def test_flip(self):
trans = transforms.Compose([
transforms.RandomHorizontalFlip(1.0),
transforms.RandomHorizontalFlip(0.0),
transforms.RandomVerticalFlip(0.0),
transforms.RandomVerticalFlip(1.0),
])
self.do_transform(trans)
def __init__(self,
path,
mode='train',
image_size=224,
resize_short_size=256):
super(ImageNetDataset, self).__init__(path)
self.mode = mode
self.samples = []
list_file = "train_list.txt" if self.mode == "train" else "val_list.txt"
with open(os.path.join([path, list_file]), 'r') as f:
for line in f:
_image, _label = line.strip().split(" ")
self.samples.append((_image, int(_label)))
normalize = transforms.Normalize(mean=[123.675, 116.28, 103.53],
std=[58.395, 57.120, 57.375])
if self.mode == 'train':
self.transform = transforms.Compose([
transforms.RandomResizedCrop(image_size),
transforms.RandomHorizontalFlip(),
transforms.Transpose(), normalize
])
else:
self.transform = transforms.Compose([
transforms.Resize(resize_short_size),
transforms.CenterCrop(image_size),
transforms.Transpose(), normalize
])
def test_trans_all(self):
normalize = transforms.Normalize(
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.120, 57.375], )
trans = transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
normalize,
])
self.do_transform(trans)
def test_trans_all(self):
normalize = transforms.Normalize(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.120, 57.375])
trans = transforms.Compose([
transforms.RandomResizedCrop(224), transforms.GaussianNoise(),
transforms.ColorJitter(
brightness=0.4, contrast=0.4, saturation=0.4,
hue=0.4), transforms.RandomHorizontalFlip(),
transforms.Permute(mode='CHW'), normalize
])
self.do_transform(trans)
def build_model(self):
""" DataLoader """
pad = int(30 * self.img_size // 256)
train_transform = T.Compose([
T.RandomHorizontalFlip(),
T.Resize((self.img_size + pad, self.img_size + pad)),
T.RandomCrop(self.img_size),
T.ToTensor(),
T.Normalize(mean=0.5, std=0.5),
])
test_transform = T.Compose([
T.Resize((self.img_size, self.img_size)),
T.ToTensor(),
T.Normalize(mean=0.5, std=0.5)
])
self.trainA = ImageFolder('dataset/photo2cartoon/trainA', self.img_size, train_transform)
self.trainB = ImageFolder('dataset/photo2cartoon/trainB', self.img_size, train_transform)
self.testA = ImageFolder('dataset/photo2cartoon/testA', self.img_size, test_transform)
self.testB = ImageFolder('dataset/photo2cartoon/testB', self.img_size, test_transform)
self.trainA_loader = DataLoader(self.trainA, batch_size=self.batch_size, shuffle=True)
self.trainB_loader = DataLoader(self.trainB, batch_size=self.batch_size, shuffle=True)
self.testA_loader = DataLoader(self.testA, batch_size=1, shuffle=False)
self.testB_loader = DataLoader(self.testB, batch_size=1, shuffle=False)
""" Define Generator, Discriminator """
self.genA2B = ResnetGenerator(ngf=self.ch, img_size=self.img_size, light=self.light)
self.genB2A = ResnetGenerator(ngf=self.ch, img_size=self.img_size, light=self.light)
self.disGA = Discriminator(input_nc=3, ndf=self.ch, n_layers=7)
self.disGB = Discriminator(input_nc=3, ndf=self.ch, n_layers=7)
self.disLA = Discriminator(input_nc=3, ndf=self.ch, n_layers=5)
self.disLB = Discriminator(input_nc=3, ndf=self.ch, n_layers=5)
""" Define Loss """
self.L1_loss = nn.loss.L1Loss()
self.MSE_loss = nn.loss.MSELoss()
self.BCE_loss = nn.loss.BCEWithLogitsLoss()
self.G_optim = paddle.optimizer.Adam(
learning_rate=self.lr, beta1=0.5, beta2=0.999, weight_decay=0.0001,
parameters=self.genA2B.parameters()+self.genB2A.parameters()
)
self.D_optim = paddle.optimizer.Adam(
learning_rate=self.lr, beta1=0.5, beta2=0.999, weight_decay=0.0001,
parameters=self.disGA.parameters()+self.disGB.parameters()+self.disLA.parameters()+self.disLB.parameters()
)
self.Rho_clipper = RhoClipper(0, self.rho_clipper)
self.W_clipper = WClipper(0, self.w_clipper)
def __init__(self,
data_dir,
mode='train',
image_size=224,
resize_short_size=256):
super(ImageNetDataset, self).__init__()
train_file_list = os.path.join(data_dir, 'train_list.txt')
val_file_list = os.path.join(data_dir, 'val_list.txt')
test_file_list = os.path.join(data_dir, 'test_list.txt')
self.data_dir = data_dir
self.mode = mode
normalize = transforms.Normalize(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.120, 57.375])
if self.mode == 'train':
self.transform = transforms.Compose([
transforms.RandomResizedCrop(image_size),
transforms.RandomHorizontalFlip(), transforms.Transpose(),
normalize
])
else:
self.transform = transforms.Compose([
transforms.Resize(resize_short_size),
transforms.CenterCrop(image_size), transforms.Transpose(),
normalize
])
if mode == 'train':
with open(train_file_list) as flist:
full_lines = [line.strip() for line in flist]
np.random.shuffle(full_lines)
if os.getenv('PADDLE_TRAINING_ROLE'):
# distributed mode if the env var `PADDLE_TRAINING_ROLE` exits
trainer_id = int(os.getenv("PADDLE_TRAINER_ID", "0"))
trainer_count = int(os.getenv("PADDLE_TRAINERS_NUM", "1"))
per_node_lines = len(full_lines) // trainer_count
lines = full_lines[trainer_id * per_node_lines:(
trainer_id + 1) * per_node_lines]
print(
"read images from %d, length: %d, lines length: %d, total: %d"
% (trainer_id * per_node_lines, per_node_lines,
len(lines), len(full_lines)))
else:
lines = full_lines
self.data = [line.split() for line in lines]
else:
with open(val_file_list) as flist:
lines = [line.strip() for line in flist]
self.data = [line.split() for line in lines]
def __init__(self,
path,
mode='train',
image_size=224,
resize_short_size=256):
super(ImageNetDataset, self).__init__(path)
self.mode = mode
normalize = transforms.Normalize(mean=[123.675, 116.28, 103.53],
std=[58.395, 57.120, 57.375])
if self.mode == 'train':
self.transform = transforms.Compose([
transforms.RandomResizedCrop(image_size),
transforms.RandomHorizontalFlip(),
transforms.Transpose(), normalize
])
else:
self.transform = transforms.Compose([
transforms.Resize(resize_short_size),
transforms.CenterCrop(image_size),
transforms.Transpose(), normalize
])
train_image = self.transform(train_image)
return train_image, 0
def __len__(self):
return len(self.img_names)
if __name__ == '__main__':
from paddle.vision.transforms import transforms as T
from paddle.io import DataLoader
img_size = 256
pad = 30
train_transform = T.Compose([
T.RandomHorizontalFlip(),
T.Resize((img_size + pad, img_size + pad)),
T.RandomCrop(img_size),
T.ToTensor(),
T.Normalize(mean=0.5, std=0.5)
])
dataloader = ImageFolder('dataset/photo2cartoon/trainB',
transform=train_transform)
train_loader = DataLoader(dataloader, batch_size=1, shuffle=True)
print('num: ', len(train_loader))
for i in range(300):
print(i)
try:
real_A, _ = next(trainA_iter)