def __init__(self, args):
self.args = args
self.rvs = args.rvs
self.insp = args.insp
self.inch = args.inch
self.outf = args.outf
self.transformer = transforms.RandomChoice([
transforms.Compose([transforms.ToPILImage(), transforms.ColorJitter(brightness=0.1), transforms.ToTensor()]),
transforms.Compose([transforms.ToPILImage(), transforms.ColorJitter(contrast=0.1), transforms.ToTensor()]),
transforms.Compose([transforms.ToPILImage(), transforms.ColorJitter(saturation=0.1), transforms.ToTensor()]),
transforms.Compose([transforms.ToPILImage(), transforms.RandomRotation(degrees=10, resample=False, expand=False, center=None), transforms.ToTensor()]),
transforms.Compose([transforms.ToPILImage(), transforms.RandomHorizontalFlip(p=1), transforms.ToTensor()]),
])
self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
self.D = D(insp=args.insp, inch=args.inch, outf=args.outf).to(self.device)
self.G = G(rvs=args.rvs).to(self.device)
self.criterion = nn.BCELoss()
self.optimizerD = torch.optim.Adam(self.D.parameters(), lr=args.lr, betas=(args.beta, 0.999))
self.optimizerG = torch.optim.Adam(self.G.parameters(), lr=args.lr, betas=(args.beta, 0.999))
self.test_noise = torch.randn(args.grid_w * args.grid_h, args.rvs, 1, 1).to(device=self.device)
self.real_label = 1
self.fake_label = 0
def get_transforms(size):
base_transforms = transforms.Compose([transforms.Resize(size)])
additional_transforms = transforms.Compose([
transforms.RandomHorizontalFlip(p=0.5),
# transforms.RandomApply([transforms.RandomRotation(degrees=5)], p=0.5),
transforms.RandomChoice(
[transforms.CenterCrop(size),
transforms.RandomCrop(size)]),
transforms.RandomApply([
transforms.ColorJitter(
brightness=0.2, contrast=(0.9, 1.2), saturation=0.3, hue=0.01)
],
p=0.5),
transforms.ToTensor(),
# transforms.Normalize(means, stds),
Rescale(),
])
return base_transforms, additional_transforms
def RandomChoice(self, **args):
return self._add(transforms.RandomChoice(**args))
from torch import nn, optim
from torchvision.transforms import transforms
import torchvision.datasets as datasets
from PIL import ImageFile
from PIL import Image
import random
import os
car_file = './train'
img_transforms = transforms.Compose([
transforms.RandomChoice([
transforms.RandomResizedCrop((768, 1024),
scale=(0.8, 1.0),
ratio=(0.75, 1.3333333),
interpolation=2),
transforms.RandomHorizontalFlip(p=0.2),
transforms.ColorJitter(brightness=random.uniform(0.8, 1.2),
contrast=random.uniform(0.8, 1.2),
saturation=random.uniform(0.8, 1.2)),
transforms.RandomGrayscale(p=0.1)
])
])
img_dataset = datasets.ImageFolder(car_file, transform=img_transforms)
for idx, (img_path, img_label) in enumerate(img_dataset.imgs):
img_name = img_path.split('/')[-1]
img = Image.open(img_path)
img_transformed = img_transforms(img)
img_transformed.show()
'여': '1'}
classes_dict = {'00': 0, # 20대 남자
'01': 1, # 20대 여자
'10': 2, # 30대 남자
'11': 3, # 30대 여자
'20': 4, # 40대 남자
'21': 5, # 40대 여자
'30': 6, # 50대 남자
'31': 7} # 50대 여자
train_transforms = transforms.Compose([
transforms.Resize((224, 224)),
transforms.RandomHorizontalFlip(),
transforms.RandomChoice([
transforms.ColorJitter(0.2, 0.2, 0.2, 0.2),
]),
transforms.ToTensor(),
transforms.Normalize((0.4452, 0.4457, 0.4464), (0.2592, 0.2596, 0.2600)),
])
train_dataset = ImageFolder(root='./data/image', transform=train_transforms) # change image directory
train_loader = DataLoader(train_dataset, batch_size=8, shuffle=True, num_workers=0)
model = EfficientNet.from_pretrained('efficientnet-b0', num_classes=8)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.0001, weight_decay=0.00001)
for epoch in range(30):
running_loss =0.0
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
plt.show()
if __name__ == '__main__':
transform = transforms.Compose([
transforms.RandomHorizontalFlip(),
transforms.RandomAffine(5,
translate=(2 / 32, 2 / 32),
scale=(0.95, 1.05),
resample=PIL.Image.NEAREST),
transforms.ToTensor(),
transforms.RandomChoice([
transforms.Normalize((0.5, 0.5, 0.5), (0.9, 0.9, 0.9)),
transforms.Normalize((0.5, 0.5, 0.5), (0.7, 0.7, 0.7)),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
])
transform_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
])
trainset = torchvision.datasets.CIFAR10(root='./data',
train=True,
download=True,
transform=transform)
trainloader = torch.utils.data.DataLoader(trainset,
batch_size=4,