opt.lr = 5e-4 # Initial learning rate
opt.lr_policy = 'linear' # decay policy. Availability: see options/train_options.py
opt.beta1 = 0.5 # parameter for ADAM
# Set up the loss function
opt.is_Feat = False # Whether to use feature matching loss or not
opt.lambda_feat = 1
opt.gan_mode = 'wgangp'
##############################################################################################################
if opt.gan_mode == 'wgangp':
opt.norm_D = 'instance' # Use instance normalization when using WGAN. Available: 'instance', 'batch', 'none'
else:
opt.norm_D = 'batch' # Used batch normalization otherwise
opt.activation_D = 'LeakyReLU'
opt.activation_G = 'ReLU' # The output activation function at the last layer in the decoder
opt.norm_G = 'batch'
if opt.dataset_mode == 'CIFAR10':
opt.dataroot = './data'
transform = 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)
