
lr = 0.0001
num_epochs = 100
loss_function = nn.BCELoss()
optimizer_discriminator = torch.optim.Adam(discriminator.parameters(), lr=lr)
optimizer_generator = torch.optim.Adam(generator.parameters(), lr=lr)
這是生成器和鑒別器的代碼。我對生成器和判別器做了些微修改。注意在鑒別器中添加了以下層
nn.Linear(784*3, 2048),
nn.ReLU(),
nn.Dropout(0.3),
nn.Linear(2048, 1024),
這些在生成器中
nn.Linear(1024, 2048),
nn.ReLU(),
nn.Linear(2048, 784*3)
這是生成和區分正確尺寸的影像所必需的。
最后，這是你的訓練回圈——
for epoch in range(num_epochs):
for n, real_samples in enumerate(train_loader):
# Data for training the discriminator
real_samples = real_samples.to(device=device)
real_samples_labels = torch.ones((batch_size, 1)).to(
device=device
)
latent_space_samples = torch.randn((batch_size, 100)).to(
device=device
)
print(f'Latent space samples : {latent_space_samples.shape}')
generated_samples = generator(latent_space_samples)
generated_samples_labels = torch.zeros((batch_size, 1)).to(
device=device
)
all_samples = torch.cat((real_samples, generated_samples))
print(f'Real samples : {real_samples.shape}, generated samples : {generated_samples.shape}')
all_samples_labels = torch.cat(
(real_samples_labels, generated_samples_labels)
)
# Training the discriminator
discriminator.zero_grad()
output_discriminator = discriminator(all_samples)
loss_discriminator = loss_function(
output_discriminator, all_samples_labels
)
loss_discriminator.backward()
optimizer_discriminator.step()
# Data for training the generator
latent_space_samples = torch.randn((batch_size, 100)).to(
device=device
)
# Training the generator
generator.zero_grad()
generated_samples = generator(latent_space_samples)
output_discriminator_generated = discriminator(generated_samples)
loss_generator = loss_function(
output_discriminator_generated, real_samples_labels
)
loss_generator.backward()
optimizer_generator.step()
# Show loss
if n == batch_size - 1:
print(f"Epoch: {epoch} Loss D.: {loss_discriminator}")
print(f"Epoch: {epoch} Loss G.: {loss_generator}")
這是有效的，因為影像從784*3到3*28*28維度被重新塑造。
這可行，但如果您正在處理 3 個通道的影像，則需要在生成器和鑒別器中撰寫ConvTranspose2d和Conv2d操作，分別對影像進行上采樣和下采樣。
ConvTranspose2d如果您對使用和處理多維影像的示例感興趣Conv2d，這里是 - https://drive.google.com/file/d/1gYiBHPu-r3kialO0klsTdE2RjBR50rMs/view?usp=sharing。要處理不同尺寸的影像，您必須修改生成器和鑒別器類中的層。
轉載請註明出處，本文鏈接：https://www.uj5u.com/houduan/497125.html